Machine Learning in Oncology: Methods, Applications, and Challenges

Redefining clinical trial strategic design to support drug approval in medical oncology

Randomized clinical trials represent the gold standard for the introduction of innovative therapies in medical oncology, and they provide the highest level of evidence to ascertain the clinical activity of new drugs or novel combinations. However, the current infrastructure of clinical trials supporting innovative drug approvals is challenged by an increased body of knowledge concerning tumor biology and therapy resistance, a fast-growing armamentarium of novel anticancer compounds, an impressively upscaled data analysis capacity, as well as increasing costs related to clinical trials management. In this scenario, modern clinical trial designs need to evolve to expedite new drug approvals by tailoring patients' treatment strategies according to their medical needs. Balanced, patient-oriented clinical trial designs are eagerly warranted to increase their efficiency, to include the fast pace of technological innovations and scientific discoveries, and, ultimately, to face the challenges of the modern medical oncology field.

Machine Learning-Driven Modeling to Predict Postdischarge Venous Thromboembolism After Pancreatectomy for Pancreas Cancer

BACKGROUND

Postdischarge venous thromboembolism (pdVTE) is a life-threatening complication following resection for pancreatic cancer (PC). While national guidelines recommend extended chemoprophylaxis for all, adherence is low and ranges from 1.5 to 44%. Predicting a patient's pdVTE risk would enable a more tailored approach to extended chemoprophylaxis, better balancing the cost and risks of overtreatment. We aimed to demonstrate the feasibility of using machine learning models to predict pdVTE.

PATIENTS AND METHODS

We analyzed data from patients undergoing pancreatectomy for PC using the National Surgical Quality Improvement Program database between 2014 and 2020. Predictive classification models were trained and independently tested on features available at the time of discharge including demographics, clinical, laboratory, cancer, and surgery-specific variables. We developed and compared logistic regression (LR), decision tree (DT), random forest (RF), and gradient boosting (GB) models to predict the development of pdVTE. Model performance and feature importance were evaluated.

RESULTS

The study included a total of 51,916 patients, with 743 (1.4%) experiencing pdVTE. The best-performing GB, RF, and DT models achieved area under the curve (AUC) scores of 0.83, 0.80, and 0.80, respectively, demonstrating superior performance compared with the traditional LR (AUC = 0.72) model. The GB model achieved a specificity of 99%, sensitivity of 0.40%, and area under the precision recall curve of 0.34. The most important variables were intraoperative antibiotic use, blood transfusion, length of stay, and postoperative infections.

CONCLUSIONS

Machine learning models can reliably identify patients who are at high risk for pdVTE. Such models should be used to inform prescription of extended VTE prophylaxis.

Predicting the efficacy of bevacizumab on peritumoral edema based on imaging features and machine learning

This study proposes a novel approach to predict the efficacy of bevacizumab (BEV) in treating peritumoral edema in metastatic brain tumor patients by integrating advanced machine learning (ML) techniques with comprehensive imaging and clinical data. A retrospective analysis was performed on 300 patients who received BEV treatment from September 2013 to January 2024. The dataset incorporated 13 predictive features: 8 clinical variables and 5 radiological variables. The dataset was divided into a training set (70%) and a test set (30%) using stratified sampling. Data preprocessing was carried out through methods such as handling missing values with the MICE method, detecting and adjusting outliers, and feature scaling. Four algorithms, namely Random Forest (RF), Logistic Regression, Gradient Boosting Tree, and Naive Bayes, were selected to construct binary classification models. A tenfold cross-validation strategy was implemented during training, and techniques like regularization, hyperparameter optimization, and oversampling were used to mitigate overfitting. The RF model demonstrated superior performance, achieving an accuracy of 0.89, a precision of 0.94, F1-score of 0.92, with both AUC-ROC and AUC-PR values reaching 0.91. Feature importance analysis consistently identified edema volume as the most significant predictor, followed by edema index, patient age, and tumor volume. Traditional multivariate logistic regression corroborated these findings, confirming that edema volume and edema index were independent predictors (p < 0.01). Our results highlight the potential of ML-driven predictive models in optimizing BEV treatment selection, reducing unnecessary treatment risks, and improving clinical decision-making in neuro-oncology.

Personalized therapeutic strategies and prognosis for advanced laryngeal squamous cell carcinoma: Insights from machine learning models

PURPOSE

Despite the development of diverse treatment options, there has been an increase in mortality rates for laryngeal squamous cell carcinoma (LSCC). Our research employed survival analysis and machine learning (ML) techniques to evaluate the impact of different therapeutic options on survival and to build a prognostic model for individualized clinical decisions in advanced LSCC.

METHODS

The Surveillance, Epidemiology and End Results (SEER) database provided the data used for this study's analysis. To identify the prognostic variables for patients with LSCC, we conducted Cox regression analysis and constructed prognostic models using five machine learning (ML) algorithms to predict 5-year survival. A method of validation that incorporated the area under the curve (AUC) of the receiver operating characteristic (ROC) curve was employed to validate the accuracy and reliability of the ML models. We also investigated the role of multiple therapeutic options using Kaplan Meier (K-M) survival analysis.

RESULTS

The study included 7350 patients, of whom 2689 were diagnosed with glottic cancer (GC), 4349 with supraglottic (SuGC) and 312 with subglottic (SC). ML models identified age, sex, and stage as the most important factors that affect survival. In terms of treatment, bets survival therapeutic options for all anatomical sites was surgery and radiotherapy (RT).

CONCLUSION

Employing multimodal therapies such as surgery and radiotherapy is crucial for managing advanced-stage LSCC. Tailored approaches that consider prognostic factors such as age, sex, and tumor stage are necessary. Additionally, chemotherapy did not significantly impact overall survival, suggesting potential areas for improvement in LSCC management.

Machine learning for modeling and identifying risk factors of pancreatic fistula

BACKGROUND

Pancreatic fistula is the most common complication of pancreatic surgeries that causes more serious conditions, including bleeding due to visceral vessel erosion and peritonitis.

AIM

To develop a machine learning (ML) model for postoperative pancreatic fistula and identify significant risk factors of the complication.

METHODS

A single-center retrospective clinical study was conducted which included 150 patients, who underwent pancreatoduodenectomy. Logistic regression, random forest, and CatBoost were employed for modeling the biochemical leak (symptomless fistula) and fistula grade B/C (clinically significant complication). The performance was estimated by receiver operating characteristic (ROC) area under the curve (AUC) after 5-fold cross-validation (20% testing and 80% training data). The risk factors were evaluated with the most accurate algorithm, based on the parameter "Importance" (Im), and Kendall correlation, P < 0.05.

RESULTS

The CatBoost algorithm was the most accurate with an AUC of 74%-86%. The study provided results of ML-based modeling and algorithm selection for pancreatic fistula prediction and risk factor evaluation. From 14 parameters we selected the main pre- and intraoperative prognostic factors of all the fistulas: Tumor vascular invasion (Im = 24.8%), age (Im = 18.6%), and body mass index (Im = 16.4%), AUC = 74%. The ML model showed that biochemical leak, blood and drain amylase level (Im = 21.6% and 16.4%), and blood leukocytes (Im = 11.2%) were crucial predictors for subsequent fistula B/C, AUC = 86%. Surgical techniques, morphology, and pancreatic duct diameter less than 3 mm were insignificant (Im < 5% and no correlations detected). The results were confirmed by correlation analysis.

CONCLUSION

This study highlights the key predictors of postoperative pancreatic fistula and establishes a robust ML-based model for individualized risk prediction. These findings contribute to the advancement of personalized perioperative care and may guide targeted preventive strategies.

Machine Learning-based Identification of Prognostic Factors for Surgical Management in Patients With NOS Sarcoma

Background

Non-otherwise specified (NOS) sarcomas, a diverse and diagnostically challenging group of mesenchymal malignancies, pose significant clinical dilemmas due to their variable clinical trajectories and therapeutic responses. This study utilizes advanced machine learning techniques, namely classification and regression trees and Shapley additive explanation (SHAP) values, to identify predictors of survival, metastatic progression, and recurrence within a well-defined patient cohort, aiming to improve risk stratification and individualized care strategies.

Methods

Through the application of classification and regression trees and SHAP values to a cohort of 122 patients with NOS sarcoma, we identified critical factors impacting disease outcomes.

Results

The study findings revealed that age and tumor diameter significantly influenced the development of metastasis, whereas body mass index and tumor grading were key predictors for relapse. Additionally, tumor size, location, and age were identified as influential factors for overall survival in patients with NOS sarcoma. These results have direct clinical relevance and can aid in risk stratification and surgical planning in this challenging patient population.

Conclusions

Considering the comparatively small cohort with which the machine learning algorithm was trained, this study underscores the importance of considering age, tumor size, location, body mass index, and tumor grading in the management of NOS sarcomas, shedding light on factors that may impact clinical outcomes and guide personalized treatment strategies.

Critical review of patient outcome study in head and neck cancer radiotherapy

Rapid technological advances in radiation therapy have significantly improved dose delivery and tumor control for head and neck cancers. However, treatment-related toxicities caused by high-dose exposure to critical structures remain a significant clinical challenge, underscoring the need for accurate prediction of clinical outcomes-encompassing both tumor control and adverse events (AEs). This review critically evaluates the evolution of data-driven approaches in predicting patient outcomes in head and neck cancer patients treated with radiation therapy, from traditional dose-volume constraints to cutting-edge artificial intelligence (AI) and causal inference framework. The integration of linear energy transfer in patient outcomes study, which has uncovered critical mechanisms behind unexpected toxicity, was also introduced for proton therapy. Three transformative methodological advances are reviewed: radiomics, AI-based algorithms, and causal inference frameworks. While radiomics has enabled quantitative characterization of medical images, AI models have demonstrated superior capability than traditional models. However, the field faces significant challenges in translating statistical correlations from real-world data into interventional clinical insights. We highlight that how causal inference methods can bridge this gap by providing a rigorous framework for identifying treatment effects. Looking ahead, we envision that combining these complementary approaches, especially the interventional prediction models, will enable more personalized treatment strategies, ultimately improving both tumor control and quality of life for head and neck cancer patients treated with radiation therapy.

Post-operative prognostication of patients diagnosed with Hurthle cell carcinoma: a machine learning approach

OBJECTIVES

To evaluate the performance of machine learning models in predicting the 5-year overall survival of patients with Hurthle cell carcinoma, and to identify significant prognostic factors influencing survival.

METHODS

A retrospective cohort study was conducted using data from the Surveillance, Epidemiology, and End Results database, encompassing patients treated between 2010 and 2015. Key variables included demographic information (age, sex, race), clinical characteristics (tumor size, T, N, M stages, and overall stage), and survival outcomes. Patients were included if they had complete data, were not censored before 60 months of follow-up, and had undergone thyroid surgery.

RESULTS

The study included 1,143 patients with a mean age of 57.7 years (standard deviation = 15.8). The cohort consisted of 770 females (67.4%) and was predominantly White (83.0%). Tumor classifications were varied, with T2 being most common (37.2%). The majority had no nodal involvement (94.1%) or distant metastasis (97.6%). The support vector model achieved the highest area under receiver characteristics operating curve of 0.8402 (95% CI: 0.7915 to 0.8847), indicating good predictive performance. Sensitivity and specificity were 81.16% and 73.72%, respectively. The Brier score for the model was 0.1223, demonstrating adequate calibration. Higher age and T classification were the most significant predictors of decreased survival, while being female was associated with increased survival.

CONCLUSION

Machine learning models, particularly the support vector model, effectively predicted 5-year overall survival in patients with Hurthle cell carcinoma. The study highlights age and tumor extent as critical prognostic factors.

Tumor-Agnostic Therapies in Practice: Challenges, Innovations, and Future Perspectives

This review comprehensively analyzes the current landscape of tumor-agnostic therapies in oncology. Tumor-agnostic therapies are designed to target specific molecular alterations rather than the primary site of the tumor, representing a shift in cancer treatment. We discuss recent approvals by regulatory agencies such as the FDA and EMA, highlighting therapies that have demonstrated efficacy across multiple cancer types sharing common alterations. We delve into the trial methodologies that underpin these approvals, emphasizing innovative designs such as basket trials and umbrella trials. These methodologies present unique advantages, including increased efficiency in patient recruitment and the ability to assess drug efficacy in diverse populations rapidly. However, they also entail certain challenges, including the need for robust biomarkers and the complexities of regulatory requirements. Moreover, we examine the promising prospects for developing therapies for rare cancers that exhibit common molecular targets typically associated with more prevalent malignancies. By synthesizing these insights, this review underscores the transformative potential of tumor-agnostic therapies in oncology. It offers a pathway for personalized cancer treatment that transcends conventional histology-based classification.

Machine learning in paediatric haematological malignancies: a systematic review of prognosis, toxicity and treatment response models

BACKGROUND

Machine Learning (ML) has demonstrated potential in enhancing care in adult oncology. However, its application in paediatric haematological malignancies is still emerging, necessitating a comprehensive review of its capabilities and limitations in this area.

METHODS

A literature search was conducted through Ovid. Studies included focused on ML models in paediatric patients with haematological malignancies. Studies were categorised into thematic groups for analysis.

RESULTS

Twenty studies, primarily on leukaemia, were included in this review. Studies were organised into thematic categories such as prognoses, treatment responses and toxicity predictions. Prognostic studies showed AUC scores between 0.685 and 0.929, indicating moderate-high predictive accuracy. Treatment response studies demonstrated AUC scores between 0.840 and 0.875, reflecting moderate accuracy. Toxicity prediction studies reported high accuracy with AUC scores from 0.870 to 0.927. Only five studies (25%) performed external validation. Significant heterogeneity was noted in ML tasks, reporting formats, and effect measures across studies, highlighting a lack of standardised reporting and challenges in data comparability.

CONCLUSION

The clinical applicability of these ML models remains limited by the lack of external validation and methodological heterogeneity. Addressing these challenges through standardised reporting and rigorous external validation is needed to translate ML from a promising research tool into a reliable clinical practice component.

IMPACT

Key message: Machine Learning (ML) significantly enhances predictive models in paediatric haematological cancers, offering new avenues for personalised treatment strategies. Future research should focus on developing ML models that can integrate with real-time clinical workflows. Addition to literature: Provides a comprehensive overview of current ML applications and trends. It identifies limitations to its applicability, including the limited diversity in datasets, which may affect the generalisability of ML models across different populations.

IMPACT

Encourages standardisation and external validation in ML studies, aiming to improve patient outcomes through precision medicine in paediatric haematological oncology.

Advances in machine learning for tumour classification in cancer of unknown primary: A mini-review

Cancers of unknown primary (CUP) are a heterogeneous group of aggressive metastatic cancers where standardised diagnostic techniques fail to identify the organ where it originated, resulting in a poor prognosis and resistance to treatment. Recent advances in large-scale sequencing techniques have enabled the identification of mutational signatures specific to particular tumour subtypes, even from liquid biopsy samples such as blood. This breakthrough paves the way for the development of new cost-effective diagnostic strategies. This mini-review explores recent advancements in Machine Learning (ML) and its application to tumour classification methods for CUP patients, identifying its weaknesses and strengths when classifying the tumour type. In the era of multi-omics, integrating several sources of information (e.g., imaging, molecular biomarkers, and family history) requires important theoretical advancements: increasing the dimensionality of the problem can result in lowering the predictive accuracy and robustness when data is scarce. Here, we review and discuss different architectures and strategies for incorporating cutting-edge machine learning into CUP diagnosis, aiming to bridge the gap between theory and clinical practice.

Predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer using a machine learning approach

BACKGROUND

For patients with breast cancer undergoing neoadjuvant chemotherapy (NACT), most of the existing prediction models of pathologic complete response (pCR) using clinicopathological features were based on standard statistical models like logistic regression, while models based on machine learning mostly utilized imaging data and/or gene expression data. This study aims to develop a robust and accessible machine learning model to predict pCR using clinicopathological features alone, which can be used to facilitate clinical decision-making in diverse settings.

METHODS

The model was developed and validated within the National Cancer Data Base (NCDB, 2018-2020) and an external cohort at the University of Chicago (2010-2020). We compared logistic regression and machine learning models, and examined whether incorporating quantitative clinicopathological features improved model performance. Decision curve analysis was conducted to assess the model's clinical utility.

RESULTS

We identified 56,209 NCDB patients receiving NACT (pCR rate: 34.0%). The machine learning model incorporating quantitative clinicopathological features showed the best discrimination performance among all the fitted models [area under the receiver operating characteristic curve (AUC): 0.785, 95% confidence interval (CI): 0.778-0.792], along with outstanding calibration performance. The model performed best among patients with hormone receptor positive/human epidermal growth factor receptor 2 negative (HR+/HER2-) breast cancer (AUC: 0.817, 95% CI: 0.802-0.832); and by adopting a 7% prediction threshold, the model achieved 90.5% sensitivity and 48.8% specificity, with decision curve analysis finding a 23.1% net reduction in chemotherapy use. In the external testing set of 584 patients (pCR rate: 33.4%), the model maintained robust performance both overall (AUC: 0.711, 95% CI: 0.668-0.753) and in the HR+/HER2- subgroup (AUC: 0.810, 95% CI: 0.742-0.878).

CONCLUSIONS

The study developed a machine learning model ( https://huolab.cri.uchicago.edu/sample-apps/pcrmodel ) to predict pCR in breast cancer patients undergoing NACT that demonstrated robust discrimination and calibration performance. The model performed particularly well among patients with HR+/HER2- breast cancer, having the potential to identify patients who are less likely to achieve pCR and can consider alternative treatment strategies over chemotherapy. The model can also serve as a robust baseline model that can be integrated with smaller datasets containing additional granular features in future research.

Early prediction of acute pancreatitis with acute kidney injury using abdominal contrast-enhanced CT features

Early prediction of acute pancreatitis (AP) with acute kidney injury (AKI) using abdominal contrast-enhanced CT could effectively reduce the mortality and the economic burden on patients and society. However, this challenge is limited by the imaging manifestations of early-stage AP that are not clearly visible to the naked eye. To address this, we developed a machine learning model using imperceptible variations in the structural changes of pancreas and peripancreatic region, extracted by radiomics and artificial intelligence technology, to screen and stratify the high-risk AP patients at the early stage of AP. The results demonstrate that the machine learning model could screen the high-risk AP with AKI patients with an area under the curve (AUC) of 0.82 for the external cohort, superior to the human radiologists. This finding confirms the significant potential of machine learning in the screening of acute pancreatitis and contributes to personalized treatment and management for AP patients.

The Role of Artificial Intelligence in the Diagnosis of Melanoma

The incidence of melanoma, the most aggressive form of skin cancer, continues to rise globally, particularly among fair-skinned populations (type I and II). Early detection is crucial for improving patient outcomes, and recent advancements in artificial intelligence (AI) have shown promise in enhancing the accuracy and efficiency of melanoma diagnosis and management. This review examines the role of AI in skin lesion diagnostics, highlighting two main approaches: machine learning, particularly convolutional neural networks (CNNs), and expert systems. AI techniques have demonstrated high accuracy in classifying dermoscopic images, often matching or surpassing dermatologists' performance. Integrating AI into dermatology has improved tasks, such as lesion classification, segmentation, and risk prediction, facilitating earlier and more accurate interventions. Despite these advancements, challenges remain, including biases in training data, interpretability issues, and integration of AI into clinical workflows. Ensuring diverse data representation and maintaining high standards of image quality are essential for reliable AI performance. Future directions involve the development of more sophisticated models, such as vision-language and multimodal models, and federated learning to address data privacy and generalizability concerns. Continuous validation and ethical integration of AI into clinical practice are vital for realizing its full potential for improving melanoma diagnosis and patient care.

Enhanced Immunohistochemistry Interpretation with a Machine Learning-Based Expert System

BACKGROUND

In recent decades, machine-learning (ML) technologies have advanced the management of high-dimensional and complex cancer data by developing reliable and user-friendly automated diagnostic tools for clinical applications. Immunohistochemistry (IHC) is an essential staining method that enables the identification of cellular origins by analyzing the expression of specific antigens within tissue samples. The aim of this study was to identify a model that could predict histopathological diagnoses based on specific immunohistochemical markers.

METHODS

The XGBoost learning model was applied, where the input variable (target variable) was the histopathological diagnosis and the predictors (independent variables influencing the target variable) were the immunohistochemical markers.

RESULTS

Our study demonstrated a precision rate of 85.97% within the dataset, indicating a high level of performance and suggesting that the model is generally reliable in producing accurate predictions.

CONCLUSIONS

This study demonstrated the feasibility and clinical efficacy of utilizing the probabilistic decision tree algorithm to differentiate tumor diagnoses according to immunohistochemistry profiles.

Collecting routine and timely cancer stage at diagnosis by implementing a cancer staging tiered framework: the Western Australian Cancer Registry experience

BACKGROUND

Current processes collecting cancer stage data in population-based cancer registries (PBCRs) lack standardisation, resulting in difficulty utilising diverse data sources and incomplete, low-quality data. Implementing a cancer staging tiered framework aims to improve stage collection and facilitate inter-PBCR benchmarking.

OBJECTIVE

Demonstrate the application of a cancer staging tiered framework in the Western Australian Cancer Staging Project to establish a standardised method for collecting cancer stage at diagnosis data in PBCRs.

METHODS

The tiered framework, developed in collaboration with a Project Advisory Group and applied to breast, colorectal, and melanoma cancers, provides business rules - procedures for stage collection. Tier 1 represents the highest staging level, involving complete American Joint Committee on Cancer (AJCC) tumour-node-metastasis (TNM) data collection and other critical staging information. Tier 2 (registry-derived stage) relies on supplementary data, including hospital admission data, to make assumptions based on data availability. Tier 3 (pathology stage) solely uses pathology reports.

FINDINGS

The tiered framework promotes flexible utilisation of staging data, recognising various levels of data completeness. Tier 1 is suitable for all purposes, including clinical and epidemiological applications. Tiers 2 and 3 are recommended for epidemiological analysis alone. Lower tiers provide valuable insights into disease patterns, risk factors, and overall disease burden for public health planning and policy decisions. Capture of staging at each tier depends on data availability, with potential shifts to higher tiers as new data sources are acquired.

CONCLUSIONS

The tiered framework offers a dynamic approach for PBCRs to record stage at diagnosis, promoting consistency in population-level staging data and enabling practical use for benchmarking across jurisdictions, public health planning, policy development, epidemiological analyses, and assessing cancer outcomes. Evolution with staging classifications and data variable changes will futureproof the tiered framework. Its adaptability fosters continuous refinement of data collection processes and encourages improvements in data quality.

Machine learning algorithms for the prognostication of abdominal aortic aneurysm progression: a systematic review

INTRODUCTION

Abdominal aortic aneurysm (AAA), often characterized by an abdominal aortic diameter over 3.0 cm, is managed through screening, surveillance, and surgical intervention. AAA growth can be heterogeneous and rupture carries a high mortality rate, with size and certain risk factors influencing rupture risk. Research is ongoing to accurately predict individual AAA growth rates for personalized management. Machine learning, a subset of artificial intelligence, has shown promise in various medical fields, including endoleak detection post-EVAR. However, its application for predicting AAA growth remains insufficiently explored, thus necessitating further investigation. Subsequently, this paper aims to summarize the current status of machine learning in predicting AAA growth.

EVIDENCE ACQUISITION

A systematic database search of Embase, MEDLINE, Cochrane, PubMed and Google Scholar from inception till December 2022 was conducted of original articles that discussed the use of machine learning in predicting AAA growth using the aforementioned databases.

EVIDENCE SYNTHESIS

Overall, 2742 articles were extracted, of which seven retrospective studies involving 410 patients were included using a predetermined criteria. Six out of seven studies applied a supervised learning approach for their machine learning (ML) models, with considerable diversity observed within specific ML models. The majority of the studies concluded that machine learning models perform better in predicting AAA growth in comparison to reference models. All studies focused on predicting AAA growth over specified durations. Maximal luminal diameter was the most frequently used indicator, with alternative predictors being AAA volume, ILT (intraluminal thrombus) and flow-medicated diameter (FMD).

CONCLUSIONS

The nascent field of applying machine learning (ML) for Abdominal Aortic Aneurysm (AAA) expansion prediction exhibits potential to enhance predictive accuracy across diverse parameters. Future studies must emphasize evidencing clinical utility in a healthcare system context, thereby ensuring patient outcome improvement. This will necessitate addressing key ethical implications in establishing prospective studies related to this topic and collaboration among pivotal stakeholders within the AI field.

The REthinking Clinical Trials Program Retreat 2023: Creating Partnerships to Optimize Quality Cancer Care

Patients, families, healthcare providers and funders face multiple comparable treatment options without knowing which provides the best quality of care. As a step towards improving this, the REthinking Clinical Trials (REaCT) pragmatic trials program started in 2014 to break down many of the traditional barriers to performing clinical trials. However, until other innovative methodologies become widely used, the impact of this program will remain limited. These innovations include the incorporation of near equivalence analyses and the incorporation of artificial intelligence (AI) into clinical trial design. Near equivalence analyses allow for the comparison of different treatments (drug and non-drug) using quality of life, toxicity, cost-effectiveness, and pharmacokinetic/pharmacodynamic data. AI offers unique opportunities to maximize the information gleaned from clinical trials, reduces sample size estimates, and can potentially "rescue" poorly accruing trials. On 2 May 2023, the first REaCT international symposium took place to connect clinicians and scientists, set goals and identify future avenues for investigator-led clinical trials. Here, we summarize the topics presented at this meeting to promote sharing and support other similarly motivated groups to learn and share their experiences.

Screening ovarian cancer by using risk factors: machine learning assists

BACKGROUND AND AIM

Ovarian cancer (OC) is a prevalent and aggressive malignancy that poses a significant public health challenge. The lack of preventive strategies for OC increases morbidity, mortality, and other negative consequences. Screening OC through risk prediction could be leveraged as a powerful strategy for preventive purposes that have not received much attention. So, this study aimed to leverage machine learning approaches as predictive assistance solutions to screen high-risk groups of OC and achieve practical preventive purposes.

MATERIALS AND METHODS

As this study is data-driven and retrospective in nature, we leveraged 1516 suspicious OC women data from one concentrated database belonging to six clinical settings in Sari City from 2015 to 2019. Six machine learning (ML) algorithms, including XG-Boost, Random Forest (RF), J-48, support vector machine (SVM), K-nearest neighbor (KNN), and artificial neural network (ANN) were leveraged to construct prediction models for OC. To choose the best model for predicting OC, we compared various prediction models built using the area under the receiver characteristic operator curve (AU-ROC).

RESULTS

Current experimental results revealed that the XG-Boost with AU-ROC = 0.93 (0.95 CI = [0.91-0.95]) was recognized as the best-performing model for predicting OC.

CONCLUSIONS

ML approaches possess significant predictive efficiency and interoperability to achieve powerful preventive strategies leveraging OC screening high-risk groups.

Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology

Machine Learning is entering a phase of maturity, but its medical applications still lag behind in terms of practical use. The field of oncological radiology (and neuro-oncology in particular) is at the forefront of these developments, now boosted by the success of Deep-Learning methods for the analysis of medical images. This paper reviews in detail some of the most recent advances in the use of Deep Learning in this field, from the broader topic of the development of Machine-Learning-based analytical pipelines to specific instantiations of the use of Deep Learning in neuro-oncology; the latter including its use in the groundbreaking field of ultra-low field magnetic resonance imaging.

Interpretable Machine Learning for Choosing Radiation Dose-volume Constraints on Cardio-pulmonary Substructures Associated with Overall Survival in NRG Oncology RTOG 0617

PURPOSE

Our objective was to use interpretable machine learning for choosing dose-volume constraints on cardiopulmonary substructures (CPSs) associated with overall survival (OS) in radiation therapy for locally advanced non-small cell lung cancer.

METHODS AND MATERIALS

A total of 428 patients with non-small cell lung cancer were randomly divided into training/validation/test subsets (n = 230/149/49) in Radiation Therapy Oncology Group 0617. Manual or automated contouring was performed to segment CPSs, including heart, atria, ventricles, aorta, left/right ventricle/atrium (LV+RV+LA+RA), inferior/superior vena cava, pulmonary artery, and pericardium. Peri (pericardium-heart), rest (heart-[LV+RV+LA+RA]), clinical target volume (CTV), and lungs-CTV contours were also obtained. Dose-volume histogram features were extracted, including minimum/mean dose to the hottest x% volume (Dx%[Gy]/MOHx%[Gy]), minimum/mean/maximum dose, percent volume receiving at least xGy (VxGy[%]), and overlapping volume of each CPS with planning target volume (PTV_Voverlap[%]). Clinical parameters were collected from the National Clinical Trials Network/Community oncology research program data archive. Feature selection was performed using a series of multiblock sparse partial least squares regression, stability selection supervised principal component analysis, and Boruta. Explainable boosting machine (EBM) was trained using a conditional survival distribution-based approach for imputing censored data, treating survival analysis as a regression problem. Harrell's C-index was used to evaluate OS discrimination performance of EBM, Cox proportional hazards (CPH), random survival forest, extreme gradient boosting survival embeddings, and CPH deep neural network (DeepSurv) models in the test set. Dose-volume constraints were selected using the binary change point detection algorithm in Shapley additive explanations-based partial dependence functions.

RESULTS

Selected features included LA_V60Gy(%), pericardium_D30%(Gy), lungs-CTV_PTV_Voverlap(%), RA_V55Gy(%), and received_cons_chemo. All models ranked LA_V60Gy(%) as the most important feature. EBM achieved the best performance for predicting OS, followed by extreme gradient boosting survival embeddings, random survival forest, DeepSurv, and CPH (C-index = 0.653, 0.646, 0.642, 0.638, and 0.632). EBM global explanations suggested that LA_V60Gy(%) < 25.6, lungs-CTV_PTV_Voverlap(%) < 1.1, pericardium_D30%(Gy) < 18.9, RA_V55Gy(%) < 19.5, and received_cons_chemo = 'Yes' for improved OS.

CONCLUSIONS

EBM can be used to discriminate OS while also guiding dose-volume constraint selection for optimal management of cardiac toxicity in lung cancer radiation therapy.

Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations

BACKGROUND

Machine learning (ML) represents a powerful tool to capture relationships between molecular alterations and cancer types and to extract biological information. Here, we developed a plain ML model aimed at distinguishing cancer types based on genetic lesions, providing an additional tool to improve cancer diagnosis, particularly for tumors of unknown origin.

METHODS

TCGA data from 9,927 samples spanning 32 different cancer types were downloaded from cBioportal. A vector space model type data transformation technique was designed to build consistently homogeneous new datasets containing, as predictive features, calls for somatic point mutations and copy number variations at chromosome arm-level, thus allowing the use of the XGBoost classifier models. Considering the imbalance in the dataset, due to large difference in the number of cases for each tumor, two preprocessing strategies were considered: i) setting a percentage cut-off threshold to remove less represented cancer types, ii) dividing cancer types into different groups based on biological criteria and training a specific XGBoost model for each of them. The performance of all trained models was mainly assessed by the out-of-sample balanced accuracy (BACC) and the AUC scores.

RESULTS

The XGBoost classifier achieved the best performance (BACC 77%; AUC 97%) on a dataset containing the 10 most represented tumor types. Moreover, dividing the 18 most represented cancers into three different groups (endocrine-related carcinomas, other carcinomas and other cancers),such analysis models achieved 78%, 71% and 86% BACC, respectively, with AUC scores greater than 96%. In addition, the model capable of linking each group to a specific cancer type reached 81% BACC and 94% AUC. Overall, the diagnostic potential of our model was comparable/higher with respect to others already described in literature and based on similar molecular data and ML approaches.

CONCLUSIONS

A boosted ML approach able to accurately discriminate different cancer types was developed. The methodology builds datasets simpler and more interpretable than the original data, while keeping enough information to accurately train standard ML models without resorting to sophisticated Deep Learning architectures. In combination with histopathological examinations, this approach could improve cancer diagnosis by using specific DNA alterations, processed by a replicable and easy-to-use automated technology. The study encourages new investigations which could further increase the classifier's performance, for example by considering more features and dividing tumors into their main molecular subtypes.

Artificial intelligence and allied subsets in early detection and preclusion of gynecological cancers

Gynecological cancers including breast, cervical, ovarian, uterine, and vaginal, pose the greatest threat to world health, with early identification being crucial to patient outcomes and survival rates. The application of machine learning (ML) and artificial intelligence (AI) approaches to the study of gynecological cancer has shown potential to revolutionize cancer detection and diagnosis. The current review outlines the significant advancements, obstacles, and prospects brought about by AI and ML technologies in the timely identification and accurate diagnosis of different types of gynecological cancers. The AI-powered technologies can use genomic data to discover genetic alterations and biomarkers linked to a particular form of gynecologic cancer, assisting in the creation of targeted treatments. Furthermore, it has been shown that the potential benefits of AI and ML technologies in gynecologic tumors can greatly increase the accuracy and efficacy of cancer diagnosis, reduce diagnostic delays, and possibly eliminate the need for needless invasive operations. In conclusion, the review focused on the integrative part of AI and ML based tools and techniques in the early detection and exclusion of various cancer types; together with a collaborative coordination between research clinicians, data scientists, and regulatory authorities, which is suggested to realize the full potential of AI and ML in gynecologic cancer care.

An interpretable AI model for recurrence prediction after surgery in gastrointestinal stromal tumour: an observational cohort study

Background

There are several models that predict the risk of recurrence following resection of localised, primary gastrointestinal stromal tumour (GIST). However, assessment of calibration is not always feasible and when performed, calibration of current GIST models appears to be suboptimal. We aimed to develop a prognostic model to predict the recurrence of GIST after surgery with both good discrimination and calibration by uncovering and harnessing the non-linear relationships among variables that predict recurrence.

Methods

In this observational cohort study, the data of 395 adult patients who underwent complete resection (R0 or R1) of a localised, primary GIST in the pre-imatinib era at Memorial Sloan Kettering Cancer Center (NY, USA) (recruited 1982-2001) and a European consortium (Spanish Group for Research in Sarcomas, 80 sites) (recruited 1987-2011) were used to train an interpretable Artificial Intelligence (AI)-based model called Optimal Classification Trees (OCT). The OCT predicted the probability of recurrence after surgery by capturing non-linear relationships among predictors of recurrence. The data of an additional 596 patients from another European consortium (Polish Clinical GIST Registry, 7 sites) (recruited 1981-2013) who were also treated in the pre-imatinib era were used to externally validate the OCT predictions with regard to discrimination (Harrell's C-index and Brier score) and calibration (calibration curve, Brier score, and Hosmer-Lemeshow test). The calibration of the Memorial Sloan Kettering (MSK) GIST nomogram was used as a comparative gold standard. We also evaluated the clinical utility of the OCT and the MSK nomogram by performing a Decision Curve Analysis (DCA).

Findings

The internal cohort included 395 patients (median [IQR] age, 63 [54-71] years; 214 men [54.2%]) and the external cohort included 556 patients (median [IQR] age, 60 [52-68] years; 308 men [55.4%]). The Harrell's C-index of the OCT in the external validation cohort was greater than that of the MSK nomogram (0.805 (95% CI: 0.803-0.808) vs 0.788 (95% CI: 0.786-0.791), respectively). In the external validation cohort, the slope and intercept of the calibration curve of the main OCT were 1.041 and 0.038, respectively. In comparison, the slope and intercept of the calibration curve for the MSK nomogram was 0.681 and 0.032, respectively. The MSK nomogram overestimated the recurrence risk throughout the entire calibration curve. Of note, the Brier score was lower for the OCT compared to the MSK nomogram (0.147 vs 0.564, respectively), and the Hosmer-Lemeshow test was insignificant (P = 0.087) for the OCT model but significant (P < 0.001) for the MSK nomogram. Both results confirmed the superior discrimination and calibration of the OCT over the MSK nomogram. A decision curve analysis showed that the AI-based OCT model allowed for superior decision making compared to the MSK nomogram for both patients with 25-50% recurrence risk as well as those with >50% risk of recurrence.

Interpretation

We present the first prognostic models of recurrence risk in GIST that demonstrate excellent discrimination, calibration, and clinical utility on external validation. Additional studies for further validation are warranted. With further validation, these tools could potentially improve patient counseling and selection for adjuvant therapy.

Funding

The NCI SPORE in Soft Tissue Sarcoma and NCI Cancer Center Support Grants.

Approach to machine learning for extraction of real-world data variables from electronic health records

Background: As artificial intelligence (AI) continues to advance with breakthroughs in natural language processing (NLP) and machine learning (ML), such as the development of models like OpenAI's ChatGPT, new opportunities are emerging for efficient curation of electronic health records (EHR) into real-world data (RWD) for evidence generation in oncology. Our objective is to describe the research and development of industry methods to promote transparency and explainability. Methods: We applied NLP with ML techniques to train, validate, and test the extraction of information from unstructured documents (e.g., clinician notes, radiology reports, lab reports, etc.) to output a set of structured variables required for RWD analysis. This research used a nationwide electronic health record (EHR)-derived database. Models were selected based on performance. Variables curated with an approach using ML extraction are those where the value is determined solely based on an ML model (i.e. not confirmed by abstraction), which identifies key information from visit notes and documents. These models do not predict future events or infer missing information. Results: We developed an approach using NLP and ML for extraction of clinically meaningful information from unstructured EHR documents and found high performance of output variables compared with variables curated by manually abstracted data. These extraction methods resulted in research-ready variables including initial cancer diagnosis with date, advanced/metastatic diagnosis with date, disease stage, histology, smoking status, surgery status with date, biomarker test results with dates, and oral treatments with dates. Conclusion: NLP and ML enable the extraction of retrospective clinical data in EHR with speed and scalability to help researchers learn from the experience of every person with cancer.

Multilingual RECIST classification of radiology reports using supervised learning

Objectives

The objective of this study is the exploration of Artificial Intelligence and Natural Language Processing techniques to support the automatic assignment of the four Response Evaluation Criteria in Solid Tumors (RECIST) scales based on radiology reports. We also aim at evaluating how languages and institutional specificities of Swiss teaching hospitals are likely to affect the quality of the classification in French and German languages.

Methods

In our approach, 7 machine learning methods were evaluated to establish a strong baseline. Then, robust models were built, fine-tuned according to the language (French and German), and compared with the expert annotation.

Results

The best strategies yield average F1-scores of 90% and 86% respectively for the 2-classes (Progressive/Non-progressive) and the 4-classes (Progressive Disease, Stable Disease, Partial Response, Complete Response) RECIST classification tasks.

Conclusions

These results are competitive with the manual labeling as measured by Matthew's correlation coefficient and Cohen's Kappa (79% and 76%). On this basis, we confirm the capacity of specific models to generalize on new unseen data and we assess the impact of using Pre-trained Language Models (PLMs) on the accuracy of the classifiers.

Machine Learning of Multi-Modal Tumor Imaging Reveals Trajectories of Response to Precision Treatment

The standard assessment of response to cancer treatments is based on gross tumor characteristics, such as tumor size or glycolysis, which provide very indirect information about the effect of precision treatments on the pharmacological targets of tumors. Several advanced imaging modalities allow for the visualization of targeted tumor hallmarks. Descriptors extracted from these images can help establishing new classifications of precision treatment response. We propose a machine learning (ML) framework to analyze metabolic-anatomical-vascular imaging features from positron emission tomography, ultrafast Doppler, and computed tomography in a mouse model of paraganglioma undergoing anti-angiogenic treatment with sunitinib. Imaging features from the follow-up of sunitinib-treated (n = 8, imaged once-per-week/6-weeks) and sham-treated (n = 8, imaged once-per-week/3-weeks) mice groups were dimensionally reduced and analyzed with hierarchical clustering Analysis (HCA). The classes extracted from HCA were used with 10 ML classifiers to find a generalized tumor stage prediction model, which was validated with an independent dataset of sunitinib-treated mice. HCA provided three stages of treatment response that were validated using the best-performing ML classifier. The Gaussian naive Bayes classifier showed the best performance, with a training accuracy of 98.7 and an average area under curve of 100. Our results show that metabolic-anatomical-vascular markers allow defining treatment response trajectories that reflect the efficacy of an anti-angiogenic drug on the tumor target hallmark.

Data-centric artificial intelligence in oncology: a systematic review assessing data quality in machine learning models for head and neck cancer

Machine learning models have been increasingly considered to model head and neck cancer outcomes for improved screening, diagnosis, treatment, and prognostication of the disease. As the concept of data-centric artificial intelligence is still incipient in healthcare systems, little is known about the data quality of the models proposed for clinical utility. This is important as it supports the generalizability of the models and data standardization. Therefore, this study overviews the quality of structured and unstructured data used for machine learning model construction in head and neck cancer. Relevant studies reporting on the use of machine learning models based on structured and unstructured custom datasets between January 2016 and June 2022 were sourced from PubMed, EMBASE, Scopus, and Web of Science electronic databases. Prediction model Risk of Bias Assessment (PROBAST) tool was used to assess the quality of individual studies before comprehensive data quality parameters were assessed according to the type of dataset used for model construction. A total of 159 studies were included in the review; 106 utilized structured datasets while 53 utilized unstructured datasets. Data quality assessments were deliberately performed for 14.2% of structured datasets and 11.3% of unstructured datasets before model construction. Class imbalance and data fairness were the most common limitations in data quality for both types of datasets while outlier detection and lack of representative outcome classes were common in structured and unstructured datasets respectively. Furthermore, this review found that class imbalance reduced the discriminatory performance for models based on structured datasets while higher image resolution and good class overlap resulted in better model performance using unstructured datasets during internal validation. Overall, data quality was infrequently assessed before the construction of ML models in head and neck cancer irrespective of the use of structured or unstructured datasets. To improve model generalizability, the assessments discussed in this study should be introduced during model construction to achieve data-centric intelligent systems for head and neck cancer management.

On the importance of interpretable machine learning predictions to inform clinical decision making in oncology

Machine learning-based tools are capable of guiding individualized clinical management and decision-making by providing predictions of a patient's future health state. Through their ability to model complex nonlinear relationships, ML algorithms can often outperform traditional statistical prediction approaches, but the use of nonlinear functions can mean that ML techniques may also be less interpretable than traditional statistical methodologies. While there are benefits of intrinsic interpretability, many model-agnostic approaches now exist and can provide insight into the way in which ML systems make decisions. In this paper, we describe how different algorithms can be interpreted and introduce some techniques for interpreting complex nonlinear algorithms.

The dominant logic of Big Tech in healthcare and pharma

Digital health and digital pharma are considered supportive tools for patients and healthcare providers (HCPs), making the market highly attractive for industry players. Not surprisingly, Tech Giants have started to move into this area. We utilized established management models and publicly available information sources, such as annual company reports, and performed a thorough analysis to uncover the underlying business models of Alphabet, Amazon, Apple, IBM, and Microsoft in order to better understand their intention and course of entering the healthcare and pharma industries. Our results indicate that Big Tech or Tech Giants do address the needs of patients and physicians, while having built clear value propositions, value chains, and revenue models to sustainably revolutionize the healthcare and pharma industries.

Artificial intelligence in cancer research and precision medicine: Applications, limitations and priorities to drive transformation in the delivery of equitable and unbiased care

Artificial intelligence (AI) has experienced explosive growth in oncology and related specialties in recent years. The improved expertise in data capture, the increased capacity for data aggregation and analytic power, along with decreasing costs of genome sequencing and related biologic "omics", set the foundation and need for novel tools that can meaningfully process these data from multiple sources and of varying types. These advances provide value across biomedical discovery, diagnosis, prognosis, treatment, and prevention, in a multimodal fashion. However, while big data and AI tools have already revolutionized many fields, medicine has partially lagged due to its complexity and multi-dimensionality, leading to technical challenges in developing and validating solutions that generalize to diverse populations. Indeed, inner biases and miseducation of algorithms, in view of their implementation in daily clinical practice, are increasingly relevant concerns; critically, it is possible for AI to mirror the unconscious biases of the humans who generated these algorithms. Therefore, to avoid worsening existing health disparities, it is critical to employ a thoughtful, transparent, and inclusive approach that involves addressing bias in algorithm design and implementation along the cancer care continuum. In this review, a broad landscape of major applications of AI in cancer care is provided, with a focus on cancer research and precision medicine. Major challenges posed by the implementation of AI in the clinical setting will be discussed. Potentially feasible solutions for mitigating bias are provided, in the light of promoting cancer health equity.

Microfluidics for Profiling miRNA Biomarker Panels in AI-Assisted Cancer Diagnosis and Prognosis

Early detection of cancers and their precise subtyping are essential to patient stratification and effective cancer management. Data-driven identification of expression biomarkers coupled with microfluidics-based detection shows promise to revolutionize cancer diagnosis and prognosis. MicroRNAs play key roles in cancers and afford detection in tissue and liquid biopsies. In this review, we focus on the microfluidics-based detection of miRNA biomarkers in AI-based models for early-stage cancer subtyping and prognosis. We describe various subclasses of miRNA biomarkers that could be useful in machine-based predictive modeling of cancer staging and progression. Strategies for optimizing the feature space of miRNA biomarkers are necessary to obtain a robust signature panel. This is followed by a discussion of the issues in model construction and validation towards producing Software-as-Medical-Devices (SaMDs). Microfluidic devices could facilitate the multiplexed detection of miRNA biomarker panels, and an overview of the different strategies for designing such microfluidic systems is presented here, with an outline of the detection principles used and the corresponding performance measures. Microfluidics-based profiling of miRNAs coupled with SaMD represent high-performance point-of-care solutions that would aid clinical decision-making and pave the way for accessible precision personalized medicine.

Prediction of chemotherapy-related complications in pediatric oncology patients: artificial intelligence and machine learning implementations

Although the overall incidence of pediatric oncological diseases tends to increase over the years, it is among the rare diseases of the pediatric population. The diagnosis, treatment, and healthcare management of this group of diseases are important. Prevention of treatment-related complications is vital for patients, particularly in the pediatric population. Nowadays, the use of artificial intelligence and machine learning technologies in the management of oncological diseases is becoming increasingly important. With the advancement of software technologies, improvements have been made in the early diagnosis of risk groups in oncological diseases, in radiology, pathology, and imaging technologies, in cancer staging and management. In addition, these technologies can be used to predict the outcome in chemotherapy treatment of oncological diseases. In this context, this study identifies artificial intelligence and machine learning methods used in the prediction of complications due to chemotherapeutic agents used in childhood cancer treatment. For this purpose, the concepts of artificial intelligence and machine learning are explained in this review. A general framework for the use of machine learning in healthcare and pediatric oncology has been drawn and examples of studies conducted on this topic in pediatric oncology have been given. IMPACT: Artificial intelligence and machine learning are advanced tools that can be used to predict chemotherapy-related complications. Algorithms can assist clinicians' decision-making processes in the management of complications. Although studies are using these methods, there is a need to increase the number of studies on artificial intelligence applications in pediatric clinics.

Artificial Intelligence and Advanced Melanoma: Treatment Management Implications

Artificial intelligence (AI), a field of research in which computers are applied to mimic humans, is continuously expanding and influencing many aspects of our lives. From electric cars to search motors, AI helps us manage our daily lives by simplifying functions and activities that would be more complex otherwise. Even in the medical field, and specifically in oncology, many studies in recent years have highlighted the possible helping role that AI could play in clinical and therapeutic patient management. In specific contexts, clinical decisions are supported by "intelligent" machines and the development of specific softwares that assist the specialist in the management of the oncology patient. Melanoma, a highly heterogeneous disease influenced by several genetic and environmental factors, to date is still difficult to manage clinically in its advanced stages. Therapies often fail, due to the establishment of intrinsic or secondary resistance, making clinical decisions complex. In this sense, although much work still needs to be conducted, numerous evidence shows that AI (through the processing of large available data) could positively influence the management of the patient with advanced melanoma, helping the clinician in the most favorable therapeutic choice and avoiding unnecessary treatments that are sure to fail. In this review, the most recent applications of AI in melanoma will be described, focusing especially on the possible finding of this field in the management of drug treatments.

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Background

The impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.

Methods

PubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.

Results

ML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.

Conclusion

Overall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

Artificial intelligence for multimodal data integration in oncology

In oncology, the patient state is characterized by a whole spectrum of modalities, ranging from radiology, histology, and genomics to electronic health records. Current artificial intelligence (AI) models operate mainly in the realm of a single modality, neglecting the broader clinical context, which inevitably diminishes their potential. Integration of different data modalities provides opportunities to increase robustness and accuracy of diagnostic and prognostic models, bringing AI closer to clinical practice. AI models are also capable of discovering novel patterns within and across modalities suitable for explaining differences in patient outcomes or treatment resistance. The insights gleaned from such models can guide exploration studies and contribute to the discovery of novel biomarkers and therapeutic targets. To support these advances, here we present a synopsis of AI methods and strategies for multimodal data fusion and association discovery. We outline approaches for AI interpretability and directions for AI-driven exploration through multimodal data interconnections. We examine challenges in clinical adoption and discuss emerging solutions.

Using machine learning to predict individual patient toxicities from cancer treatments

PURPOSE

Machine learning (ML) is a powerful tool for interrogating datasets and learning relationships between multiple variables. We utilized a ML model to identify those early breast cancer (EBC) patients at highest risk of developing severe vasomotor symptoms (VMS).

METHODS

A gradient boosted decision model utilizing cross-sectional survey data from 360 EBC patients was created. Seventeen patient- and treatment-specific variables were considered in the model. The outcome variable was based on the Hot Flush Night Sweats (HFNS) Problem Rating Score, and individual scores were dichotomized around the median to indicate individuals with high and low problem scores. Model accuracy was assessed using the area under the receiver operating curve, and conditional partial dependence plots were constructed to illustrate relationships between variables and the outcome of interest.

RESULTS

The model area under the ROC curve was 0.731 (SD 0.074). The most important variables in the model were as follows: the number of hot flashes per week, age, the prescription, or use of drug interventions to manage VMS, whether patients were asked about VMS in routine follow-up visits, and the presence or absence of changes to breast cancer treatments due to VMS. A threshold of 17 hot flashes per week was identified as being more predictive of severe VMS. Patients between the ages of 49 and 63 were more likely to report severe symptoms.

CONCLUSION

Machine learning is a unique tool for predicting severe VMS. The use of ML to assess other treatment-related toxicities and their management requires further study.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

Plasma secretome analyses identify IL-8 and nitrites as predictors of poor prognosis in nasopharyngeal carcinoma patients

Predicting tumor recurrence and death in patients with nasopharyngeal carcinoma (NPC) remains to date challenging. We here analyzed the plasmatic secretomes of NPC untreated and relapsing patients, and explored possible correlations with the clinical and pathological features and survival characteristics of the corresponding patient cohorts, with the aim of identifying novel prognostic biomarkers. This study included 27 controls, 45 untreated NPC and 11 relapsed patients. A set of 14 plasma cytokines were analyzed using Millipore multiplex assay. Nitrites were assessed by Griess method. A comparative analysis of each groups' secretome showed upregulation of IL-8, IL-12p70, IL-10 and IP-10 in untreated patients, and of IL-6, IL-10, MCP-1 and IP-10 in relapsing patients. Nitrites significantly correlated with IL-8 during relapse. Secretomes' network analyses revealed prevalence of high correlations between IL8/IL-17A and IFN-γ/IL12p70 in the control group, between TNF-α/IL-8/IL-6, TNF-α/VEGF/IFN-γ and IL-10/MCP-1 in the untreated group, and between IL-8/IL-6/IL-10, TNF-α/IL-8/IL-6, IL12-p70/VEGF/IL-10/IFN-γ, IL-6/IL-10/IFN-γ and IL-8/IP-10 in the relapse group. IL-12p70, IP-10 and MCP-1 levels respectively associated with gender, age and node metastasis respectively. Recurrence-free survival (RFS) analysis showed that patients presenting High IL-8/Low NO immunological scores presented a combined 80% probability of relapse/death after 53 months (combined log-rank test p = 0.0034; individual p = 0.012 and p = 0.016). Multivariate Cox hazard regression analysis revealed that IL-8 (HR = 7.451; 95% CI [2.398-23.152]; p = 0.001) and treatment type (HR = 0.232; 95% CI 0.072-0.749; p = 0.015) were independent prognostic factors. C&RT decision tree analysis showed that High IL-8/Low NO immunological scores predicted treatment failure in 50% cases starting the 36th month of follow-up (AUC = 1) for all of the studied cases and in 57% cases for patients receiving chemotherapy alone (AUC = 1). Altogether, our results showed that NPC development is accompanied with cytokines deregulation to form specific interaction networks at time of diagnosis and relapse, and demonstrate that High IL-8/Low NO signature may constitute a predictor of poor prognosis which may be useful to improve risk stratification and therapy failure management.

Artificial intelligence in mammographic phenotyping of breast cancer risk: a narrative review

BACKGROUND

Improved breast cancer risk assessment models are needed to enable personalized screening strategies that achieve better harm-to-benefit ratio based on earlier detection and better breast cancer outcomes than existing screening guidelines. Computational mammographic phenotypes have demonstrated a promising role in breast cancer risk prediction. With the recent exponential growth of computational efficiency, the artificial intelligence (AI) revolution, driven by the introduction of deep learning, has expanded the utility of imaging in predictive models. Consequently, AI-based imaging-derived data has led to some of the most promising tools for precision breast cancer screening.

MAIN BODY

This review aims to synthesize the current state-of-the-art applications of AI in mammographic phenotyping of breast cancer risk. We discuss the fundamentals of AI and explore the computing advancements that have made AI-based image analysis essential in refining breast cancer risk assessment. Specifically, we discuss the use of data derived from digital mammography as well as digital breast tomosynthesis. Different aspects of breast cancer risk assessment are targeted including (a) robust and reproducible evaluations of breast density, a well-established breast cancer risk factor, (b) assessment of a woman's inherent breast cancer risk, and (c) identification of women who are likely to be diagnosed with breast cancers after a negative or routine screen due to masking or the rapid and aggressive growth of a tumor. Lastly, we discuss AI challenges unique to the computational analysis of mammographic imaging as well as future directions for this promising research field.

CONCLUSIONS

We provide a useful reference for AI researchers investigating image-based breast cancer risk assessment while indicating key priorities and challenges that, if properly addressed, could accelerate the implementation of AI-assisted risk stratification to future refine and individualize breast cancer screening strategies.

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

The interpretation of imaging in medicine in general and in oncology specifically remains problematic due to several limitations which include the need to incorporate detailed clinical history, patient and disease-specific history, clinical exam features, previous and ongoing treatment, and account for the dependency on reproducible human interpretation of multiple factors with incomplete data linkage. To standardize reporting, minimize bias, expedite management, and improve outcomes, the use of Artificial Intelligence (AI) has gained significant prominence in imaging analysis. In oncology, AI methods have as a result been explored in most cancer types with ongoing progress in employing AI towards imaging for oncology treatment, assessing treatment response, and understanding and communicating prognosis. Challenges remain with limited available data sets, variability in imaging changes over time augmented by a growing heterogeneity in analysis approaches. We review the imaging analysis workflow and examine how hand-crafted features also referred to as traditional Machine Learning (ML), Deep Learning (DL) approaches, and hybrid analyses, are being employed in AI-driven imaging analysis in central nervous system tumors. ML, DL, and hybrid approaches coexist, and their combination may produce superior results although data in this space is as yet novel, and conclusions and pitfalls have yet to be fully explored. We note the growing technical complexities that may become increasingly separated from the clinic and enforce the acute need for clinician engagement to guide progress and ensure that conclusions derived from AI-driven imaging analysis reflect that same level of scrutiny lent to other avenues of clinical research.

Applications of Artificial Intelligence in Pediatric Oncology: A Systematic Review

PURPOSE

There is a need for an improved understanding of clinical and biologic risk factors in pediatric cancer to improve patient outcomes. Machine learning (ML) represents the application of computational inference from advanced statistical methods that can be applied to increasing amount of data available for study in pediatric oncology. The goal of this systematic review was to systematically characterize the state of ML in pediatric oncology and highlight advances and opportunities in the field.

METHODS

We conducted a systematic review of the Embase, Scopus, and MEDLINE databases for applications of ML in pediatric oncology. Query results from all three databases were aggregated and duplicate studies were removed.

RESULTS

A total of 42 unique articles that examined the applications of ML in pediatric oncology met inclusion criteria for review. We identified 20 studies of CNS tumors, 13 of solid tumors, and nine of leukemia. ML tasks included classification, prediction of treatment response, and dose optimization with a variety of methods being used including neural network, k-nearest neighbor, random forest, naive Bayes, and support vector machines. Strengths of the identified studies included matching or outperforming physician comparators via automated analysis and predicting therapeutic response. Common limitations included significant heterogeneity in reporting standards, clinical applicability, small sample sizes, and missing external validation cohorts.

CONCLUSION

We identified areas where ML can enhance clinical care in ways that may not otherwise be achievable. Although ML promises enormous potential in improving diagnostics, decision making, and monitoring for children with cancer, the field remains in early stages and future work will be aided by standards and guidelines to ensure rigorous methodologic design and maximizing clinical utility.

Computing the Hazard Ratios Associated With Explanatory Variables Using Machine Learning Models of Survival Data

PURPOSE

The application of Cox proportional hazards (CoxPH) models to survival data and the derivation of hazard ratio (HR) are well established. Although nonlinear, tree-based machine learning (ML) models have been developed and applied to the survival analysis, no methodology exists for computing HRs associated with explanatory variables from such models. We describe a novel way to compute HRs from tree-based ML models using the SHapley Additive exPlanation values, which is a locally accurate and consistent methodology to quantify explanatory variables' contribution to predictions.

METHODS

We used three sets of publicly available survival data consisting of patients with colon, breast, or pan cancer and compared the performance of CoxPH with the state-of-the-art ML model, XGBoost. To compute the HR for explanatory variables from the XGBoost model, the SHapley Additive exPlanation values were exponentiated and the ratio of the means over the two subgroups was calculated. The CI was computed via bootstrapping the training data and generating the ML model 1,000 times. Across the three data sets, we systematically compared HRs for all explanatory variables. Open-source libraries in Python and R were used in the analyses.

RESULTS

For the colon and breast cancer data sets, the performance of CoxPH and XGBoost was comparable, and we showed good consistency in the computed HRs. In the pan-cancer data set, we showed agreement in most variables but also an opposite finding in two of the explanatory variables between the CoxPH and XGBoost result. Subsequent Kaplan-Meier plots supported the finding of the XGBoost model.

CONCLUSION

Enabling the derivation of HR from ML models can help to improve the identification of risk factors from complex survival data sets and to enhance the prediction of clinical trial outcomes.

A Quantitative Paradigm for Decision-Making in Precision Oncology

The complexity and variability of cancer progression necessitate a quantitative paradigm for therapeutic decision-making that is dynamic, personalized, and capable of identifying optimal treatment strategies for individual patients under substantial uncertainty. Here, we discuss the core components and challenges of such an approach and highlight the need for comprehensive longitudinal clinical and molecular data integration in its development. We describe the complementary and varied roles of mathematical modeling and machine learning in constructing dynamic optimal cancer treatment strategies and highlight the potential of reinforcement learning approaches in this endeavor.