The first two authors contributed equally to this article.
ABSTRACT
Introduction
Artificial intelligence (AI) has significant potential to improve health outcomes in oncology. However, as AI utility increases, it is imperative to ensure that these models do not systematize racial and ethnic bias and further perpetuate disparities in health. This scoping review evaluates the transparency of demographic data reporting and diversity of participants included in published clinical studies utilizing AI in oncology.
Methods
We utilized PubMed to search for peer-reviewed research articles published between 2016 and 2021 with the query type “(“deep learning” or “machine learning” or “neural network” or “artificial intelligence”) and (“neoplas$” or “cancer$” or “tumor$” or “tumour$”).” We included clinical trials and original research studies and excluded reviews and meta-analyses. Oncology-related studies that described data sets used in training or validation of the AI models were eligible. Data regarding public reporting of patient demographics were collected, including age, sex at birth, and race. We used descriptive statistics to analyze these data across studies.
Results
Out of 220 total studies, 118 were eligible and 47 (40%) had at least one described training or validation data set publicly available. 69 studies (58%) reported age data for patients included in training or validation sets, 60 studies (51%) reported sex, and six studies (5%) reported race. Of the studies that reported race, a range of 70.7%–93.4% of individuals were White. Only three studies reported racial demographic data with greater than two categories (i.e. “White” vs. “non-White” or “White” vs. “Black”).
Conclusions
We found that a minority of studies (5%) analyzed reported racial and ethnic demographic data. Furthermore, studies that did report racial demographic data had few non-White patients. Increased transparency regarding reporting of demographics and greater representation in data sets is essential to ensure fair and unbiased clinical integration of AI in oncology.
1 Introduction
Artificial intelligence (AI) algorithms, which broadly include those implementing machine learning, neural networks, and/or deep learning methods, have great potential to revolutionize oncology [1, 2]. Recent years have seen a substantial rise in research, implementation, and marketing for AI applications across the cancer care continuum, including screening, diagnosis, prognostication, patient decision support, treatment, and surveillance [1, 2]. For example, these advances range from enhanced methods of imaging and pathologic assessment for diagnosis to integration of genomics, biomarkers, and tumor profiling in predictive models for treatment response, as well as improved tumor segmentation and dose optimization in radiation therapy planning [3-5].
One crucial factor in the development of these tools is the utilization of high-quality, representative datasets. The data used to train and validate a model directly influence its potential applications [6]. It is thus essential that datasets reflect a broad spectrum of real-world scenarios. When datasets are flawed or lacking in diversity—algorithms learn to internalize these patterns as ground truth, reinforcing biases from the dataset into their predictions. Accordingly, various case studies in recent years have highlighted the potential of AI to reproduce and even amplify structural inequities and long-standing disparities in healthcare [7-12].
In response to this growing concern, international research consortiums such as the Consolidated Standards of Reporting Trials (CONSORT-AI) and regulatory bodies such as the US Food and Drug Administration (FDA), which control entry of all medical devices into the US market, have developed frameworks and workgroups for the safe and effective development of AI in medicine [13-15]. Their guidelines have called for improved generalizability and validity of test datasets, increased transparency for users, collaboration with clinicians, and real-world monitoring of post-marketing performance [16, 17]. While absolute representation may be impossible to implement, a central mitigation strategy includes the characterization of datasets, calling on developers to make relevant information on the diversity of patient training sets and outcome measures available to the community of physicians who are responsible for interpreting information from these algorithms for clinical use so they may be aware of any potential biases.
As the use of AI rapidly increases in medicine, it is imperative to ensure that these models do not systematize racial and ethnic bias and further perpetuate disparities in health. Given these advancements in AI and well-established cancer disparities based on minority and medically underserved statuses [18], we sought to investigate the role of AI models in propagating such disparities. The goals of this scoping review were twofold: first, to determine the transparency and availability of demographic information—predominantly race, as well as sex and age—in training and validation datasets used in AI models within published oncologic studies; and second, to evaluate the diversity of these datasets to identify potential performance biases and opportunities for improvement, with the aim of promoting more equitable health outcomes among cancer patients.
2 Methods
To evaluate the transparency of demographic data reporting and diversity of participants included in training and validation sets in published clinical studies utilizing AI in oncology, we utilized a scoping review approach to identify current literature in AI development. A scoping review approach was selected consistent with previous studies that have investigated the racial and ethnic disparities among AI algorithms used in clinical care [19]. Additionally, we utilized a scoping review to identify the publications utilizing AI models for oncology research, to determine the transparency of demographic data in training/validation sets, and to determine areas of potential bias and disparities [20].
In this review, we used a PubMed extraction to search for peer-reviewed research articles published between 2016 and 2021. Eligibility criteria included published trials of AI models for oncology research containing any age group and all cancer types, including solid and liquid tumors. To identify these articles, we searched the database with the query type “(“deep learning” or “machine learning” or “neural network” or “artificial intelligence”) AND (“neoplas$” or “cancer$” or “tumor$” or “tumor$”).” Oncology-related article types in English including clinical trials, clinical studies, and randomized controlled trials were filtered for. In addition to these criteria, additional eligibility criteria included that the manuscript must have utilized either training sets and/or validation sets for the AI development in the main text. Furthermore, the papers must have presented AI models that had been internally or externally validated. We excluded reviews, systematic reviews, books, documents, and meta-analyses. Additionally, we excluded abstract-only publications. Overall, we identified 118 studies that met our criteria (Figure 1).
Inclusion and exclusion criteria to select eligible articles for the scoping review. Two hundred and seventeen articles were screened for eligibility, and 118 overall were eligible. Ninety-nine studies were excluded for not publicly reporting the full text, no AI models, no training or validation sets in the methods, and not oncology-related.
Three investigators (AD, TC, CA) screened studies to determine if they met the above eligibility criteria and to ensure that the full text of these studies were available. The investigators then analyzed the domain of cancer type in each study and determined if the articles publicly reported the training and validating sets (Figure 2). If so, the number of training and validation sets that each study reported was collected. If a study reported multiple separate validation sets, then these datasets were also separated in our analysis.
Domains of cancer included in the AI models. Breast cancer (n = 19) was the most represented in the studies analyzed in this scoping review, followed by gastrointestinal (n = 16), and head and neck/skin (n = 16). Hematologic (n = 4) cancer was the least represented.
The researchers also determined if the studies publicly reported patient demographics for the training and validating sets used to create the respective AI models, including age, sex at birth, and race. Age, sex at birth, and race were recorded for all patients in each training and validation set. Descriptive statistics, including the sample size, mean and median ages, weighted means of age, percent of women versus men, and percentages of race categories, were all calculated for each training and validation set for every study individually. Demographic data, including the mean and median ages, percent of women versus men, and percentages of race categories, were also calculated across studies.
3 Results
Out of 220 total studies, 118 were eligible and 47 had at least one described training or validation data set [21-132]. All studies were published between 2016 and 2021. The main study characteristics, including cancer types, mean ages, and sex distribution, both overall and stratified by training and validation sets, are shown in (Table 1) and cancer types are shown in (Figure 2).
TABLE 1.
Study characteristics. This table describes the publication dates, cancer types described, mean ages, and sex distribution in the articles that published their training/validation sets and/or reported age and sex distribution data. We describe this data for training sets, validation sets, and overall across all datasets.
Training set
Validation sets
Overall
Years published
2016–2021
2016–2021
2016–2021
Cancer types (%)
Breast
16.24
8.11
15.22
Central nervous system
7.69
8.11
0.00
Colorectal
11.11
18.92
17.39
Gastrointestinal
13.68
21.62
19.57
Genitourinary
12.82
10.81
10.87
Head and neck/skin
13.68
5.41
6.52
Hematologic
4.27
8.11
6.52
Lung
11.97
16.22
17.39
Multiple cancer types
8.55
2.70
6.52
Mean age (years)
56.6 ± 7.2
55.4 ± 11.7
56.8 ± 11.01
Sex distribution
49.1% Female
50.9% Male
54.2% Female
45.8% Male
51.5% Female
48.5% Male
Of these 118 eligible articles, 69 studies (58%) reported age data for patients who were included in training or validation sets. Across studies, age ranged from 16 days to 96 years For studies that reported mean age, the overall mean age of participants was 56.8 ± 11.0 years. The mean age of those used in the training sets was 56.6 ± 7.2 years, and the mean age of those used in the validation sets was 55.4 ± 11.7 years.
Additionally, 60 studies (51%) reported sex data for the participants. Across studies, 47.4% of patients included in studies with reported sex were male, and 52.6% were female (Figure 3). Thirty-eight studies (63.3%) that reported sex included a majority of males, and 22 studies (36.7%) had a majority of females. Among the training sets, 49.1% of participants were female, and 50.9% were male. Regarding the validation sets, 54.2% of participants were female, and 45.8% were male.
Male and female participants in studies that reported sex. Studies included 47.4% males and 52.6% females.
Among the 118 studies, only six studies (5.0%) reported patient race in at least one validation or training set, while 112 studies (95.0%) failed to report this data (Figure 4). We assessed these six studies, and a complete breakdown of racial demographics in the six studies that reported race is shown in (Table 2) [133-138]. Within these studies that reported race, 70.7%–93.4% of individuals were White. Overall, 87.8% (n = 13,501) of participants included in the training or validation sets for these articles were White, while 12.2% (n = 1868) of participants were non-White (Figure 5). The total counts in each racial category included 13,501 White, 1868 non-White, 507 Black, 300 Hispanic, 92 Asian and 189 other patients. The overall median percentage of non-white individuals across these studies was 14.4%.
Percentages of studies that reported race. Out of 118 studies analyzed, six (5.0%) reported the racial demographics of the participants included in their training sets and/or validation sets, while 112 (95.0%) studies omitted this information.
TABLE 2.
Breakdown of racial demographics in studies that reported race. In the six studies that reported racial demographics for their training and/or validation sets, 88% of participants (n = 13,501) were White while 12% (n = 1868) were non-White. The total sum of each racial category included 13,501 White, 1868 non-White, 507 Black, 300 Hispanic, 92 Asian, and 189 other patients. Out of these six studies, two (Study 1 and Study 6) utilized the categories White versus non-White, while the other four utilized the categories White, Black, Hispanic, Asian, and other.
Percentage of white versus non-white patients in studies that reported race. In the six studies that reported race, 87.8% of participants included in the training and/or validation sets were White while 12.2% were non-White.
Regarding the non-White racial category data, only four studies (3.4%) reported racial demographic data with more than two categories (i.e., “White” vs. “non-White” or “White” vs. “Black”). Two studies [133, 138] utilized the categories White versus non-White, while the other four utilized the categories White, Black, Hispanic, Asian, and other.
4 Discussion
As the influence of AI in medicine continues to grow, it is imperative to hold the application of these technologies to high standards to prevent negative impacts on patients and communities. To date, there is relatively little literature investigating avenues for bias in models used in healthcare and medicine; this scoping review aims to probe that question as it relates to studies in oncology. We analyzed 118 studies utilizing AI technology for machine-based learning and neural networks in oncology to assess for transparency in the reporting of, and representation within, demographic data of training and validation sets. Of these, 47 studies (40%) had at least one training or validation set published and publicly available. With regard to the reporting of demographic information, while over half of all studies reported on the sex and/or age of the participants included in their training or validation sets (58% and 51%, respectively), we found that only six studies (5%) reported race. Of these six, four studies reported on racial demographic data utilizing specific racial categories rather than the binary categorizations of “White” versus “non-White.” Across these six studies overall, 88% of patients included in the training and/or validation sets were White.
These results point to two primary needs that must be addressed in the utilization of AI in oncology. First, greater transparency in the reporting of this data is needed to assess representation in the training and validation of these models and further determine ways in which they may be perpetuating inequities against medically underserved populations. The implementation of clear guidelines and explicit requirements regarding these standards are needed to mitigate potential bias of AI technology in medicine. Required reporting of race, age, and sex characteristics among models is an important start to addressing these inequities. This is because studies with a lack of representation can be easily identified and potentially modified. However, it may not be fully sufficient to address disparities. This is because, as shown in these results, the studies that did report racial demographics utilized datasets that showed a general lack of diversity, indicating a need for more representative datasets. An increasing number of diverse training and validation sets is imperative to train machine learning and neural networks to become competent in caring for minority populations. Important repercussions for a lack of reporting include the propagation of racial disparities among health outcomes in cancer patients.
Given the ways in which structural inequities already impact cancer care, such as through barriers in access to care and patients of color presenting with later stages of disease at diagnosis [139], it is important to ensure that the rollout of AI technology does not embed the continuation of disparity into its algorithm. As such, AI models that are trained on primarily White patient datasets, such as those we identified in this study, are concerning for their lack of diversity. Without addressing this issue, structural inequities that are reflected in training and validation sets can all too easily manifest in the exacerbation of tangible health disparities among non-White individuals.
There have been numerous accounts of AI model bias contributing to the systemization of structural inequities in healthcare. For example, one study found that a widely used algorithm gave Black patients the same risk score as White patients, despite the Black patients presenting as considerably sicker, leading to fewer resources being provided to them [7]. This bias was found to be due to the algorithm using healthcare cost as a proxy for health despite unequal access to care. This study highlighted the importance of label choice and how it is imperative to remain mindful of structural inequities the chosen labels may reflect as not to propagate these further.
Another study investigating algorithmic underdiagnosis in chest X-ray pathology classification using three large, public datasets found consistent underdiagnosis of diseases in underserved patient populations, such as female patients, Black patients, Hispanic patients, younger patients, and patients of lower socioeconomic status [8]. This effect was compounded for intersectional underserved subpopulations. Such biases can lead to the perpetuation of delays in access to care.
On a broader scale, several other reviews investigating AI datasets have similarly found a lack of transparency and representation, indicating that this is a ubiquitous issue not limited to oncology. For example, a 2021 scoping review on AI use in dermatology by Daneshjou et al. reported a lack of dataset characterization and transparency, nonstandard and unverified disease labels, and an inability to assess patient diversity in the testing and development of the models used [19]. Furthermore, a 2022 systematic review on randomized clinical trials (RCTs) of ML interventions in healthcare by Plana et al. found that there was a high degree of variability in study adherence to CONSORT-AI reporting standards, as well as variability in risk of bias and an overall lack of participants from underrepresented minority groups among studies that reported race and ethnicity data [140].
To date, there are a limited number of studies evaluating AI datasets in oncology. Oncology is a field driven by innovation—however, the issue of the lack of diversity in cancer clinical trials is a factor severely limiting the generalizability of trial results, particularly for African American and Hispanic patients [141]. AI is a novel, powerful technology that will likely significantly impact the future of oncology research and practice. As such, the implementation of AI in oncology necessitates diversity in datasets and transparency in demographic reporting. By providing insight into the existing body of literature on this topic, we hope to build awareness of important considerations for clinicians and researchers as the use of AI becomes more widespread.
It is imperative to center equity in the implementation of AI in healthcare and medicine. The training and validation sets used to generate these AI models can profoundly impact their performance; thus, these datasets must be robust and representative of diverse populations to avoid model bias and subsequent perpetuation of health disparities. While AI has the potential to have positive impacts across the spectrum of cancer care, its utilization must be approached cautiously and conscientiously. As discussed, model bias can have disastrous effects on patient care, especially if the algorithms or datasets used are reflective of structural inequities in healthcare. Based on our findings, many studies do not make their datasets publicly available, and a large majority do not report on the race of participants used in the training and validation of these models. Furthermore, among the studies that did report race, the datasets used were concerning for their lack of diversity. Implementing standardized guidelines to increase transparency in the reporting of the demographics of participants included in the training and validation of AI models, as well as ensuring representation among the datasets used in this process, are two important steps in addressing the pitfalls of AI utilization in medicine.
5 Limitations
As a scoping review, this study was limited by publications that were available on PubMed with the full text accessible. Additionally, many studies did not publish the training or validation sets, so we could not assess the demographic breakdown of these studies. Additionally, artificial intelligence is broadly defined here as encompassing machine learning, deep learning, and/or neural networks. However, this is consistent with scientific literature and industry discourse. This study does not explicitly include studies employing natural language processing. Furthermore, we focused our research on AI models used in implementing machine learning and neural networks for oncology-related pursuits. These findings do not extend to other uses for AI, such as large language models.
6 Conclusion
This scoping review of AI-based interventions utilized in oncology reveals two primary concerns: first, the lack of transparency in the reporting of racial demographics of patients included in the training and validation of these models and second, the issue of homogeneous datasets. Based on the few studies that reported racial demographics, datasets need to be more inclusive of non-White patient populations. This lack of racial diversity is concerning for the potential perpetuation of racial and ethnic bias in these models. Instituting ubiquitous AI reporting guidelines for demographic reporting, as well as the utilization of datasets that are reflective of diverse populations, may ameliorate some of these concerns and promote greater inclusion in these studies.
Author Contributions
Anjali J. D'Amiano: conceptualization (lead), data curation (lead), formal analysis (lead), investigation (lead), methodology (lead), project administration (lead), resources (lead), validation (lead), visualization (lead), writing – original draft (lead), writing – review and editing (lead). Tia Cheunkarndee: conceptualization (equal), data curation (equal), formal analysis (equal), investigation (equal), methodology (equal), resources (equal), supervision (equal), validation (equal), visualization (equal), writing – original draft (equal), writing – review and editing (supporting). Chinenye Azoba: conceptualization (equal), data curation (equal), investigation (equal). Krista Y. Chen: writing – original draft (supporting), writing – review and editing (supporting). Raymond H. Mak: supervision (equal), validation (equal), writing – review and editing (equal). Subha Perni: conceptualization (equal), data curation (equal), formal analysis (equal), funding acquisition (equal), project administration (lead), supervision (lead).
Acknowledgements
No sources of funding.
Ethics Statement
This study adheres to the editorial policies and ethical considerations required by Cancer Medicine. This study does not include human studies and subjects, photographs with identifiable patients, or animal studies.
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
1C. Luchini, A. Pea, and A. Scarpa, “Artificial Intelligence in Oncology: Current Applications and Future Perspectives,” British Journal of Cancer126, no. 1 (2022): 4–9, https://doi.org/10.1038/s41416-021-01633-1.
2J. T. Shreve, S. A. Khanani, and T. C. Haddad, “Artificial Intelligence in Oncology: Current Capabilities, Future Opportunities, and Ethical Considerations,” American Society of Clinical Oncology Educational Book42 (2022): 842–851, https://doi.org/10.1200/EDBK_350652.
3P. R. Liu, L. Lu, J. Y. Zhang, T. T. Huo, S. X. Liu, and Z. W. Ye, “Application of Artificial Intelligence in Medicine: An Overview,” Current Medical Science41, no. 6 (2021): 1105–1115, https://doi.org/10.1007/s11596-021-2474-3.
4B. Bhinder, C. Gilvary, N. S. Madhukar, and O. Elemento, “Artificial Intelligence in Cancer Research and Precision Medicine,” Cancer Discovery11, no. 4 (2021): 900–915, https://doi.org/10.1158/2159-8290.CD-21-0090.
6M. Mittermaier, M. M. Raza, and J. C. Kvedar, “Bias in AI-Based Models for Medical Applications: Challenges and Mitigation Strategies,” NPJ Digital Medicine6, no. 1 (2023): 113, https://doi.org/10.1038/s41746-023-00858-z.
7Z. Obermeyer, B. Powers, C. Vogeli, and S. Mullainathan, “Dissecting Racial Bias in an Algorithm Used to Manage the Health of Populations,” Science366, no. 6464 (2019): 447–453, https://doi.org/10.1126/science.aax2342.
8L. Seyyed-Kalantari, H. Zhang, M. B. A. McDermott, I. Y. Chen, and M. Ghassemi, “Underdiagnosis Bias of Artificial Intelligence Algorithms Applied to Chest Radiographs in Under-Served Patient Populations,” Nature Medicine27, no. 12 (2021): 2176–2182, https://doi.org/10.1038/s41591-021-01595-0.
9A. Esteva, B. Kuprel, R. A. Novoa, et al., “Dermatologist-Level Classification of Skin Cancer With Deep Neural Networks,” Nature542, no. 7639 (2017): 115–118, https://doi.org/10.1038/nature21056.
10D. Cirillo, S. Catuara-Solarz, C. Morey, et al., “Sex and Gender Differences and Biases in Artificial Intelligence for Biomedicine and Healthcare,” NPJ Digital Medicine3, no. 1 (2020): 81, https://doi.org/10.1038/s41746-020-0288-5.
11M. A. Gianfrancesco, S. Tamang, J. Yazdany, and G. Schmajuk, “Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data,” JAMA Internal Medicine178, no. 11 (2018): 1544–1547, https://doi.org/10.1001/jamainternmed.2018.3763.
12A. S. Adamson and A. Smith, “Machine Learning and Health Care Disparities in Dermatology,” JAMA Dermatology154, no. 11 (2018): 1247–1248, https://doi.org/10.1001/jamadermatol.2018.2348.
13X. Liu, S. Cruz Rivera, D. Moher, et al., “Reporting Guidelines for Clinical Trial Reports for Interventions Involving Artificial Intelligence: The CONSORT-AI Extension,” Nature Medicine26, no. 9 (2020): 1364–1374, https://doi.org/10.1038/s41591-020-1034-x.
14US Food and Drug Administration, “Using Artifical Intelligence & Machine Learning in the Development of Drug & Biological Products,” published online 2021, https://www.fda.gov/media/167973/download.
15V. Muralidharan, B. A. Adewale, C. J. Huang, et al., “A Scoping Review of Reporting Gaps in FDA-Approved AI Medical Devices,” NPJ Digital Medicine7, no. 1 (2024): 273, https://doi.org/10.1038/s41746-024-01270-x.
16E. Wu, K. Wu, R. Daneshjou, D. Ouyang, D. E. Ho, and J. Zou, “How Medical AI Devices Are Evaluated: Limitations and Recommendations From an Analysis of FDA Approvals,” Nature Medicine27, no. 4 (2021): 582–584, https://doi.org/10.1038/s41591-021-01312-x.
17J. Wiens, S. Saria, M. Sendak, et al., “Do no Harm: A Roadmap for Responsible Machine Learning for Health Care,” Nature Medicine25, no. 9 (2019): 1337–1340, https://doi.org/10.1038/s41591-019-0548-6.
19R. Daneshjou, M. P. Smith, M. D. Sun, V. Rotemberg, and J. Zou, “Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review,” JAMA Dermatology157, no. 11 (2021): 1362–1369, https://doi.org/10.1001/jamadermatol.2021.3129.
20Z. Munn, M. D. J. Peters, C. Stern, C. Tufanaru, A. McArthur, and E. Aromataris, “Systematic Review or Scoping Review? Guidance for Authors When Choosing Between a Systematic or Scoping Review Approach,” BMC Medical Research Methodology18, no. 1 (2018): 143, https://doi.org/10.1186/s12874-018-0611-x.
21Z. Zhu, M. Harowicz, J. Zhang, et al., “Deep Learning Analysis of Breast MRIs for Prediction of Occult Invasive Disease in Ductal Carcinoma In Situ,” Computers in Biology and Medicine115 (2019): 103498, https://doi.org/10.1016/j.compbiomed.2019.103498.
22Z. Zhu, E. Albadawy, A. Saha, J. Zhang, M. R. Harowicz, and M. A. Mazurowski, “Deep Learning for Identifying Radiogenomic Associations in Breast Cancer,” Computers in Biology and Medicine109 (2019): 85–90, https://doi.org/10.1016/j.compbiomed.2019.04.018.
23W. Zhou, L. Yao, H. Wu, et al., “Multi-Step Validation of a Deep Learning-Based System for the Quantification of Bowel Preparation: A Prospective, Observational Study,” Lancet Digital Health3, no. 11 (2021): e697–e706, https://doi.org/10.1016/S2589-7500(21)00109-6.
24Y. Zhang, E. M. Lobo-Mueller, P. Karanicolas, S. Gallinger, M. A. Haider, and F. Khalvati, “Improving Prognostic Performance in Resectable Pancreatic Ductal Adenocarcinoma Using Radiomics and Deep Learning Features Fusion in CT Images,” Scientific Reports11, no. 1 (2021): 1378, https://doi.org/10.1038/s41598-021-80998-y.
25Y. Zhang, X. Lv, J. Qiu, et al., “Deep Learning With 3D Convolutional Neural Network for Noninvasive Prediction of Microvascular Invasion in Hepatocellular Carcinoma,” Journal of Magnetic Resonance Imaging54, no. 1 (2021): 134–143, https://doi.org/10.1002/jmri.27538.
26W. Zhang, H. Yin, Z. Huang, et al., “Development and Validation of MRI-Based Deep Learning Models for Prediction of Microsatellite Instability in Rectal Cancer,” Cancer Medicine10, no. 12 (2021): 4164–4173, https://doi.org/10.1002/cam4.3957.
27Y. Yu, Z. He, J. Ouyang, et al., “Magnetic Resonance Imaging Radiomics Predicts Preoperative Axillary Lymph Node Metastasis to Support Surgical Decisions and Is Associated With Tumor Microenvironment in Invasive Breast Cancer: A Machine Learning, Multicenter Study,” eBioMedicine69 (2021): 103460, https://doi.org/10.1016/j.ebiom.2021.103460.
28T. F. Yu, W. He, C. G. Gan, et al., “Deep Learning Applied to Two-Dimensional Color Doppler Flow Imaging Ultrasound Images Significantly Improves Diagnostic Performance in the Classification of Breast Masses: A Multicenter Study,” Chinese Medical Journal134, no. 4 (2021): 415–424, https://doi.org/10.1097/CM9.0000000000001329.
29L. Yin, C. Song, J. Cui, et al., “A Fusion Decision System to Identify and Grade Malnutrition in Cancer Patients: Machine Learning Reveals Feasible Workflow From Representative Real-World Data,” Clinical Nutrition40, no. 8 (2021): 4958–4970, https://doi.org/10.1016/j.clnu.2021.06.028.
30H. Y. Yang, Y. C. Wang, H. Y. Peng, and C. H. Huang, “Breath Biopsy of Breast Cancer Using Sensor Array Signals and Machine Learning Analysis,” Scientific Reports11, no. 1 (2021): 103, https://doi.org/10.1038/s41598-020-80570-0.
31J. Yan, Y. Zhao, Y. Chen, et al., “Deep Learning Features From Diffusion Tensor Imaging Improve Glioma Stratification and Identify Risk Groups With Distinct Molecular Pathway Activities,” eBioMedicine72 (2021): 103583, https://doi.org/10.1016/j.ebiom.2021.103583.
32S. Xu, J. Qi, B. Li, Z. X. Bie, Y. M. Li, and X. G. Li, “Risk Prediction of Pleural Effusion in Lung Malignancy Patients Treated With CT-Guided Percutaneous Microwave Ablation: A Nomogram and Artificial Neural Network Model,” International Journal of Hyperthermia38, no. 1 (2021): 220–228, https://doi.org/10.1080/02656736.2021.1885755.
33J. Xiong, W. Yu, J. Ma, Y. Ren, X. Fu, and J. Zhao, “The Role of PET-Based Radiomic Features in Predicting Local Control of Esophageal Cancer Treated With Concurrent Chemoradiotherapy,” Scientific Reports8, no. 1 (2018): 9902, https://doi.org/10.1038/s41598-018-28243-x.
34W. Xing, H. Sun, C. Yan, et al., “A Prediction Model Based on DNA Methylation Biomarkers and Radiological Characteristics for Identifying Malignant From Benign Pulmonary Nodules,” BMC Cancer21, no. 1 (2021): 263, https://doi.org/10.1186/s12885-021-08002-4.
35Q. Y. Wu, S. L. Liu, P. Sun, et al., “Establishment and Clinical Application Value of an Automatic Diagnosis Platform for Rectal Cancer T-Staging Based on a Deep Neural Network,” Chinese Medical Journal134, no. 7 (2021): 821–828, https://doi.org/10.1097/CM9.0000000000001401.
36L. Wu, X. He, M. Liu, et al., “Evaluation of the Effects of an Artificial Intelligence System on Endoscopy Quality and Preliminary Testing of Its Performance in Detecting Early Gastric Cancer: A Randomized Controlled Trial,” Endoscopy53, no. 12 (2021): 1199–1207, https://doi.org/10.1055/a-1350-5583.
37X. X. Wang, Y. Ding, S. W. Wang, et al., “Intratumoral and Peritumoral Radiomics Analysis for Preoperative Lauren Classification in Gastric Cancer,” Cancer Imaging20, no. 1 (2020): 83, https://doi.org/10.1186/s40644-020-00358-3.
38R. Wang, X. Shao, J. Zheng, et al., “A Machine-Learning Approach to Identify a Prognostic Cytokine Signature That Is Associated With Nivolumab Clearance in Patients With Advanced Melanoma,” Clinical Pharmacology and Therapeutics107, no. 4 (2020): 978–987, https://doi.org/10.1002/cpt.1724.
39D. Wang, J. Xu, Z. Zhang, et al., “Evaluation of Rectal Cancer Circumferential Resection Margin Using Faster Region-Based Convolutional Neural Network in High-Resolution Magnetic Resonance Images,” Diseases of the Colon and Rectum63, no. 2 (2020): 143–151, https://doi.org/10.1097/DCR.0000000000001519.
40B. N. Walker, J. M. Rehg, A. Kalra, et al., “Dermoscopy Diagnosis of Cancerous Lesions Utilizing Dual Deep Learning Algorithms via Visual and Audio (Sonification) Outputs: Laboratory and Prospective Observational Studies,” eBioMedicine40 (2019): 176–183, https://doi.org/10.1016/j.ebiom.2019.01.028.
41S. Wagner, J. Vadakekolathu, S. K. Tasian, et al., “A Parsimonious 3-Gene Signature Predicts Clinical Outcomes in an Acute Myeloid Leukemia Multicohort Study,” Blood Advances3, no. 8 (2019): 1330–1346, https://doi.org/10.1182/bloodadvances.2018030726.
42J. Toivonen, I. Montoya Perez, P. Movahedi, et al., “Radiomics and Machine Learning of Multisequence Multiparametric Prostate MRI: Towards Improved Non-Invasive Prostate Cancer Characterization,” PLoS One14, no. 7 (2019): e0217702, https://doi.org/10.1371/journal.pone.0217702.
43J. R. Su, Z. Li, X. J. Shao, et al., “Impact of a Real-Time Automatic Quality Control System on Colorectal Polyp and Adenoma Detection: A Prospective Randomized Controlled Study (With Videos),” Gastrointestinal Endoscopy91, no. 2 (2020): 415–424.e4, https://doi.org/10.1016/j.gie.2019.08.026.
44SOS Study team, S. Chauvie, A. De Maggi, et al., “Artificial Intelligence and Radiomics Enhance the Positive Predictive Value of Digital Chest Tomosynthesis for Lung Cancer Detection Within SOS Clinical Trial,” European Radiology30, no. 7 (2020): 4134–4140, https://doi.org/10.1007/s00330-020-06783-z.
45L. L. Song, S. J. Chen, W. Chen, et al., “Radiomic Model for Differentiating Parotid Pleomorphic Adenoma From Parotid Adenolymphoma Based on MRI Images,” BMC Medical Imaging21, no. 1 (2021): 54, https://doi.org/10.1186/s12880-021-00581-9.
46B. Sobottka, M. Nowak, A. L. Frei, et al., “Establishing Standardized Immune Phenotyping of Metastatic Melanoma by Digital Pathology,” Laboratory Investigation101, no. 12 (2021): 1561–1570, https://doi.org/10.1038/s41374-021-00653-y.
47O. J. Skrede, S. De Raedt, A. Kleppe, et al., “Deep Learning for Prediction of Colorectal Cancer Outcome: A Discovery and Validation Study,” Lancet395, no. 10221 (2020): 350–360, https://doi.org/10.1016/S0140-6736(19)32998-8.
48M. Shew, J. New, and A. M. Bur, “Machine Learning to Predict Delays in Adjuvant Radiation Following Surgery for Head and Neck Cancer,” Otolaryngology and Head and Neck Surgery160, no. 6 (2019): 1058–1064, https://doi.org/10.1177/0194599818823200.
49S. P. Shayesteh, A. Alikhassi, A. Fard Esfahani, et al., “Neo-Adjuvant Chemoradiotherapy Response Prediction Using MRI Based Ensemble Learning Method in Rectal Cancer Patients,” Physica Medica62 (2019): 111–119, https://doi.org/10.1016/j.ejmp.2019.03.013.
50Q. y. Shan, H. t. Hu, S. t. Feng, et al., “CT-Based Peritumoral Radiomics Signatures to Predict Early Recurrence in Hepatocellular Carcinoma After Curative Tumor Resection or Ablation,” Cancer Imaging19, no. 1 (2019): 11, https://doi.org/10.1186/s40644-019-0197-5.
51K. Sasaki, E. J. Jabbour, F. Ravandi, et al., “The LEukemia Artificial Intelligence Program (LEAP) in Chronic Myeloid Leukemia in Chronic Phase: A Model to Improve Patient Outcomes,” American Journal of Hematology96, no. 2 (2021): 241–250, https://doi.org/10.1002/ajh.26047.
52H. Qin, X. Hu, J. Zhang, et al., “Machine-Learning Radiomics to Predict Early Recurrence in Perihilar Cholangiocarcinoma After Curative Resection,” Liver International41, no. 4 (2021): 837–850, https://doi.org/10.1111/liv.14763.
53P. Peneder, A. M. Stütz, D. Surdez, et al., “Multimodal Analysis of Cell-Free DNA Whole-Genome Sequencing for Pediatric Cancers With Low Mutational Burden,” Nature Communications12, no. 1 (2021): 3230, https://doi.org/10.1038/s41467-021-23445-w.
54C. Parkinson, M. Evans, T. Guerrero-Urbano, et al., “Machine-Learned Target Volume Delineation of 18F-FDG PET Images After One Cycle of Induction Chemotherapy,” Physica Medica61 (2019): 85–93, https://doi.org/10.1016/j.ejmp.2019.04.020.
55L. Papp, C. P. Spielvogel, B. Grubmüller, et al., “Supervised Machine Learning Enables Non-Invasive Lesion Characterization in Primary Prostate Cancer With [68Ga]ga-PSMA-11 PET/MRI,” European Journal of Nuclear Medicine and Molecular Imaging48, no. 6 (2021): 1795–1805, https://doi.org/10.1007/s00259-020-05140-y.
56X. Ou, J. Zhang, J. Wang, et al., “Radiomics Based on 18 F-FDG PET/CT Could Differentiate Breast Carcinoma From Breast Lymphoma Using Machine-Learning Approach: A Preliminary Study,” Cancer Medicine9, no. 2 (2020): 496–506, https://doi.org/10.1002/cam4.2711.
57H. Nakashima, H. Kawahira, H. Kawachi, and N. Sakaki, “Endoscopic Three-Categorical Diagnosis of Helicobacter pylori Infection Using Linked Color Imaging and Deep Learning: A Single-Center Prospective Study (With Video),” Gastric Cancer23, no. 6 (2020): 1033–1040, https://doi.org/10.1007/s10120-020-01077-1.
58I. Montoya Perez, I. Jambor, T. Pahikkala, et al., “Prostate Cancer Risk Stratification in Men With a Clinical Suspicion of Prostate Cancer Using a Unique Biparametric MRI and Expression of 11 Genes in Apparently Benign Tissue: Evaluation Using Machine-Learning Techniques,” Journal of Magnetic Resonance Imaging51, no. 5 (2020): 1540–1553, https://doi.org/10.1002/jmri.26945.
59H. Merisaari, P. Taimen, R. Shiradkar, et al., “Repeatability of Radiomics and Machine Learning for DWI: Short-Term Repeatability Study of 112 Patients With Prostate Cancer,” Magnetic Resonance in Medicine83, no. 6 (2020): 2293–2309, https://doi.org/10.1002/mrm.28058.
60K. Men, H. Geng, H. Zhong, Y. Fan, A. Lin, and Y. Xiao, “A Deep Learning Model for Predicting Xerostomia due to Radiation Therapy for Head and Neck Squamous Cell Carcinoma in the RTOG 0522 Clinical Trial,” International Journal of Radiation Oncology, Biology, Physics105, no. 2 (2019): 440–447, https://doi.org/10.1016/j.ijrobp.2019.06.009.
61D. Mathios, J. S. Johansen, S. Cristiano, et al., “Detection and Characterization of Lung Cancer Using Cell-Free DNA Fragmentomes,” Nature Communications12, no. 1 (2021): 5060, https://doi.org/10.1038/s41467-021-24994-w.
62S. Marcišauskas, B. Ulfenborg, B. Kristjansdottir, S. Waldemarson, and K. Sundfeldt, “Univariate and Classification Analysis Reveals Potential Diagnostic Biomarkers for Early Stage Ovarian Cancer Type 1 and Type 2,” Journal of Proteomics196 (2019): 57–68, https://doi.org/10.1016/j.jprot.2019.01.017.
63M. Ma, L. Gan, Y. Liu, et al., “Radiomics Features Based on Automatic Segmented MRI Images: Prognostic Biomarkers for Triple-Negative Breast Cancer Treated With Neoadjuvant Chemotherapy,” European Journal of Radiology146 (2022): 110095, https://doi.org/10.1016/j.ejrad.2021.110095.
64M. Ma, R. Liu, C. Wen, et al., “Predicting the Molecular Subtype of Breast Cancer and Identifying Interpretable Imaging Features Using Machine Learning Algorithms,” European Radiology32, no. 3 (2022): 1652–1662, https://doi.org/10.1007/s00330-021-08271-4.
65Y. Luo, Y. Zhang, M. Liu, et al., “Artificial Intelligence-Assisted Colonoscopy for Detection of Colon Polyps: A Prospective, Randomized Cohort Study,” Journal of Gastrointestinal Surgery25, no. 8 (2021): 2011–2018, https://doi.org/10.1007/s11605-020-04802-4.
66H. Luo, G. Xu, C. Li, et al., “Real-Time Artificial Intelligence for Detection of Upper Gastrointestinal Cancer by Endoscopy: A Multicentre, Case-Control, Diagnostic Study,” Lancet Oncology20, no. 12 (2019): 1645–1654, https://doi.org/10.1016/S1470-2045(19)30637-0.
67Y. H. Liu, J. Jin, and Y. J. Liu, “Machine Learning–Based Random Forest for Predicting Decreased Quality of Life in Thyroid Cancer Patients After Thyroidectomy,” Supportive Care in Cancer30, no. 3 (2022): 2507–2513, https://doi.org/10.1007/s00520-021-06657-0.
68X. Liu, Y. Hou, X. Wang, et al., “Machine Learning-Based Development and Validation of a Scoring System for Progression-Free Survival in Liver Cancer,” Hepatology International14, no. 4 (2020): 567–576, https://doi.org/10.1007/s12072-020-10046-w.
69Q. Liu, D. Zhou, T. Han, et al., “A Noninvasive Multianalytical Approach for Lung Cancer Diagnosis of Patients With Pulmonary Nodules,” Advancement of Science8, no. 13 (2021): 2100104, https://doi.org/10.1002/advs.202100104.
70P. Liu, X. Z. Tan, T. Zhang, et al., “Prediction of Microvascular Invasion in Solitary Hepatocellular Carcinoma ≤ 5 cm Based on Computed Tomography Radiomics,” World Journal of Gastroenterology27, no. 17 (2021): 2015–2024, https://doi.org/10.3748/wjg.v27.i17.2015.
72J. Liu, Y. Mao, Z. Li, et al., “Use of Texture Analysis Based on Contrast-Enhanced MRI to Predict Treatment Response to Chemoradiotherapy in Nasopharyngeal Carcinoma: MRI in Treatment Response Prediction,” Journal of Magnetic Resonance Imaging44, no. 2 (2016): 445–455, https://doi.org/10.1002/jmri.25156.
73H. Liu, Y. Chen, Y. Zhang, et al., “A Deep Learning Model Integrating Mammography and Clinical Factors Facilitates the Malignancy Prediction of BI-RADS 4 Microcalcifications in Breast Cancer Screening,” European Radiology31, no. 8 (2021): 5902–5912, https://doi.org/10.1007/s00330-020-07659-y.
74Y. Liang, J. Huan, J. D. Li, C. Jiang, C. Fang, and Y. Liu, “Use of Artificial Intelligence to Recover Mandibular Morphology After Disease,” Scientific Reports10, no. 1 (2020): 16431, https://doi.org/10.1038/s41598-020-73394-5.
75Y. Li, D. Wei, X. Liu, et al., “Molecular Subtyping of Diffuse Gliomas Using Magnetic Resonance Imaging: Comparison and Correlation Between Radiomics and Deep Learning,” European Radiology32, no. 2 (2022): 747–758, https://doi.org/10.1007/s00330-021-08237-6.
76C. Li, K. Li, X. Xu, W. Qi, X. Hu, and P. Jin, “A Pilot Study for Colorectal Carcinoma Screening by Instant Metabolomic Profiles Using Conductive Polymer Spray Ionization Mass Spectrometry,” Biochimica et Biophysica Acta-Molecular Basis of Disease1867, no. 11 (2021): 166210, https://doi.org/10.1016/j.bbadis.2021.166210.
77S. Lee, S. Kerns, H. Ostrer, B. Rosenstein, J. O. Deasy, and J. H. Oh, “Machine Learning on a Genome-Wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy,” International Journal of Radiation Oncology, Biology, Physics101, no. 1 (2018): 128–135, https://doi.org/10.1016/j.ijrobp.2018.01.054.
78M. Kjellman, U. Knigge, S. Welin, et al., “A Plasma Protein Biomarker Strategy for Detection of Small Intestinal Neuroendocrine Tumors,” Neuroendocrinology111, no. 9 (2021): 840–849, https://doi.org/10.1159/000510483.
79M. Kirienko, M. Sollini, M. Corbetta, et al., “Radiomics and Gene Expression Profile to Characterise the Disease and Predict Outcome in Patients With Lung Cancer,” European Journal of Nuclear Medicine and Molecular Imaging48, no. 11 (2021): 3643–3655, https://doi.org/10.1007/s00259-021-05371-7.
80Y. G. Kim, S. Kim, C. E. Cho, et al., “Effectiveness of Transfer Learning for Enhancing Tumor Classification With a Convolutional Neural Network on Frozen Sections,” Scientific Reports10, no. 1 (2020): 21899, https://doi.org/10.1038/s41598-020-78129-0.
81J. Kim and I. Jang, “Predictors of Bleeding Event Among Elderly Patients With Mechanical Valve Replacement Using Random Forest Model: A Retrospective Study,” Medicine100, no. 19 (2021): e25875, https://doi.org/10.1097/MD.0000000000025875.
82K. V. Kepesidis, M. Bozic-Iven, M. Huber, et al., “Breast-Cancer Detection Using Blood-Based Infrared Molecular Fingerprints,” BMC Cancer21, no. 1 (2021): 1287, https://doi.org/10.1186/s12885-021-09017-7.
83M. Kazemimoghadam, W. Chi, A. Rahimi, et al., “Saliency-Guided Deep Learning Network for Automatic Tumor Bed Volume Delineation in Post-Operative Breast Irradiation,” Physics in Medicine and Biology66, no. 17 (2021): 175019, https://doi.org/10.1088/1361-6560/ac176d.
84S. T. Kakileti, H. J. Madhu, L. Krishnan, G. Manjunath, S. Sampangi, and H. V. Ramprakash, “Observational Study to Evaluate the Clinical Efficacy of Thermalytix for Detecting Breast Cancer in Symptomatic and Asymptomatic Women,” JCO Global Oncology6 (2020): 1472–1480, https://doi.org/10.1200/GO.20.00168.
85G. Kaissis, S. Ziegelmayer, F. Lohöfer, et al., “A Machine Learning Algorithm Predicts Molecular Subtypes in Pancreatic Ductal Adenocarcinoma With Differential Response to Gemcitabine-Based Versus FOLFIRINOX Chemotherapy,” PLoS One14, no. 10 (2019): e0218642, https://doi.org/10.1371/journal.pone.0218642.
86G. D. Jones, W. S. Brandt, R. Shen, et al., “A Genomic-Pathologic Annotated Risk Model to Predict Recurrence in Early-Stage Lung Adenocarcinoma,” JAMA Surgery156, no. 2 (2021): e205601, https://doi.org/10.1001/jamasurg.2020.5601.
87C. Johnson, G. Price, J. Khalifa, et al., “A Method to Combine Target Volume Data From 3D and 4D Planned Thoracic Radiotherapy Patient Cohorts for Machine Learning Applications,” Radiotherapy and Oncology126, no. 2 (2018): 355–361, https://doi.org/10.1016/j.radonc.2017.11.015.
88N. Jiang and X. Xu, “Exploring the Survival Prognosis of Lung Adenocarcinoma Based on the Cancer Genome Atlas Database Using Artificial Neural Network,” Medicine98, no. 20 (2019): e15642, https://doi.org/10.1097/MD.0000000000015642.
89C. Jayachandran Preetha, H. Meredig, G. Brugnara, et al., “Deep-Learning-Based Synthesis of Post-Contrast T1-Weighted MRI for Tumour Response Assessment in Neuro-Oncology: A Multicentre, Retrospective Cohort Study,” Lancet Digital Health3, no. 12 (2021): e784–e794, https://doi.org/10.1016/S2589-7500(21)00205-3.
90H. E. Janes, K. W. Cohen, N. Frahm, et al., “Higher T-Cell Responses Induced by DNA/rAd5 HIV-1 Preventive Vaccine Are Associated With Lower HIV-1 Infection Risk in an Efficacy Trial,” Journal of Infectious Diseases215, no. 9 (2017): 1376–1385, https://doi.org/10.1093/infdis/jix086.
91S. Iivanainen, J. Ekstrom, H. Virtanen, V. V. Kataja, and J. P. Koivunen, “Electronic Patient-Reported Outcomes and Machine Learning in Predicting Immune-Related Adverse Events of Immune Checkpoint Inhibitor Therapies,” BMC Medical Informatics and Decision Making21, no. 1 (2021): 205, https://doi.org/10.1186/s12911-021-01564-0.
92B. Hunt, J. H. T. G. Fregnani, D. Brenes, et al., “Cervical Lesion Assessment Using Real-Time Microendoscopy Image Analysis in Brazil: The CLARA Study,” International Journal of Cancer149, no. 2 (2021): 431–441, https://doi.org/10.1002/ijc.33543.
93V. Huber, L. Di Guardo, L. Lalli, et al., “Back to Simplicity: A Four-Marker Blood Cell Score to Quantify Prognostically Relevant Myeloid Cells in Melanoma Patients,” Journal for Immunotherapy of Cancer9, no. 2 (2021): e001167, https://doi.org/10.1136/jitc-2020-001167.
95L. Huang, W. Lin, D. Xie, et al., “Development and Validation of a Preoperative CT-Based Radiomic Nomogram to Predict Pathology Invasiveness in Patients With a Solitary Pulmonary Nodule: A Machine Learning Approach, Multicenter, Diagnostic Study,” European Radiology32, no. 3 (2022): 1983–1996, https://doi.org/10.1007/s00330-021-08268-z.
96H. W. Huang, P. Y. Wu, P. F. Su, et al., “A Simplified Diagnostic Classification Scheme of Chemotherapy-Induced Peripheral Neuropathy,” Disease Markers2020 (2020): 1–8, https://doi.org/10.1155/2020/3402108.
97C. M. Huang, M. Y. Huang, C. W. Huang, et al., “Machine Learning for Predicting Pathological Complete Response in Patients With Locally Advanced Rectal Cancer After Neoadjuvant Chemoradiotherapy,” Scientific Reports10, no. 1 (2020): 12555, https://doi.org/10.1038/s41598-020-69345-9.
98C. H. Huang, C. Zeng, Y. C. Wang, et al., “A Study of Diagnostic Accuracy Using a Chemical Sensor Array and a Machine Learning Technique to Detect Lung Cancer,” Sensors18, no. 9 (2018): 2845, https://doi.org/10.3390/s18092845.
99N. Horeweg, M. De Bruyn, R. A. Nout, et al., “Prognostic Integrated Image-Based Immune and Molecular Profiling in Early-Stage Endometrial Cancer,” Cancer Immunology Research8, no. 12 (2020): 1508–1519, https://doi.org/10.1158/2326-6066.CIR-20-0149.
100Y. Hong, Y. J. Heo, B. Kim, et al., “Deep Learning-Based Virtual Cytokeratin Staining of Gastric Carcinomas to Measure Tumor–Stroma Ratio,” Scientific Reports11, no. 1 (2021): 19255, https://doi.org/10.1038/s41598-021-98857-1.
101A. Hartenstein, F. Lübbe, A. D. J. Baur, et al., “Prostate Cancer Nodal Staging: Using Deep Learning to Predict 68Ga-PSMA-Positivity From CT Imaging Alone,” Scientific Reports10, no. 1 (2020): 3398, https://doi.org/10.1038/s41598-020-60311-z.
102H. A. Haenssle, C. Fink, R. Schneiderbauer, et al., “Man Against Machine: Diagnostic Performance of a Deep Learning Convolutional Neural Network for Dermoscopic Melanoma Recognition in Comparison to 58 Dermatologists,” Annals of Oncology29, no. 8 (2018): 1836–1842, https://doi.org/10.1093/annonc/mdy166.
103J. T. Grist, S. Withey, C. Bennett, et al., “Combining Multi-Site Magnetic Resonance Imaging With Machine Learning Predicts Survival in Pediatric Brain Tumors,” Scientific Reports11, no. 1 (2021): 18897, https://doi.org/10.1038/s41598-021-96189-8.
104I. González-García, V. Pierre, V. F. S. Dubois, et al., “Early Predictions of Response and Survival From a Tumor Dynamics Model in Patients With Recurrent, Metastatic Head and Neck Squamous Cell Carcinoma Treated With Immunotherapy,” CPT: Pharmacometrics & Systems Pharmacology10, no. 3 (2021): 230–240, https://doi.org/10.1002/psp4.12594.
105E. D. H. Gates, J. S. Lin, J. S. Weinberg, et al., “Imaging-Based Algorithm for the Local Grading of Glioma,” American Journal of Neuroradiology41, no. 3 (2020): 400–407, https://doi.org/10.3174/ajnr.A6405.
106P. Franco, U. Würtemberger, K. Dacca, et al., “SPectroscOpic Prediction of bRain Tumours (SPORT): Study Protocol of a Prospective Imaging Trial,” BMC Medical Imaging20, no. 1 (2020): 123, https://doi.org/10.1186/s12880-020-00522-y.
107M. Eskes, M. J. A. Van Alphen, A. J. M. Balm, L. E. Smeele, D. Brandsma, and F. Van Der Heijden, “Predicting 3D Lip Shapes Using Facial Surface EMG,” PLoS One12, no. 4 (2017): e0175025, https://doi.org/10.1371/journal.pone.0175025.
108A. Eresen, Y. Li, J. Yang, et al., “Preoperative Assessment of Lymph Node Metastasis in Colon Cancer Patients Using Machine Learning: A Pilot Study,” Cancer Imaging20, no. 1 (2020): 30, https://doi.org/10.1186/s40644-020-00308-z.
109M. J. Emaus, I. Išgum, S. G. M. Van Velzen, et al., “Bragatston Study Protocol: A Multicentre Cohort Study on Automated Quantification of Cardiovascular Calcifications on Radiotherapy Planning CT Scans for Cardiovascular Risk Prediction in Patients With Breast Cancer,” BMJ Open9, no. 7 (2019): e028752, https://doi.org/10.1136/bmjopen-2018-028752.
110A. Dittberner, E. Rodner, W. Ortmann, et al., “Automated Analysis of Confocal Laser Endomicroscopy Images to Detect Head and Neck Cancer: Confocal Laser Endomicroscopy for Head and Neck Cancer,” Head & Neck38, no. S1 (2016): E1419–E1426, https://doi.org/10.1002/hed.24253.
111L. Dihge, J. Vallon-Christersson, C. Hegardt, et al., “Prediction of Lymph Node Metastasis in Breast Cancer by Gene Expression and Clinicopathological Models: Development and Validation Within a Population-Based Cohort,” Clinical Cancer Research25, no. 21 (2019): 6368–6381, https://doi.org/10.1158/1078-0432.CCR-19-0075.
112D. DiCenzo, K. Quiaoit, K. Fatima, et al., “Quantitative Ultrasound Radiomics in Predicting Response to Neoadjuvant Chemotherapy in Patients With Locally Advanced Breast Cancer: Results From Multi-Institutional Study,” Cancer Medicine9, no. 16 (2020): 5798–5806, https://doi.org/10.1002/cam4.3255.
113U. Deding, J. Herp, A. Havshoei, et al., “Colon Capsule Endoscopy Versus CT Colonography After Incomplete Colonoscopy. Application of Artificial Intelligence Algorithms to Identify Complete Colonic Investigations,” United European Gastroenterology Journal8, no. 7 (2020): 782–789, https://doi.org/10.1177/2050640620937593.
114E. E. C. De Jong, W. Van Elmpt, S. Rizzo, et al., “Applicability of a Prognostic CT-Based Radiomic Signature Model Trained on Stage I-III Non-small Cell Lung Cancer in Stage IV Non-Small Cell Lung Cancer,” Lung Cancer124 (2018): 6–11, https://doi.org/10.1016/j.lungcan.2018.07.023.
115A. Dasgupta, K. Fatima, D. DiCenzo, et al., “Quantitative Ultrasound Radiomics in Predicting Recurrence for Patients With Node-Positive Head-Neck Squamous Cell Carcinoma Treated With Radical Radiotherapy,” Cancer Medicine10, no. 8 (2021): 2579–2589, https://doi.org/10.1002/cam4.3634.
116E. F. Crowell, C. Bazin, V. Thurotte, et al., “Adaptation of CytoProcessor for Cervical Cancer Screening of Challenging Slides,” Diagnostic Cytopathology47, no. 9 (2019): 890–897, https://doi.org/10.1002/dc.24213.
117G. Cosma, S. E. McArdle, G. A. Foulds, et al., “Prostate Cancer: Early Detection and Assessing Clinical Risk Using Deep Machine Learning of High Dimensional Peripheral Blood Flow Cytometric Phenotyping Data,” Frontiers in Immunology12 (2021): 786828, https://doi.org/10.3389/fimmu.2021.786828.
118F. Citak-Er, Z. Firat, I. Kovanlikaya, U. Ture, and E. Ozturk-Isik, “Machine-Learning in Grading of Gliomas Based on Multi-Parametric Magnetic Resonance Imaging at 3T,” Computers in Biology and Medicine99 (2018): 154–160, https://doi.org/10.1016/j.compbiomed.2018.06.009.
119M. A. Chapman, J. Sive, J. Ambrose, et al., “RNA-Seq of Newly Diagnosed Patients in the PADIMAC Study Leads to a Bortezomib/Lenalidomide Decision Signature,” Blood132, no. 20 (2018): 2154–2165, https://doi.org/10.1182/blood-2018-05-849893.
120S. S. Byun, T. S. Heo, J. M. Choi, et al., “Deep Learning Based Prediction of Prognosis in Nonmetastatic Clear Cell Renal Cell Carcinoma,” Scientific Reports11, no. 1 (2021): 1242, https://doi.org/10.1038/s41598-020-80262-9.
121H. J. Butler, P. M. Brennan, J. M. Cameron, et al., “Development of High-Throughput ATR-FTIR Technology for Rapid Triage of Brain Cancer,” Nature Communications10, no. 1 (2019): 4501, https://doi.org/10.1038/s41467-019-12527-5.
122V. Bobée, F. Drieux, V. Marchand, et al., “Combining Gene Expression Profiling and Machine Learning to Diagnose B-Cell Non-Hodgkin Lymphoma,” Blood Cancer Journal10, no. 5 (2020): 59, https://doi.org/10.1038/s41408-020-0322-5.
123L. Bielak, N. Wiedenmann, N. H. Nicolay, et al., “Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction,” Tomography5, no. 3 (2019): 292–299, https://doi.org/10.18383/j.tom.2019.00010.
124J. E. Bibault, D. T. Chang, and L. Xing, “Development and Validation of a Model to Predict Survival in Colorectal Cancer Using a Gradient-Boosted Machine,” Gut70, no. 5 (2021): 884–889, https://doi.org/10.1136/gutjnl-2020-321799.
125S. Bhattarai, S. Klimov, M. A. Aleskandarany, et al., “Machine Learning-Based Prediction of Breast Cancer Growth Rate In Vivo,” British Journal of Cancer121, no. 6 (2019): 497–504, https://doi.org/10.1038/s41416-019-0539-x.
127R. Banchereau, N. Leng, O. Zill, et al., “Molecular Determinants of Response to PD-L1 Blockade Across Tumor Types,” Nature Communications12, no. 1 (2021): 3969, https://doi.org/10.1038/s41467-021-24112-w.
128E. Arvaniti, K. S. Fricker, M. Moret, et al., “Automated Gleason Grading of Prostate Cancer Tissue Microarrays via Deep Learning,” Scientific Reports8, no. 1 (2018): 12054, https://doi.org/10.1038/s41598-018-30535-1.
129S. Alig, V. Jurinovic, M. Shahrokh Esfahani, et al., “Evaluating Upfront High-Dose Consolidation After R-CHOP for Follicular Lymphoma by Clinical and Genetic Risk Models,” Blood Advances4, no. 18 (2020): 4451–4462, https://doi.org/10.1182/bloodadvances.2020002546.
130H. R. Ali, A. Dariush, E. Provenzano, et al., “Computational Pathology of Pre-Treatment Biopsies Identifies Lymphocyte Density as a Predictor of Response to Neoadjuvant Chemotherapy in Breast Cancer,” Breast Cancer Research18, no. 1 (2016): 21, https://doi.org/10.1186/s13058-016-0682-8.
131P. Afshar, A. Mohammadi, P. N. Tyrrell, et al., “DRTOP: Deep Learning-Based Radiomics for the Time-To-Event Outcome Prediction in Lung Cancer,” Scientific Reports10, no. 1 (2020): 12366, https://doi.org/10.1038/s41598-020-69106-8.
132T. M. A. Abdel-Fatah, D. Agarwal, D. X. Liu, et al., “SPAG5 as a Prognostic Biomarker and Chemotherapy Sensitivity Predictor in Breast Cancer: A Retrospective, Integrated Genomic, Transcriptomic, and Protein Analysis,” Lancet Oncology17, no. 7 (2016): 1004–1018, https://doi.org/10.1016/S1470-2045(16)00174-1.
133L. Lenchik, R. Barnard, R. D. Boutin, et al., “Automated Muscle Measurement on Chest CT Predicts all-Cause Mortality in Older Adults From the National Lung Screening Trial,” Journals of Gerontology: Series A76, no. 2 (2021): 277–285, https://doi.org/10.1093/gerona/glaa141.
134E. A. Klein, D. Richards, A. Cohn, et al., “Clinical Validation of a Targeted Methylation-Based Multi-Cancer Early Detection Test Using an Independent Validation Set,” Annals of Oncology32, no. 9 (2021): 1167–1177, https://doi.org/10.1016/j.annonc.2021.05.806.
135J. C. Hong, N. C. W. Eclov, N. H. Dalal, et al., “System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT): A Prospective Randomized Study of Machine Learning–Directed Clinical Evaluations During Radiation and Chemoradiation,” Journal of Clinical Oncology38, no. 31 (2020): 3652–3661, https://doi.org/10.1200/JCO.20.01688.
136E. D. H. Gates, J. S. Lin, J. S. Weinberg, et al., “Guiding the First Biopsy in Glioma Patients Using Estimated Ki-67 Maps Derived From MRI: Conventional Versus Advanced Imaging,” NeuroOncology21, no. 4 (2019): 527–536, https://doi.org/10.1093/neuonc/noz004.
137J. S. Gandelman, M. T. Byrne, A. M. Mistry, et al., “Machine Learning Reveals Chronic Graft-Versus-Host Disease Phenotypes and Stratifies Survival After Stem Cell Transplant for Hematologic Malignancies,” Haematologica104, no. 1 (2019): 189–196, https://doi.org/10.3324/haematol.2018.193441.
138J. Y. Dai, M. LeBlanc, P. J. Goodman, M. S. Lucia, I. M. Thompson, and C. M. Tangen, “Case-Only Methods Identified Genetic Loci Predicting a Subgroup of Men With Reduced Risk of High-Grade Prostate Cancer by Finasteride,” Cancer Prevention Research12, no. 2 (2019): 113–120, https://doi.org/10.1158/1940-6207.CAPR-18-0284.
140D. Plana, D. L. Shung, A. A. Grimshaw, A. Saraf, J. J. Y. Sung, and B. H. Kann, “Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review,” JAMA Network Open5, no. 9 (2022): e2233946, https://doi.org/10.1001/jamanetworkopen.2022.33946.
141F. Mutale, “Inclusion of Racial and Ethnic Minorities in Cancer Clinical Trials: 30 Years After the NIH Revitalization Act, Where Are we?,” Journal of the Advanced Practitioner in Oncology13, no. 8 (2022): 755–757, https://doi.org/10.6004/jadpro.2022.13.8.2.
Please check your email for instructions on resetting your password.
If you do not receive an email within 10 minutes, your email address may not be registered,
and you may need to create a new Wiley Online Library account.
Request Username
Can't sign in? Forgot your username?
Enter your email address below and we will send you your username
If the address matches an existing account you will receive an email with instructions to retrieve your username
The full text of this article hosted at iucr.org is unavailable due to technical difficulties.
