Artificial Intelligence, Machine Learning and Big Data in Radiation Oncology

This review explores the applications of artificial intelligence and machine learning (AI/ML) in radiation oncology, focusing on computer vision (CV) and natural language processing (NLP) techniques. We examined CV-based AI/ML in digital pathology and radiomics, highlighting the prospective clinical studies demonstrating their utility. We also reviewed NLP-based AI/ML applications in clinical documentation analysis, knowledge assessment, and quality assurance. While acknowledging the challenges for clinical adoption, this review underscores the transformative potential of AI/ML in enhancing precision, efficiency, and quality of care in radiation oncology.

Patterns in Symptoms Preceding Acute Care in Patients With Cancer

Importance

Patients with cancer frequently experience unplanned acute care with emergency department visits and hospitalization due to disease or treatment complications, which impacts outcomes, quality of life, and health care costs. There remains a knowledge gap in understanding patterns of symptoms that precede acute care events. Natural language processing (NLP) may enable greater understanding of the symptoms and identify differences across patient and cancer characteristics.

Objective

To characterize symptoms preceding acute care in patients with cancer and quantify differences in symptom documentation across sociodemographic and cancer histologic subgroups.

Design, Setting, and Participants

A cohort study in a single tertiary-care institution, including all acute care (emergency department and hospitalization) encounters for patients aged 18 years or older with a primary cancer diagnosis identified between January 1, 2013, and December 31, 2023.

Main Outcomes and Measures

Natural language processing was used to identify routine clinical documentation to characterize symptoms documented in the 30 days preceding acute care. Logistic regression analyses was used to examine the possible association between sex, age, race and ethnicity, insurance coverage, cancer histologic characteristics, and reported symptoms.

Results

Overall, 28 708 patients with cancer had 70 606 acute care visits with 854 830 associated preceding documented symptoms. Median age was 61 (IQR, 48-70) years. Men (37 861 encounters [53.62%]) and patients of White race (39 989 encounters [56.64%]) accounted for most acute care encounters. Pain (7.54% of documented symptoms), nausea (6.74%), and vomiting (5.79%) were the most frequently documented symptoms. Acute care encounters with patients who were female (adjusted odds ratio [AOR], 1.14; 95% CI, 1.10-1.18; P < .001), Asian (AOR, 1.22; 1.17-1.28; P < .001), Black (AOR, 1.17; 95% CI, 1.10-1.25; P < .001), American Indian or Alaska Native (AOR, 1.21; 95% CI, 1.01-1.44; P = .04), or Medicaid-insured (AOR, 1.10; 95% CI, 1.05-1.14; P < .001) were associated with a high documented symptom burden (>10 unique symptoms) preceding acute care visits. Patients aged 65 years or older (AOR, 0.96; 95% CI, 0.92-1.00; P = .04) or uninsured (AOR, 0.58; 95% CI, 0.45-0.76; P < .001) were less likely to have a high symptom burden documented before acute care events.

Conclusions and Relevance

The findings of this study highlight common symptoms preceding acute care as well as the need for further research on interventions to reduce patient burden, improve quality of life, and reduce the use of acute care in patients with cancer.

Continuous multimodal data supply chain and expandable clinical decision support for oncology

The study introduces a clinical decision support system (CDSS) developed at a single academic cancer center, integrating real-time clinical, genomic, and imaging data for over 170,000 patients across 11 cancer types. We have developed the Yonsei Cancer Data Library (YCDL) data integration framework to continuously collect and update multimodal datasets comprising over 800 features per case. Quality control measures, using 143 logical comparisons, addressed missing data and outliers, achieving median accuracies of 92.6% for surgical and 98.7% for molecular pathology. An Extract-Transform-Load (ETL) process with natural language processing transformed unstructured data, enabling survival analyses stratified by tumor stage, which revealed significant stage-dependent differences. The CDSS dashboard visualizes patient trajectories and key milestones. User feedback from oncology professionals showed strong acceptance, with satisfaction scores exceeding 4 out of 5. This framework demonstrates the potential of multimodal data integration to enhance clinical decision-making and patient outcomes, with future research needed to validate its generalizability and scalability.

Effectiveness of Dyadic Interventions on Quality of Life for Cancer Patients and Family Caregivers: A Systematic Review and Meta-Analysis of Randomised Controlled Trials

BACKGROUND

Increases in cancer survivorship negatively impact patients and family caregivers, decreasing quality of life. Previous dyadic interventions involved them as a unit and focused on their outcomes, but inconsistent results existed in influencing quality of life.

OBJECTIVES

To assess dyadic intervention effect on quality of life for cancer patients and family caregivers across different cancer types and intervention durations.

DESIGN

A systematic review and meta-analysis based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA).

METHODS

Six databases were searched from establishment until 14 January 2024. Two authors independently performed the search process, literature screening, and data extraction. The ROB version 2 and GRADE were respectively used to check the methodology and evidence quality. The data were analysed via RStudio, and intervention effects were estimated with 95% CIs and SMDs. The statistical heterogeneity was explored through the I2 statistic, P values, and Egger's test, and differences in overall effects were deemed statistically significant, having a P value < 0.05. Subgroup analysis was also conducted.

RESULTS

13 RCTs with 1625 participants, published from 2005 to 2021, were included. The results demonstrated that dyadic interventions enhanced quality of life for both cancer patients and family caregivers. Subgroup analysis suggested that family-centred interventions for patients with specific cancer types, which lasted for a long period (> 6 weeks), enhanced quality of life for cancer patients and family caregivers. The evidence and methodology were of a moderate quality.

CONCLUSIONS

Nurses are important practitioners of culture-oriented dyadic interventions. Long-term (> 6 weeks) and family-centred dyadic interventions for patients with a specific cancer type can enhance cancer patients' and family caregivers' quality of life, along with digital intelligence approaches to promote mutual communication and strengthen family relationships, thereby optimising oncology clinical nursing and enhancing the quality of life, health, and welfare of the entire family.

RELEVANCE TO CLINICAL PRACTICE

Dyadic interventions emphasising the involvement of both cancer patients and family caregivers should be considered and tailored by professionals and oncology nurses to establish harmonious family relationships, improve family coping techniques and decision-making to enhance the whole family's quality of life and well-being according to their cultural contexts, and promote more efficient, targeted, and economical oncology care.

PATIENT OR PUBLIC CONTRIBUTION

No Patient or Public Contribution because all the involved participants were from existing studies, and the design, conduction, analysis, and interpretation of the data were completed by the authors in this article.

TRIAL REGISTRATION

International Prospective Register of Systematic Reviews: CRD42024519432; https://www.crd.york.ac.uk/PROSPERO/#recordDetails.

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.

Benefits and harms associated with the use of AI-related algorithmic decision-making systems by healthcare professionals: a systematic review

Background

Despite notable advancements in artificial intelligence (AI) that enable complex systems to perform certain tasks more accurately than medical experts, the impact on patient-relevant outcomes remains uncertain. To address this gap, this systematic review assesses the benefits and harms associated with AI-related algorithmic decision-making (ADM) systems used by healthcare professionals, compared to standard care.

Methods

In accordance with the PRISMA guidelines, we included interventional and observational studies published as peer-reviewed full-text articles that met the following criteria: human patients; interventions involving algorithmic decision-making systems, developed with and/or utilizing machine learning (ML); and outcomes describing patient-relevant benefits and harms that directly affect health and quality of life, such as mortality and morbidity. Studies that did not undergo preregistration, lacked a standard-of-care control, or pertained to systems that assist in the execution of actions (e.g., in robotics) were excluded. We searched MEDLINE, EMBASE, IEEE Xplore, and Google Scholar for studies published in the past decade up to 31 March 2024. We assessed risk of bias using Cochrane's RoB 2 and ROBINS-I tools, and reporting transparency with CONSORT-AI and TRIPOD-AI. Two researchers independently managed the processes and resolved conflicts through discussion. This review has been registered with PROSPERO (CRD42023412156) and the study protocol has been published.

Findings

Out of 2,582 records identified after deduplication, 18 randomized controlled trials (RCTs) and one cohort study met the inclusion criteria, covering specialties such as psychiatry, oncology, and internal medicine. Collectively, the studies included a median of 243 patients (IQR 124-828), with a median of 50.5% female participants (range 12.5-79.0, IQR 43.6-53.6) across intervention and control groups. Four studies were classified as having low risk of bias, seven showed some concerns, and another seven were assessed as having high or serious risk of bias. Reporting transparency varied considerably: six studies showed high compliance, four moderate, and five low compliance with CONSORT-AI or TRIPOD-AI. Twelve studies (63%) reported patient-relevant benefits. Of those with low risk of bias, interventions reduced length of stay in hospital and intensive care unit (10.3 vs. 13.0 days, p = 0.042; 6.3 vs. 8.4 days, p = 0.030), in-hospital mortality (9.0% vs. 21.3%, p = 0.018), and depression symptoms in non-complex cases (45.1% vs. 52.3%, p = 0.03). However, harms were frequently underreported, with only eight studies (42%) documenting adverse events. No study reported an increase in adverse events as a result of the interventions.

Interpretation

The current evidence on AI-related ADM systems provides limited insights into patient-relevant outcomes. Our findings underscore the essential need for rigorous evaluations of clinical benefits, reinforced compliance with methodological standards, and balanced consideration of both benefits and harms to ensure meaningful integration into healthcare practice.

Funding

This study did not receive any funding.

Artificial intelligence in oncology: ensuring safe and effective integration of language models in clinical practice

In this Personal View, we address the latest advancements in automatic text analysis with artificial intelligence (AI) in medicine, with a focus on its implications in aiding treatment decisions in medical oncology. Acknowledging that a majority of hospital medical content is embedded in narrative format, natural language processing has become one of the most dynamic research fields for developing clinical decision support tools. In addition, large language models have recently reached unprecedented performance, notably when answering medical questions. Emerging applications include prognosis estimation, treatment recommendations, multidisciplinary tumor board recommendations and matching patients to recruiting clinical trials. Altogether, we advocate for a forward-looking approach in which the community efficiently initiates global prospective clinical evaluations of promising AI-based decision support systems. Such assessments will be essential to validate and evaluate potential biases, ensuring these innovations can be effectively and safely translated into practical tools for oncological practice. We are at a pivotal moment, where continued advancements in patient care must be pursued with scientific rigor.

Spending Analysis of Machine Learning-Based Communication Nudges in Oncology

BACKGROUND

Serious illness conversations (SICs) in the outpatient setting may improve mood and quality of life among patients with cancer and decrease aggressive end-of-life care. Interventions informed by behavioral economics may increase rates of SICs between oncology clinicians and patients, but the impact of these interventions on end-of-life spending is unknown.

METHODS

This study is a secondary analysis of a stepped-wedge cluster randomized, controlled trial that involved nine medical oncology practices and their high-risk patients at a large academic institution between June 2019 and April 2020. The study included 1187 patients who were identified by a machine-learning algorithm as high risk of 180-day mortality and who died by December 2020. The patients were randomly assigned to standard of care (controls) or to a behavioral intervention designed to increase clinician-initiated SICs. We abstracted spending - defined as inflation-adjusted costs for acute care (inpatient plus emergency room), office/outpatient care, intravenous systemic therapy, other therapy (e.g., radiation), long-term care, and hospice - from the institution's accounting system, and we captured spending at inpatient, outpatient, and pharmacy settings. To evaluate intervention impacts on spending, we used a two-part model, first using logistic regression to model zero versus nonzero spending and second using generalized linear mixed models with gamma distribution and log-link function to model daily mean spending in the last 180days of life. Models were adjusted for clinic and wedge fixed effects, and they were clustered at the oncologist level. For all patients with at least one SIC within 6 months of death, we also calculated their mean daily spending before and after SIC.

RESULTS

Median age at death was 68years (interquartile range, 15.5), 317 patients (27%) were Black or of ethnicities other than white, and 448 patients (38%) had an SIC. The intervention was associated with lower unadjusted mean daily spending in the last 6 months of life for the intervention group versus controls ($377.96 vs. $449.92; adjusted mean difference, -$75.33; 95% confidence interval, -$136.42 to -$14.23; P=0.02), translating to $13,747 total adjusted savings per decedent and $13 million in cumulative savings across all decedents in the intervention group. Compared with controls, patients in the intervention group incurred lower mean daily spending for systemic therapy (adjusted difference, -$44.59; P=0.001), office/outpatient care (-$9.62; P=0.001), and other therapy (-$8.65; P=0.04). The intervention was not associated with differences in end-of-life spending for acute care, long-term care, or hospice. Results were consistent for spending in the last 1 and 3 months of life and after adjusting for age, race, and ethnicity. For patients with SICs, mean daily spending decreased by $37.92 following the first SIC ($329.87 vs. $291.95).

CONCLUSIONS

A machine learning-based, behaviorally informed intervention to prompt SICs led to end-of-life savings among patients with cancer, driven by decreased systemic therapy and outpatient spending. (Funded by the Penn Center for Precision Medicine and the National Institutes of Health; ClinicalTrials.gov number, NCT03984773.).

Prospective evaluation of artificial intelligence (AI) applications for use in cancer pathways following diagnosis: a systematic review

The role of artificial intelligence (AI) in cancer care has evolved in the face of ageing population, workforce shortages and technological advancement. Despite recent uptake in AI research and adoption, the extent to which it improves quality, efficiency and equity of care beyond cancer diagnostics is uncertain to date. Henceforth, the objective of our systematic review is to assess the clinical readiness and deployability of AI through evaluation of prospective studies of AI in cancer care following diagnosis. We undertook a systematic review to determine the types of AI involved and their respective outcomes. A PubMed and Web of Science search between 1 January 2013 and 1 May 2023 identified 15 articles detailing prospective evaluation of AI in postdiagnostic cancer pathway. We appraised all studies using Risk of Bias Assessment of Randomised Controlled Trials and Risk of Bias In Non-randomised Studies-of Interventions quality assessment tools, as well as implementational analysis concerning time, cost and resource, to ascertain the quality of clinical evidence and real-world feasibility of AI. The results revealed that the majority of AI oncological research remained experimental without prospective clinical validation or deployment. Most studies failed to establish clinical validity and to translate measured AI efficacy into beneficial clinical outcomes. AI research are limited by lack of research standardisation and health system interoperability. Furthermore, implementational analysis and equity considerations of AI were largely missing. To overcome the triad of low-level clinical evidence, efficacy-outcome gap and incompatible research ecosystem for AI, future work should focus on multicollaborative AI implementation research designed and conducted in accordance with up-to-date research standards and local health systems.

Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review

This scoping review of randomised controlled trials on artificial intelligence (AI) in clinical practice reveals an expanding interest in AI across clinical specialties and locations. The USA and China are leading in the number of trials, with a focus on deep learning systems for medical imaging, particularly in gastroenterology and radiology. A majority of trials (70 [81%] of 86) report positive primary endpoints, primarily related to diagnostic yield or performance; however, the predominance of single-centre trials, little demographic reporting, and varying reports of operational efficiency raise concerns about the generalisability and practicality of these results. Despite the promising outcomes, considering the likelihood of publication bias and the need for more comprehensive research including multicentre trials, diverse outcome measures, and improved reporting standards is crucial. Future AI trials should prioritise patient-relevant outcomes to fully understand AI's true effects and limitations in health care.

Machine Learning-Based Prediction of Hospitalization During Chemoradiotherapy With Daily Step Counts

Importance

Toxic effects of concurrent chemoradiotherapy (CRT) can cause treatment interruptions and hospitalizations, reducing treatment efficacy and increasing health care costs. Physical activity monitoring may enable early identification of patients at high risk for hospitalization who may benefit from proactive intervention.

Objective

To develop and validate machine learning (ML) approaches based on daily step counts collected by wearable devices on prospective trials to predict hospitalizations during CRT.

Design, Setting, and Participants

This study included patients with a variety of cancers enrolled from June 2015 to August 2018 on 3 prospective, single-institution trials of activity monitoring using wearable devices during CRT. Patients were followed up during and 1 month following CRT. Training and validation cohorts were generated temporally, stratifying for cancer diagnosis (70:30). Random forest, neural network, and elastic net-regularized logistic regression (EN) were trained to predict short-term hospitalization risk based on a combination of clinical characteristics and the preceding 2 weeks of activity data. To predict outcomes of activity data, models based only on activity-monitoring features and only on clinical features were trained and evaluated. Data analysis was completed from January 2022 to March 2023.

Main Outcomes and Measures

Model performance was evaluated in terms of the receiver operating characteristic area under curve (ROC AUC) in the stratified temporal validation cohort.

Results

Step counts from 214 patients (median [range] age, 61 [53-68] years; 113 [52.8%] male) were included. EN based on step counts and clinical features had high predictive ability (ROC AUC, 0.83; 95% CI, 0.66-0.92), outperforming random forest (ROC AUC, 0.76; 95% CI, 0.56-0.87; P = .02) and neural network (ROC AUC, 0.80; 95% CI, 0.71-0.88; P = .36). In an ablation study, the EN model based on only step counts demonstrated greater predictive ability than the EN model with step counts and clinical features (ROC AUC, 0.85; 95% CI, 0.70-0.93; P = .09). Both models outperformed the EN model trained on only clinical features (ROC AUC, 0.53; 95% CI, 0.31-0.66; P < .001).

Conclusions and Relevance

This study developed and validated a ML model based on activity-monitoring data collected during prospective clinical trials. Patient-generated health data have the potential to advance predictive ability of ML approaches. The resulting model from this study will be evaluated in an upcoming multi-institutional, cooperative group randomized trial.

Health Care Cost Reductions with Machine Learning-Directed Evaluations during Radiation Therapy - An Economic Analysis of a Randomized Controlled Study

BACKGROUND

Machine learning (ML) may cost-effectively direct health care by identifying patients most likely to benefit from preventative interventions to avoid negative and expensive outcomes. System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT; NCT04277650) was a single-institution, randomized controlled study in which electronic health record-based ML accurately identified patients at high risk for acute care (emergency visit or hospitalization) during radiotherapy (RT) and targeted them for supplemental clinical evaluations. This ML-directed intervention resulted in decreased acute care utilization. Given the limited prospective data showing the ability of ML to direct interventions cost-efficiently, an economic analysis was performed.

METHODS

A post hoc economic analysis was conducted of SHIELD-RT that included RT courses from January 7, 2019, to June 30, 2019. ML-identified high-risk courses (≥10% risk of acute care during RT) were randomized to receive standard of care weekly clinical evaluations with ad hoc supplemental evaluations per clinician discretion versus mandatory twice-weekly evaluations. The primary outcome was difference in mean total medical costs during and 15 days after RT. Acute care costs were obtained via institutional cost accounting. Physician and intervention costs were estimated via Medicare and Medicaid data. Negative binomial regression was used to estimate cost outcomes after adjustment for patient and disease factors.

RESULTS

A total of 311 high-risk RT courses among 305 patients were randomized to the standard (n=157) or the intervention (n=154) group. Unadjusted mean intervention group supplemental visit costs were $155 per course (95% confidence interval, $142 to $168). The intervention group had fewer acute care visits per course (standard, 0.47; intervention, 0.31; P=0.04). Total mean adjusted costs were $3110 per course for the standard group and $1494 for the intervention group (difference in means, $1616 [95% confidence interval, $1450 to $1783]; P=0.03).

CONCLUSIONS

In this economic analysis of a randomized controlled, health care ML study, mandatory supplemental evaluations for ML-identified high-risk patients were associated with both reduced total medical costs and improved clinical outcomes. Further study is needed to determine whether economic results are generalizable. (Funded in part by The Duke Endowment, The Conquer Cancer Foundation, the Duke Department of Radiation Oncology, and the National Cancer Institute of the National Institutes of Health [R01CA277782]; ClinicalTrials.gov number, NCT04277650.).

Characterizing the limitations of using diagnosis codes in the context of machine learning for healthcare

BACKGROUND

Diagnostic codes are commonly used as inputs for clinical prediction models, to create labels for prediction tasks, and to identify cohorts for multicenter network studies. However, the coverage rates of diagnostic codes and their variability across institutions are underexplored. The primary objective was to describe lab- and diagnosis-based labels for 7 selected outcomes at three institutions. Secondary objectives were to describe agreement, sensitivity, and specificity of diagnosis-based labels against lab-based labels.

METHODS

This study included three cohorts: SickKids from The Hospital for Sick Children, and StanfordPeds and StanfordAdults from Stanford Medicine. We included seven clinical outcomes with lab-based definitions: acute kidney injury, hyperkalemia, hypoglycemia, hyponatremia, anemia, neutropenia and thrombocytopenia. For each outcome, we created four lab-based labels (abnormal, mild, moderate and severe) based on test result and one diagnosis-based label. Proportion of admissions with a positive label were presented for each outcome stratified by cohort. Using lab-based labels as the gold standard, agreement using Cohen's Kappa, sensitivity and specificity were calculated for each lab-based severity level.

RESULTS

The number of admissions included were: SickKids (n = 59,298), StanfordPeds (n = 24,639) and StanfordAdults (n = 159,985). The proportion of admissions with a positive diagnosis-based label was significantly higher for StanfordPeds compared to SickKids across all outcomes, with odds ratio (99.9% confidence interval) for abnormal diagnosis-based label ranging from 2.2 (1.7-2.7) for neutropenia to 18.4 (10.1-33.4) for hyperkalemia. Lab-based labels were more similar by institution. When using lab-based labels as the gold standard, Cohen's Kappa and sensitivity were lower at SickKids for all severity levels compared to StanfordPeds.

CONCLUSIONS

Across multiple outcomes, diagnosis codes were consistently different between the two pediatric institutions. This difference was not explained by differences in test results. These results may have implications for machine learning model development and deployment.

Interpretable machine learning model to predict surgical difficulty in laparoscopic resection for rectal cancer

Background

Laparoscopic total mesorectal excision (LaTME) is standard surgical methods for rectal cancer, and LaTME operation is a challenging procedure. This study is intended to use machine learning to develop and validate prediction models for surgical difficulty of LaTME in patients with rectal cancer and compare these models' performance.

Methods

We retrospectively collected the preoperative clinical and MRI pelvimetry parameter of rectal cancer patients who underwent laparoscopic total mesorectal resection from 2017 to 2022. The difficulty of LaTME was defined according to the scoring criteria reported by Escal. Patients were randomly divided into training group (80%) and test group (20%). We selected independent influencing features using the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression method. Adopt synthetic minority oversampling technique (SMOTE) to alleviate the class imbalance problem. Six machine learning model were developed: light gradient boosting machine (LGBM); categorical boosting (CatBoost); extreme gradient boost (XGBoost), logistic regression (LR); random forests (RF); multilayer perceptron (MLP). The area under receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity and F1 score were used to evaluate the performance of the model. The Shapley Additive Explanations (SHAP) analysis provided interpretation for the best machine learning model. Further decision curve analysis (DCA) was used to evaluate the clinical manifestations of the model.

Results

A total of 626 patients were included. LASSO regression analysis shows that tumor height, prognostic nutrition index (PNI), pelvic inlet, pelvic outlet, sacrococcygeal distance, mesorectal fat area and angle 5 (the angle between the apex of the sacral angle and the lower edge of the pubic bone) are the predictor variables of the machine learning model. In addition, the correlation heatmap shows that there is no significant correlation between these seven variables. When predicting the difficulty of LaTME surgery, the XGBoost model performed best among the six machine learning models (AUROC=0.855). Based on the decision curve analysis (DCA) results, the XGBoost model is also superior, and feature importance analysis shows that tumor height is the most important variable among the seven factors.

Conclusions

This study developed an XGBoost model to predict the difficulty of LaTME surgery. This model can help clinicians quickly and accurately predict the difficulty of surgery and adopt individualized surgical methods.

Artificial intelligence across oncology specialties: current applications and emerging tools

Oncology is becoming increasingly personalised through advancements in precision in diagnostics and therapeutics, with more and more data available on both ends to create individualised plans. The depth and breadth of data are outpacing our natural ability to interpret it. Artificial intelligence (AI) provides a solution to ingest and digest this data deluge to improve detection, prediction and skill development. In this review, we provide multidisciplinary perspectives on oncology applications touched by AI-imaging, pathology, patient triage, radiotherapy, genomics-driven therapy and surgery-and integration with existing tools-natural language processing, digital twins and clinical informatics.

Adaptive Cancer Therapy in the Age of Generative Artificial Intelligence

Therapeutic resistance is a major challenge facing the design of effective cancer treatments. Adaptive cancer therapy is in principle the most viable approach to manage cancer's adaptive dynamics through drug combinations with dose timing and modulation. However, there are numerous open issues facing the clinical success of adaptive therapy. Chief among these issues is the feasibility of real-time predictions of treatment response which represent a bedrock requirement of adaptive therapy. Generative artificial intelligence has the potential to learn prediction models of treatment response from clinical, molecular, and radiomics data about patients and their treatments. The article explores this potential through a proposed integration model of Generative Pre-Trained Transformers (GPTs) in a closed loop with adaptive treatments to predict the trajectories of disease progression. The conceptual model and the challenges facing its realization are discussed in the broader context of artificial intelligence integration in oncology.

Artificial intelligence research in radiation oncology: a practical guide for the clinician on concepts and methods

The use of artificial intelligence (AI) holds great promise for radiation oncology, with many applications being reported in the literature, including some of which are already in clinical use. These are mainly in areas where AI provides benefits in efficiency (such as automatic segmentation and treatment planning). Prediction models that directly impact patient decision-making are far less mature in terms of their application in clinical practice. Part of the limited clinical uptake of these models may be explained by the need for broader knowledge, among practising clinicians within the medical community, about the processes of AI development. This lack of understanding could lead to low commitment to AI research, widespread scepticism, and low levels of trust. This attitude towards AI may be further negatively impacted by the perception that deep learning is a "black box" with inherently low transparency. Thus, there is an unmet need to train current and future clinicians in the development and application of AI in medicine. Improving clinicians' AI-related knowledge and skills is necessary to enhance multidisciplinary collaboration between data scientists and physicians, that is, involving a clinician in the loop during AI development. Increased knowledge may also positively affect the acceptance and trust of AI. This paper describes the necessary steps involved in AI research and development, and thus identifies the possibilities, limitations, challenges, and opportunities, as seen from the perspective of a practising radiation oncologist. It offers the clinician with limited knowledge and experience in AI valuable tools to evaluate research papers related to an AI model application.

Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks

OBJECTIVE

Development of electronic health records (EHR)-based machine learning models for pediatric inpatients is challenged by limited training data. Self-supervised learning using adult data may be a promising approach to creating robust pediatric prediction models. The primary objective was to determine whether a self-supervised model trained in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients, for pediatric inpatient clinical prediction tasks.

MATERIALS AND METHODS

This retrospective cohort study used EHR data and included patients with at least one admission to an inpatient unit. One admission per patient was randomly selected. Adult inpatients were 18 years or older while pediatric inpatients were more than 28 days and less than 18 years. Admissions were temporally split into training (January 1, 2008 to December 31, 2019), validation (January 1, 2020 to December 31, 2020), and test (January 1, 2021 to August 1, 2022) sets. Primary comparison was a self-supervised model trained in adult inpatients versus count-based logistic regression models trained in pediatric inpatients. Primary outcome was mean area-under-the-receiver-operating-characteristic-curve (AUROC) for 11 distinct clinical outcomes. Models were evaluated in pediatric inpatients.

RESULTS

When evaluated in pediatric inpatients, mean AUROC of self-supervised model trained in adult inpatients (0.902) was noninferior to count-based logistic regression models trained in pediatric inpatients (0.868) (mean difference = 0.034, 95% CI=0.014-0.057; P < .001 for noninferiority and P = .006 for superiority).

CONCLUSIONS

Self-supervised learning in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients. This finding suggests transferability of self-supervised models trained in adult patients to pediatric patients, without requiring costly model retraining.

Artificial intelligence-based risk stratification, accurate diagnosis and treatment prediction in gynecologic oncology

As data-driven science, artificial intelligence (AI) has paved a promising path toward an evolving health system teeming with thrilling opportunities for precision oncology. Notwithstanding the tremendous success of oncological AI in such fields as lung carcinoma, breast tumor and brain malignancy, less attention has been devoted to investigating the influence of AI on gynecologic oncology. Hereby, this review sheds light on the ever-increasing contribution of state-of-the-art AI techniques to the refined risk stratification and whole-course management of patients with gynecologic tumors, in particular, cervical, ovarian and endometrial cancer, centering on information and features extracted from clinical data (electronic health records), cancer imaging including radiological imaging, colposcopic images, cytological and histopathological digital images, and molecular profiling (genomics, transcriptomics, metabolomics and so forth). However, there are still noteworthy challenges beyond performance validation. Thus, this work further describes the limitations and challenges faced in the real-word implementation of AI models, as well as potential solutions to address these issues.

Development and validation of the SickKids Enterprise-wide Data in Azure Repository (SEDAR)

Objectives

To describe the processes developed by The Hospital for Sick Children (SickKids) to enable utilization of electronic health record (EHR) data by creating sequentially transformed schemas for use across multiple user types.

Methods

We used Microsoft Azure as the cloud service provider and named this effort the SickKids Enterprise-wide Data in Azure Repository (SEDAR). Epic Clarity data from on-premises was copied to a virtual network in Microsoft Azure. Three sequential schemas were developed. The Filtered Schema added a filter to retain only SickKids and valid patients. The Curated Schema created a data structure that was easier to navigate and query. Each table contained a logical unit such as patients, hospital encounters or laboratory tests. Data validation of randomly sampled observations in the Curated Schema was performed. The SK-OMOP Schema was designed to facilitate research and machine learning. Two individuals mapped medical elements to standard Observational Medical Outcomes Partnership (OMOP) concepts.

Results

A copy of Clarity data was transferred to Microsoft Azure and updated each night using log shipping. The Filtered Schema and Curated Schema were implemented as stored procedures and executed each night with incremental updates or full loads. Data validation required up to 16 iterations for each Curated Schema table. OMOP concept mapping achieved at least 80 % coverage for each SK-OMOP table.

Conclusions

We described our experience in creating three sequential schemas to address different EHR data access requirements. Future work should consider replicating this approach at other institutions to determine whether approaches are generalizable.

Integrating Artificial Intelligence and Machine Learning Into Cancer Clinical Trials

The practice of oncology requires analyzing and synthesizing abundant data. From the patient's workup to determine eligibility to the therapies received to the post-treatment surveillance, practitioners must constantly juggle, evaluate, and weigh decision-making based on their best understanding of information at hand. These complex, multifactorial decisions have a tremendous opportunity to benefit from data-driven machine learning (ML) methods to drive opportunities in artificial intelligence (AI). Within the past 5 years, we have seen AI move from simply a promising opportunity to being used in prospective trials. Here, we review recent efforts of AI in clinical trials that have moved the needle towards improved prediction of actionable outcomes, such as predicting acute care visits, short term mortality, and pathologic extranodal extension. We then pause and reflect on how these AI models ask a different question than traditional statistics models that readers may be more familiar with; how then should readers conceptualize and interpret AI models that they are not as familiar with. We end with what we believe are promising future opportunities for AI in oncology, with an eye towards allowing the data to inform us through unsupervised learning and generative models, rather than asking AI to perform specific functions.

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

Multiomics data including imaging radiomics and various types of molecular biomarkers have been increasingly investigated for better diagnosis and therapy in the era of precision oncology. Artificial intelligence (AI) including machine learning (ML) and deep learning (DL) techniques combined with the exponential growth of multiomics data may have great potential to revolutionize cancer subtyping, risk stratification, prognostication, prediction and clinical decision-making. In this article, we first present different categories of multiomics data and their roles in diagnosis and therapy. Second, AI-based data fusion methods and modeling methods as well as different validation schemes are illustrated. Third, the applications and examples of multiomics research in oncology are demonstrated. Finally, the challenges regarding the heterogeneity data set, availability of omics data, and validation of the research are discussed. The transition of multiomics research to real clinics still requires consistent efforts in standardizing omics data collection and analysis, building computational infrastructure for data sharing and storing, developing advanced methods to improve data fusion and interpretability, and ultimately, conducting large-scale prospective clinical trials to fill the gap between study findings and clinical benefits.

Efficacy and Quality-of-Life Following Involved Nodal Radiotherapy for Head and Neck Squamous Cell Carcinoma: The INRT-AIR Phase II Clinical Trial

PURPOSE

Elective neck irradiation (ENI) has long been considered mandatory when treating head and neck squamous cell carcinoma (HNSCC) with definitive radiotherapy, but it is associated with significant dose to normal organs-at-risk (OAR). In this prospective phase II study, we investigated the efficacy and tolerability of eliminating ENI and strictly treating involved and suspicious lymph nodes (LN) with intensity-modulated radiotherapy.

PATIENTS AND METHODS

Patients with newly diagnosed HNSCC of the oropharynx, larynx, and hypopharynx were eligible for enrollment. Each LN was characterized as involved or suspicious based on radiologic criteria and an in-house artificial intelligence (AI)-based classification model. Gross disease received 70 Gray (Gy) in 35 fractions and suspicious LNs were treated with 66.5 Gy, without ENI. The primary endpoint was solitary elective volume recurrence, with secondary endpoints including patterns-of-failure and patient-reported outcomes.

RESULTS

Sixty-seven patients were enrolled, with 18 larynx/hypopharynx and 49 oropharynx cancer. With a median follow-up of 33.4 months, the 2-year risk of solitary elective nodal recurrence was 0%. Gastrostomy tubes were placed in 14 (21%), with median removal after 2.9 months for disease-free patients; no disease-free patient is chronically dependent. Grade I/II dermatitis was seen in 90%/10%. There was no significant decline in composite MD Anderson Dysphagia Index scores after treatment, with means of 89.1 and 92.6 at 12 and 24 months, respectively.

CONCLUSIONS

These results suggest that eliminating ENI is oncologically sound for HNSCC, with highly favorable quality-of-life outcomes. Additional prospective studies are needed to support this promising paradigm before implementation in any nontrial setting.

A Bayesian approach to predictive uncertainty in chemotherapy patients at risk of acute care utilization

BACKGROUND

Machine learning (ML) predictions are becoming increasingly integrated into medical practice. One commonly used method, ℓ1-penalised logistic regression (LASSO), can estimate patient risk for disease outcomes but is limited by only providing point estimates. Instead, Bayesian logistic LASSO regression (BLLR) models provide distributions for risk predictions, giving clinicians a better understanding of predictive uncertainty, but they are not commonly implemented.

METHODS

This study evaluates the predictive performance of different BLLRs compared to standard logistic LASSO regression, using real-world, high-dimensional, structured electronic health record (EHR) data from cancer patients initiating chemotherapy at a comprehensive cancer centre. Multiple BLLR models were compared against a LASSO model using an 80-20 random split using 10-fold cross-validation to predict the risk of acute care utilization (ACU) after starting chemotherapy.

FINDINGS

This study included 8439 patients. The LASSO model predicted ACU with an area under the receiver operating characteristic curve (AUROC) of 0.806 (95% CI: 0.775-0.834). BLLR with a Horseshoe+ prior and a posterior approximated by Metropolis-Hastings sampling showed similar performance: 0.807 (95% CI: 0.780-0.834) and offers the advantage of uncertainty estimation for each prediction. In addition, BLLR could identify predictions too uncertain to be automatically classified. BLLR uncertainties were stratified by different patient subgroups, demonstrating that predictive uncertainties significantly differ across race, cancer type, and stage.

INTERPRETATION

BLLRs are a promising yet underutilised tool that increases explainability by providing risk estimates while offering a similar level of performance to standard LASSO-based models. Additionally, these models can identify patient subgroups with higher uncertainty, which can augment clinical decision-making.

FUNDING

This work was supported in part by the National Library Of Medicine of the National Institutes of Health under Award Number R01LM013362. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Big Data, Machine Learning, and Artificial Intelligence to Advance Cancer Care: Opportunities and Challenges

OBJECTIVES

The rapid advances in artificial intelligence (AI), big data, and machine learning (ML) technologies hold promise for personalized, equitable cancer care and improved health outcomes within the context of cancer and beyond. Furthermore, integrating these technologies into cancer research has been effective in addressing many of the challenges for cancer control and cure. This can be achieved through the insights generated from massive amounts of data, in ways that can help inform decisions, interventions, and precision cancer care. AI, big data, and ML technologies offer, either in isolation or in combination, unconventional pathways that facilitate the better understanding and management of cancer and its impact on the person. The value of AI, big data, and ML technologies has been acknowledged and integrated within the Cancer Moonshot program in the U.S. and the EU Beating Cancer Plan in Europe.

DATA SOURCES

Relevant studies on the topic have formed the basis for this article.

CONCLUSION

In a shifting health care environment where cancer care is becoming more complex and demanding, big data and AI technologies can act as a vehicle to facilitating the care continuum. An increasing body of literature demonstrates their impactful contributions in areas such as treatment and diagnosis. These technologies, however, create additional requirements from health care professionals in terms of capacity and preparedness to integrate them effectively and efficiently in clinical practice. Therefore, there is an increasing need for investment and training in oncology to combat and overcome some of the challenges posed by cancer control.

IMPLICATIONS FOR NURSING PRACTICE

AI, big data, and ML are increasingly integrated in various aspects of health care. As a result, health care professionals, including nurses, will need to adjust in an ever-changing practice environment where these technologies have potential applications in clinical settings to improve risk stratification, early detection, and surveillance management of cancer patients.

Development of artificial blood loss and duration of excision score to evaluate surgical difficulty of total laparoscopic anterior resection in rectal cancer

PURPOSE

Total laparoscopic anterior resection (tLAR) has been gradually applied in the treatment of rectal cancer (RC). This study aims to develop a scoring system to predict the surgical difficulty of tLAR.

METHODS

RC patients treated with tLAR were collected. The blood loss and duration of excision (BLADE) scoring system was built to assess the surgical difficulty by using restricted cubic spline regression. Multivariate logistic regression was used to evaluate the effect of the BLADE score on postoperative complications. The random forest (RF) algorithm was used to establish a preoperative predictive model for the BLADE score.

RESULTS

A total of 1,994 RC patients were randomly selected for the training set and the test set, and 325 RC patients were identified as the external validation set. The BLADE score, which was built based on the thresholds of blood loss (60 ml) and duration of surgical excision (165 min), was the most important risk factor for postoperative complications. The areas under the curve of the predictive RF model were 0.786 in the training set, 0.640 in the test set, and 0.665 in the external validation set.

CONCLUSION

This preoperative predictive model for the BLADE score presents clinical feasibility and reliability in identifying the candidates to receive tLAR and in making surgical plans for RC patients.

Comparison of Oncologist and Model Estimates of Risk for Hospitalization During Systemic Therapy for Advanced Cancer

PURPOSE

A validated risk model with inputs of pretreatment sodium and albumin can identify patients at risk for hospitalization during cancer treatment. We evaluated how the model compares with risk estimates from treating oncologists.

METHODS

We evaluated the 30-day risk of hospitalization or death in patients starting palliative-intent systemic therapy for solid tumor malignancy. For each patient, we prospectively recorded categorical estimates of 30-day hospitalization risk (bottom third, middle third, top third) generated by a treating oncologist and by the two-variable model; a third hybrid risk estimate represented a composite of the oncologist and model risk assessments. We analyzed the agreement of oncologist and model-based risk estimates and compared discrimination, sensitivity, and specificity of each risk assessment method.

RESULTS

We collected oncologist, model, and hybrid estimates of hospitalization risk for 120 patients. The 30-day rate of hospitalization or death was 20%. There was minimal agreement between oncologist and model risk estimates (weighted kappa = 0.27). The c-statistic (a measure of discrimination) was 0.69 (95% CI, 0.57 to 0.81) for the clinician assessment, 0.77 for the model assessment (CI, 0.67 to 0.86; P = .24 compared with the oncologist assessment), and 0.79 for the hybrid assessment (CI, 0.69 to 0.90; P = .007 compared with the oncologist assessment). Sensitivity and specificity of the high-risk categorization did not differ significantly between the oncologist and model assessments; the hybrid assessment was significantly more sensitive (P = .02) and less specific (P = .03) than the oncologist assessment.

CONCLUSION

A model with inputs of pretreatment sodium and albumin improves oncologists' predictions of hospitalization risk during cancer treatment.

Long-term Effect of Machine Learning-Triggered Behavioral Nudges on Serious Illness Conversations and End-of-Life Outcomes Among Patients With Cancer: A Randomized Clinical Trial

Importance

Serious illness conversations (SICs) between oncology clinicians and patients are associated with improved quality of life and may reduce aggressive end-of-life care. However, most patients with cancer die without a documented SIC.

Objective

To test the impact of behavioral nudges to clinicians to prompt SICs on the SIC rate and end-of-life outcomes among patients at high risk of death within 180 days (high-risk patients) as identified by a machine learning algorithm.

Design, Setting, and Participants

This prespecified 40-week analysis of a stepped-wedge randomized clinical trial conducted between June 17, 2019, and April 20, 2020 (including 16 weeks of intervention rollout and 24 weeks of follow-up), included 20 506 patients with cancer representing 41 021 encounters at 9 tertiary or community-based medical oncology clinics in a large academic health system. The current analyses were conducted from June 1, 2021, to May 31, 2022.

Intervention

High-risk patients were identified using a validated electronic health record machine learning algorithm to predict 6-month mortality. The intervention consisted of (1) weekly emails to clinicians comparing their SIC rates for all patients against peers' rates, (2) weekly lists of high-risk patients, and (3) opt-out text messages to prompt SICs before encounters with high-risk patients.

Main Outcomes and Measures

The primary outcome was SIC rates for all and high-risk patient encounters; secondary end-of-life outcomes among decedents included inpatient death, hospice enrollment and length of stay, and intensive care unit admission and systemic therapy close to death. Intention-to-treat analyses were adjusted for clinic and wedge fixed effects and clustered at the oncologist level.

Results

The study included 20 506 patients (mean [SD] age, 60.0 [14.0] years) and 41 021 patient encounters: 22 259 (54%) encounters with female patients, 28 907 (70.5%) with non-Hispanic White patients, and 5520 (13.5%) with high-risk patients; 1417 patients (6.9%) died by the end of follow-up. There were no meaningful differences in demographic characteristics in the control and intervention periods. Among high-risk patient encounters, the unadjusted SIC rates were 3.4% (59 of 1754 encounters) in the control period and 13.5% (510 of 3765 encounters) in the intervention period. In adjusted analyses, the intervention was associated with increased SICs for all patients (adjusted odds ratio, 2.09 [95% CI, 1.53-2.87]; P < .001) and decreased end-of-life systemic therapy (7.5% [72 of 957 patients] vs 10.4% [24 of 231 patients]; adjusted odds ratio, 0.25 [95% CI, 0.11-0.57]; P = .001) relative to controls, but there was no effect on hospice enrollment or length of stay, inpatient death, or end-of-life ICU use.

Conclusions and Relevance

In this randomized clinical trial, a machine learning-based behavioral intervention and behavioral nudges to clinicans led to an increase in SICs and reduction in end-of-life systemic therapy but no changes in other end-of-life outcomes among outpatients with cancer. These results suggest that machine learning and behavioral nudges can lead to long-lasting improvements in cancer care delivery.

Trial Registration

ClinicalTrials.gov Identifier: NCT03984773.

Association Between Remote Monitoring and Acute Care Visits in High-Risk Patients Initiating Intravenous Antineoplastic Therapy

PURPOSE

Traditional oncology care models have not effectively identified and managed at-risk patients to prevent acute care. A next step is to harness advances in technology to enable patients to report symptoms any time, enabling digital hovering-intensive symptom monitoring and management. Our objective was to evaluate a digital platform that identifies and remotely monitors high-risk patients initiating antineoplastic therapy with the goal of preventing acute care visits.

METHODS

This was a single-institution matched cohort quality improvement study conducted at a National Cancer Institute-designated cancer center between January 1, 2019, and March 31, 2020. Eligible patients were those initiating intravenous antineoplastic therapy who were identified as high risk for seeking acute care. Enrolled patients' symptoms were monitored using a digital platform. A dedicated team of clinicians managed reported symptoms. The primary outcomes of emergency department visits and hospitalizations within 6 months of treatment initiation were analyzed using cumulative incidence analyses with a competing risk of death.

RESULTS

Eighty-one patients from the intervention arm were matched by stage and disease with contemporaneous high-risk control patients. The matched cohort had similar baseline characteristics. The cumulative incidence of an emergency department visit for the intervention cohort was 0.27 (95% CI, 0.17 to 0.37) at six months compared with 0.47 (95% CI, 0.36 to 0.58) in the control (P = .01) and of an inpatient admission was 0.23 (95% CI, 0.14 to 0.33) in the intervention cohort versus 0.41 (95% CI, 0.30 to 0.51) in the control (P = .02).

CONCLUSION

The narrow employment of technology solutions to complex care delivery challenges in oncology can improve outcomes and innovate care. This program was a first step in using a digital platform and a remote team to improve symptom care for high-risk patients.

Digital Health Applications in Oncology: An Opportunity to Seize

Digital health advances have transformed many clinical areas including psychiatric and cardiovascular care. However, digital health innovation is relatively nascent in cancer care, which represents the fastest growing area of health-care spending. Opportunities for digital health innovation in oncology include patient-facing technologies that improve patient experience, safety, and patient-clinician interactions; clinician-facing technologies that improve their ability to diagnose pathology and predict adverse events; and quality of care and research infrastructure to improve clinical workflows, documentation, decision support, and clinical trial monitoring. The COVID-19 pandemic and associated shifts of care to the home and community dramatically accelerated the integration of digital health technologies into virtually every aspect of oncology care. However, the pandemic has also exposed potential flaws in the digital health ecosystem, namely in clinical integration strategies; data access, quality, and security; and regulatory oversight and reimbursement for digital health technologies. Stemming from the proceedings of a 2020 workshop convened by the National Cancer Policy Forum of the National Academies of Sciences, Engineering, and Medicine, this article summarizes the current state of digital health technologies in medical practice and strategies to improve clinical utility and integration. These recommendations, with calls to action for clinicians, health systems, technology innovators, and policy makers, will facilitate efficient yet safe integration of digital health technologies into cancer care.

Implementation of machine learning in the clinic: challenges and lessons in prospective deployment from the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) randomized controlled study

Background

Artificial intelligence (AI) and machine learning (ML) have resulted in significant enthusiasm for their promise in healthcare. Despite this, prospective randomized controlled trials and successful clinical implementation remain limited. One clinical application of ML is mitigation of the increased risk for acute care during outpatient cancer therapy. We previously reported the results of the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) study (NCT04277650), which was a prospective, randomized quality improvement study demonstrating that ML based on electronic health record (EHR) data can direct supplemental clinical evaluations and reduce the rate of acute care during cancer radiotherapy with and without chemotherapy. The objective of this study is to report the workflow and operational challenges encountered during ML implementation on the SHIELD-RT study.

Results

Data extraction and manual review steps in the workflow represented significant time commitments for implementation of clinical ML on a prospective, randomized study. Barriers include limited data availability through the standard clinical workflow and commercial products, the need to aggregate data from multiple sources, and logistical challenges from altering the standard clinical workflow to deliver adaptive care.

Conclusions

The SHIELD-RT study was an early randomized controlled study which enabled assessment of barriers to clinical ML implementation, specifically those which leverage the EHR. These challenges build on a growing body of literature and may provide lessons for future healthcare ML adoption.

Trial registration: NCT04277650. Registered 20 February 2020. Retrospectively registered quality improvement study.

Development and Validation of a Machine Learning Algorithm Predicting Emergency Department Use and Unplanned Hospitalization in Patients With Head and Neck Cancer

Importance

Patient-reported symptom burden was recently found to be associated with emergency department use and unplanned hospitalization (ED/Hosp) in patients with head and neck cancer. It was hypothesized that symptom scores could be combined with administrative health data to accurately risk stratify patients.

Objective

To develop and validate a machine learning approach to predict future ED/Hosp in patients with head and neck cancer.

Design, Setting, and Participants

This was a population-based predictive modeling study of patients in Ontario, Canada, diagnosed with head and neck cancer from January 2007 through March 2018. All outpatient clinical encounters were identified. Edmonton Symptom Assessment System (ESAS) scores and clinical and demographic factors were abstracted. Training and test cohorts were randomly generated in a 4:1 ratio. Various machine learning algorithms were explored, including (1) logistic regression using a least absolute shrinkage and selection operator, (2) random forest, (3) gradient boosting machine, (4) k-nearest neighbors, and (5) an artificial neural network. Data analysis was performed from September 2021 to January 2022.

Main Outcomes and Measures

The main outcome was any 14-day ED/Hosp event following symptom assessment. The performance of each model was assessed on the test cohort using the area under the receiver operator characteristic (AUROC) curve and calibration plots. Shapley values were used to identify the variables with greatest contribution to the model.

Results

The training cohort consisted of 9409 patients (mean [SD] age, 63.3 [10.9] years) undergoing 59 089 symptom assessments (80%). The remaining 2352 patients (mean [SD] age, 63.3 [11] years) and 14 193 symptom assessments were set aside as the test cohort (20%). Several models had high predictive accuracy, particularly the gradient boosting machine (validation AUROC, 0.80 [95% CI, 0.78-0.81]). A Youden-based cutoff corresponded to a validation sensitivity of 0.77 and specificity of 0.66. Patient-reported symptom scores were consistently identified as being the most predictive features within models. A second model built only with symptom severity data had an AUROC of 0.72 (95% CI, 0.70-0.74).

Conclusions and Relevance

In this study, machine learning approaches predicted with a high degree of accuracy ED/Hosp in patients with head and neck cancer. These tools could be used to accurately risk stratify patients and may help direct targeted intervention.

Machine learning in neuro-oncology: toward novel development fields

PURPOSE

Artificial Intelligence (AI) involves several and different techniques able to elaborate a large amount of data responding to a specific planned outcome. There are several possible applications of this technology in neuro-oncology.

METHODS

We reviewed, according to PRISMA guidelines, available studies adopting AI in different fields of neuro-oncology including neuro-radiology, pathology, surgery, radiation therapy, and systemic treatments.

RESULTS

Neuro-radiology presented the major number of studies assessing AI. However, this technology is being successfully tested also in other operative settings including surgery and radiation therapy. In this context, AI shows to significantly reduce resources and costs maintaining an elevated qualitative standard. Pathological diagnosis and development of novel systemic treatments are other two fields in which AI showed promising preliminary data.

CONCLUSION

It is likely that AI will be quickly included in some aspects of daily clinical practice. Possible applications of these techniques are impressive and cover all aspects of neuro-oncology.

Improving Adjuvant Liver-Directed Treatment Recommendations for Unresectable Hepatocellular Carcinoma: An Artificial Intelligence-Based Decision-Making Tool

PURPOSE

Liver-directed therapy after transarterial chemoembolization (TACE) can lead to improvement in survival for selected patients with unresectable hepatocellular carcinoma (HCC). However, there is uncertainty in the appropriate application and modality of therapy in current clinical practice guidelines. The aim of this study was to develop a proof-of-concept, machine learning (ML) model for treatment recommendation in patients previously treated with TACE and select patients who might benefit from additional treatment with combination stereotactic body radiotherapy (SBRT) or radiofrequency ablation (RFA).

METHODS

This retrospective observational study was based on data from an urban, academic hospital system selecting for patients diagnosed with stage I-III HCC from January 1, 2008, to December 31, 2018, treated with TACE, followed by adjuvant RFA, SBRT, or no additional liver-directed modality. A feedforward, ML ensemble model provided a treatment recommendation on the basis of pairwise assessments evaluating each potential treatment option and estimated benefit in survival.

RESULTS

Two hundred thirty-seven patients met inclusion criteria, of whom 54 (23%) and 49 (21%) received combination of TACE and SBRT or TACE and RFA, respectively. The ML model suggested a different consolidative modality in 32.7% of cases among patients who had previously received combination treatment. Patients treated in concordance with model recommendations had significant improvement in progression-free survival (hazard ratio 0.5; P = .007). The most important features for model prediction were cause of cirrhosis, stage of disease, and albumin-bilirubin grade (a measure of liver function).

CONCLUSION

In this proof-of-concept study, an ensemble ML model was able to provide treatment recommendations for HCC who had undergone prior TACE. Additional treatment in line with model recommendations was associated with significant improvement in progression-free survival, suggesting a potential benefit for ML-guided medical decision making.

Evaluating High-Dimensional Machine Learning Models to Predict Hospital Mortality Among Older Patients With Cancer

PURPOSE

Older hospitalized cancer patients face high risks of hospital mortality. Improved risk stratification could help identify high-risk patients who may benefit from future interventions, although we lack validated tools to predict in-hospital mortality for patients with cancer. We evaluated the ability of a high-dimensional machine learning prediction model to predict inpatient mortality and compared the performance of this model to existing prediction indices.

METHODS

We identified patients with cancer older than 75 years from the National Emergency Department Sample between 2016 and 2018. We constructed a high-dimensional predictive model called Cancer Frailty Assessment Tool (cFAST), which used an extreme gradient boosting algorithm to predict in-hospital mortality. cFAST model inputs included patient demographic, hospital variables, and diagnosis codes. Model performance was assessed with an area under the curve (AUC) from receiver operating characteristic curves, with an AUC of 1.0 indicating perfect prediction. We compared model performance to existing indices including the Modified 5-Item Frailty Index, Charlson comorbidity index, and Hospital Frailty Risk Score.

RESULTS

We identified 2,723,330 weighted emergency department visits among older patients with cancer, of whom 144,653 (5.3%) died in the hospital. Our cFAST model included 240 features and demonstrated an AUC of 0.92. Comparator models including the Modified 5-Item Frailty Index, Charlson comorbidity index, and Hospital Frailty Risk Score achieved AUCs of 0.58, 0.62, and 0.71, respectively. Predictive features of the cFAST model included acute conditions (respiratory failure and shock), chronic conditions (lipidemia and hypertension), patient demographics (age and sex), and cancer and treatment characteristics (metastasis and palliative care).

CONCLUSION

High-dimensional machine learning models enabled accurate prediction of in-hospital mortality among older patients with cancer, outperforming existing prediction indices. These models show promise in identifying patients at risk of severe adverse outcomes, although additional validation and research studying clinical implementation of these tools is needed.

Disadvantaged Subgroups Within the Global Head and Neck Cancer Population: How Can We Optimize Care?

Within the global head and neck cancer population, there are subgroups of patients with poorer cancer outcomes independent from tumor characteristics. In this article, we review three such groups. The first group comprises patients with nasopharyngeal cancer in low- and middle-income countries where access to high-volume, well-resourced radiotherapy centers is limited. We discuss a recent study that is aiming to improve outcomes through the instigation of a comprehensive radiotherapy quality assurance program. The second group comprises patients with low socioeconomic status in a high-income country who experience substantial financial toxicity, defined as financial hardship for patients due to health care costs. We review causes and consequences of financial toxicity and discuss how it can be mitigated. The third group comprises older patients who may poorly tolerate and not benefit from intensive standard-of-care treatment. We discuss the role of geriatric assessment, particularly in relation to the use of chemotherapy. Through better recognition and understanding of disadvantaged groups within the global head and neck cancer population, we will be better placed to instigate the necessary changes to improve outcomes and quality of life for patients with head and neck cancer.

Opportunities to use electronic health record audit logs to improve cancer care

The rapid adoption of electronic health records (EHRs) has created extensive repositories of digitized data that can be used to inform improvements in care delivery, processes, and patient outcomes. While the clinical data captured in EHRs are widely used for such efforts, EHRs also capture audit log data that reflect how users interact with the EHR to deliver care. Automatically collected audit log data provide a unique opportunity for new insights into EHR user behavior and decision‐making processes. Here, we provide an overview of audit log data and examples that could be used to improve oncology care and outcomes in four domains: diagnostic reasoning and consumption, care team collaboration and communication, patient outcomes and experience, and provider burnout/fatigue. This data source could identify gaps in performance and care, physician uptake of EHR features that enhance decision‐making, and integration of data trends for oncology. Ensuring researchers and oncologists are familiar with the data's potential and developing the data engineering capacity to utilize this rich data source, will expand the breadth of research to improve cancer care.

Sources of bias in artificial intelligence that perpetuate healthcare disparities-A global review

BACKGROUND

While artificial intelligence (AI) offers possibilities of advanced clinical prediction and decision-making in healthcare, models trained on relatively homogeneous datasets, and populations poorly-representative of underlying diversity, limits generalisability and risks biased AI-based decisions. Here, we describe the landscape of AI in clinical medicine to delineate population and data-source disparities.

METHODS

We performed a scoping review of clinical papers published in PubMed in 2019 using AI techniques. We assessed differences in dataset country source, clinical specialty, and author nationality, sex, and expertise. A manually tagged subsample of PubMed articles was used to train a model, leveraging transfer-learning techniques (building upon an existing BioBERT model) to predict eligibility for inclusion (original, human, clinical AI literature). Of all eligible articles, database country source and clinical specialty were manually labelled. A BioBERT-based model predicted first/last author expertise. Author nationality was determined using corresponding affiliated institution information using Entrez Direct. And first/last author sex was evaluated using the Gendarize.io API.

RESULTS

Our search yielded 30,576 articles, of which 7,314 (23.9%) were eligible for further analysis. Most databases came from the US (40.8%) and China (13.7%). Radiology was the most represented clinical specialty (40.4%), followed by pathology (9.1%). Authors were primarily from either China (24.0%) or the US (18.4%). First and last authors were predominately data experts (i.e., statisticians) (59.6% and 53.9% respectively) rather than clinicians. And the majority of first/last authors were male (74.1%).

INTERPRETATION

U.S. and Chinese datasets and authors were disproportionately overrepresented in clinical AI, and almost all of the top 10 databases and author nationalities were from high income countries (HICs). AI techniques were most commonly employed for image-rich specialties, and authors were predominantly male, with non-clinical backgrounds. Development of technological infrastructure in data-poor regions, and diligence in external validation and model re-calibration prior to clinical implementation in the short-term, are crucial in ensuring clinical AI is meaningful for broader populations, and to avoid perpetuating global health inequity.

Building a Precision Medicine Delivery Platform for Clinics: The University of California, San Francisco, BRIDGE Experience

Despite an ever-expanding number of analytics with the potential to impact clinical care, the field currently lacks point-of-care technological tools that allow clinicians to efficiently select disease-relevant data about their patients, algorithmically derive clinical indices (eg, risk scores), and view these data in straightforward graphical formats to inform real-time clinical decisions. Thus far, solutions to this problem have relied on either bottom-up approaches that are limited to a single clinic or generic top-down approaches that do not address clinical users’ specific setting-relevant or disease-relevant needs. As a road map for developing similar platforms, we describe our experience with building a custom but institution-wide platform that enables economies of time, cost, and expertise. The BRIDGE platform was designed to be modular and scalable and was customized to data types relevant to given clinical contexts within a major university medical center. The development process occurred by using a series of human-centered design phases with extensive, consistent stakeholder input. This institution-wide approach yielded a unified, carefully regulated, cross-specialty clinical research platform that can be launched during a patient’s electronic health record encounter. The platform pulls clinical data from the electronic health record (Epic; Epic Systems) as well as other clinical and research sources in real time; analyzes the combined data to derive clinical indices; and displays them in simple, clinician-designed visual formats specific to each disorder and clinic. By integrating an application into the clinical workflow and allowing clinicians to access data sources that would otherwise be cumbersome to assemble, view, and manipulate, institution-wide platforms represent an alternative approach to achieving the vision of true personalized medicine.

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature

BACKGROUND

The term "data science" encompasses several methods, many of which are considered cutting edge and are being used to influence care processes across the world. Nursing is an applied science and a key discipline in health care systems in both clinical and administrative areas, making the profession increasingly influenced by the latest advances in data science. The greater informatics community should be aware of current trends regarding the intersection of nursing and data science, as developments in nursing practice have cross-professional implications.

OBJECTIVES

This study aimed to summarize the latest (calendar year 2020) research and applications of nursing-relevant patient outcomes and clinical processes in the data science literature.

METHODS

We conducted a rapid review of the literature to identify relevant research published during the year 2020. We explored the following 16 topics: (1) artificial intelligence/machine learning credibility and acceptance, (2) burnout, (3) complex care (outpatient), (4) emergency department visits, (5) falls, (6) health care-acquired infections, (7) health care utilization and costs, (8) hospitalization, (9) in-hospital mortality, (10) length of stay, (11) pain, (12) patient safety, (13) pressure injuries, (14) readmissions, (15) staffing, and (16) unit culture.

RESULTS

Of 16,589 articles, 244 were included in the review. All topics were represented by literature published in 2020, ranging from 1 article to 59 articles. Numerous contemporary data science methods were represented in the literature including the use of machine learning, neural networks, and natural language processing.

CONCLUSION

This review provides an overview of the data science trends that were relevant to nursing practice in 2020. Examinations of such literature are important to monitor the status of data science's influence in nursing practice.

An artificial intelligence framework integrating longitudinal electronic health records with real-world data enables continuous pan-cancer prognostication

Despite widespread adoption of electronic health records (EHRs), most hospitals are not ready to implement data science research in the clinical pipelines. Here, we develop MEDomics, a continuously learning infrastructure through which multimodal health data are systematically organized and data quality is assessed with the goal of applying artificial intelligence for individual prognosis. Using this framework, currently composed of thousands of individuals with cancer and millions of data points over a decade of data recording, we demonstrate prognostic utility of this framework in oncology. As proof of concept, we report an analysis using this infrastructure, which identified the Framingham risk score to be robustly associated with mortality among individuals with early-stage and advanced-stage cancer, a potentially actionable finding from a real-world cohort of individuals with cancer. Finally, we show how natural language processing (NLP) of medical notes could be used to continuously update estimates of prognosis as a given individual's disease course unfolds.

Prior Frequent Emergency Department Use as a Predictor of Emergency Department Visits After a New Cancer Diagnosis

PURPOSE

To determine whether emergency department (ED) visit history prior to cancer diagnosis is associated with ED visit volume after cancer diagnosis.

METHODS

This was a retrospective cohort study of adults (≥ 18 years) with an incident cancer diagnosis (excluding nonmelanoma skin cancers or leukemia) at an academic medical center between 2008 and 2018 and a safety-net hospital between 2012 and 2016. Our primary outcome was the number of ED visits in the first 6 months after cancer diagnosis, modeled using a multivariable negative binomial regression accounting for ED visit history in the 6-12 months preceding cancer diagnosis, electronic health record proxy social determinants of health, and clinical cancer-related characteristics.

RESULTS

Among 35,090 patients with cancer (49% female and 50% non-White), 57% had ≥ 1 ED visit in the 6 months immediately following cancer diagnosis and 20% had ≥ 1 ED visit in the 6-12 months prior to cancer diagnosis. The strongest predictor of postdiagnosis ED visits was frequent (≥ 4) prediagnosis ED visits (adjusted incidence rate ratio [aIRR]: 3.68; 95% CI, 3.36 to 4.02). Other covariates associated with greater postdiagnosis ED use included having 1-3 prediagnosis ED visits (aIRR: 1.32; 95% CI, 1.28 to 1.36), Hispanic (aIRR: 1.12; 95% CI, 1.07 to 1.17) and Black (aIRR: 1.21; 95% CI, 1.17 to 1.25) race, homelessness (aIRR: 1.95; 95% CI, 1.73 to 2.20), advanced-stage cancer (aIRR: 1.30; 95% CI, 1.26 to 1.35), and treatment regimens including chemotherapy (aIRR: 1.44; 95% CI, 1.40 to 1.48).

CONCLUSION

The strongest independent predictor for ED use after a new cancer diagnosis was frequent ED visits before cancer diagnosis. Efforts to reduce potentially avoidable ED visits among patients with cancer should consider educational initiatives that target heavy prior ED users and offer them alternative ways to seek urgent medical care.

Machine Learning Applied to Electronic Health Records: Identification of Chemotherapy Patients at High Risk for Preventable Emergency Department Visits and Hospital Admissions

PURPOSE

Acute care use (ACU) is a major driver of oncologic costs and is penalized by a Centers for Medicare & Medicaid Services quality measure, OP-35. Targeted interventions reduce preventable ACU; however, identifying which patients might benefit remains challenging. Prior predictive models have made use of a limited subset of the data in the electronic health record (EHR). We aimed to predict risk of preventable ACU after starting chemotherapy using machine learning (ML) algorithms trained on comprehensive EHR data.

METHODS

Chemotherapy patients treated at an academic institution and affiliated community care sites between January 2013 and July 2019 who met inclusion criteria for OP-35 were identified. Preventable ACU was defined using OP-35 criteria. Structured EHR data generated before chemotherapy treatment were obtained. ML models were trained to predict risk for ACU after starting chemotherapy using 80% of the cohort. The remaining 20% were used to test model performance by the area under the receiver operator curve.

RESULTS

Eight thousand four hundred thirty-nine patients were included, of whom 35% had preventable ACU within 180 days of starting chemotherapy. Our primary model classified patients at risk for preventable ACU with an area under the receiver operator curve of 0.783 (95% CI, 0.761 to 0.806). Performance was better for identifying admissions than emergency department visits. Key variables included prior hospitalizations, cancer stage, race, laboratory values, and a diagnosis of depression. Analyses showed limited benefit from including patient-reported outcome data and indicated inequities in outcomes and risk modeling for Black and Medicaid patients.

CONCLUSION

Dense EHR data can identify patients at risk for ACU using ML with promising accuracy. These models have potential to improve cancer care outcomes, patient experience, and costs by allowing for targeted, preventative interventions.