Editorial: Artificial Intelligence (AI), Digital Image Analysis, and the Future of Cancer Diagnosis and Prognosis.

On October 8 2024, the Royal Swedish Academy of Sciences announced the 2024 Nobel Prize in Physics was awarded to Hopfield and Hinton for their foundation research on machine learning with artificial neural networks, which resulted in the current applications for artificial intelligence (AI). Digital diagnostic histopathology combines image capture with image analysis and uses digital tools to collect, analyze, and share diagnostic information. An increase in chronic diseases, diagnostic departmental workloads, and diagnostic tests to support targeted therapy in cancer patients have driven the use and development of image analysis systems, and several medical device companies have recently developed whole-slide scanning devices. In April 2017, the US Food and Drug Administration (FDA) permitted marketing authorization for the first whole slide imaging (WSI) system. During 2024, large-scale studies from several cancer centers have shown the potential for diagnostic reporting for real-world data and whole-slide modeling to develop validated diagnostic AI algorithms. This editorial discusses why recent advances and applications in AI and digital image analysis may have an important future role in cancer diagnosis and prognosis.

Efficacy of ColonFlag as a Complete Blood Count-Based Machine Learning Algorithm for Early Detection of Colorectal Cancer: A Systematic Review.

Background: Colorectal cancer (CRC) screening is essential to reduce incidence and mortality rates. However, participation in screening remains suboptimal. ColonFlag, a machine learning algorithm using complete blood count (CBC), identifies individuals at high CRC risk using routinely performed tests. This study aims to review the existing literature assessing the efficacy of ColonFlag across diverse populations in multiple countries. Methods: The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) were followed in reporting this systematic review. Searches were conducted on PubMed, Cochrane, ScienceDirect, and Google Scholar for English articles, using keywords related to CBC, machine learning, ColonFlag, and CRC, covering the first development study from 2016 to August 2023. The Cochrane Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias. Results: A total of 949 articles were identified during the literature search. Ten studies were found to be eligible. ColonFlag yielded Area Under the Curve (AUC) values ranging from 0.736 to 0.82. The sensitivity and specificity ranged from 3.91% to 35.4% and 82.73% to 94%, respectively. The positive predictive values ranged between 2.6% and 9.1%, while the negative predictive values ranged from 97.6% to 99.9%. ColonFlag performed better in shorter time windows, tumors located more proximally, in advanced stages, and in cases of CRC compared to adenoma. Conclusion: While ColonFlag exhibits low sensitivity compared to established screening methods such as the fecal immunochemical test (FIT) or colonoscopy, its potential to detect CRC before clinical diagnosis suggests an opportunity for identifying more cases than regular screening alone.

The future of machine learning for small-molecule drug discovery will be driven by data.

Many studies have prophesied that the integration of machine learning techniques into small-molecule therapeutics development will help to deliver a true leap forward in drug discovery. However, increasingly advanced algorithms and novel architectures have not always yielded substantial improvements in results. In this Perspective, we propose that a greater focus on the data for training and benchmarking these models is more likely to drive future improvement, and explore avenues for future research and strategies to address these data challenges.

Interpretable subgroup learning-based modeling framework: Study of diabetic kidney disease prediction.

OBJECTIVES: Complex diseases, like diabetic kidney disease (DKD), often exhibit heterogeneity, challenging accurate risk prediction with machine learning. Traditional global models ignore patient differences, and subgroup learning lacks interpretability and predictive efficiency. This study introduces the Interpretable Subgroup Learning-based Modeling (iSLIM) framework to address these issues. METHODS: iSLIM integrates expert knowledge with a tree-based recursive partitioning approach to identify DKD subgroups within an EHR dataset of 11,559 patients. It then constructs separate models for each subgroup, enhancing predictive accuracy while preserving interpretability. RESULTS: Five clinically relevant subgroups are identified, achieving an average sensitivity of 0.8074, outperforming a single global model by 0.1104. Post hoc analyses provide pathological and biological evidence supporting subgroup validity and potential DKD risk factors. CONCLUSION: The iSLIM surpasses traditional global model in predictive performance and subgroup-specific risk factor interpretation, enhancing the understanding of DKD's heterogeneous mechanisms and potentially increasing the adoption of machine learning models in clinical decision-making.

Studies of Artificial Intelligence/Machine Learning Registered on ClinicalTrials.gov: Cross-Sectional Study With Temporal Trends, 2010-2023.

BACKGROUND: The rapid growth of research in artificial intelligence (AI) and machine learning (ML) continues. However, it is unclear whether this growth reflects an increase in desirable study attributes or merely perpetuates the same issues previously raised in the literature. OBJECTIVE: This study aims to evaluate temporal trends in AI/ML studies over time and identify variations that are not apparent from aggregated totals at a single point in time. METHODS: We identified AI/ML studies registered on ClinicalTrials.gov with start dates between January 1, 2010, and December 31, 2023. Studies were included if AI/ML-specific terms appeared in the official title, detailed description, brief summary, intervention, primary outcome, or sponsors' keywords. Studies registered as systematic reviews and meta-analyses were excluded. We reported trends in AI/ML studies over time, along with study characteristics that were fast-growing and those that remained unchanged during 2010-2023. RESULTS: Of 3106 AI/ML studies, only 7.6% (n=235) were regulated by the US Food and Drug Administration. The most common study characteristics were randomized (56.2%; 670/1193; interventional) and prospective (58.9%; 1126/1913; observational) designs; a focus on diagnosis (28.2%; 335/1190) and treatment (24.4%; 290/1190); hospital/clinic (44.2%; 1373/3106) or academic (28%; 869/3106) sponsorship; and neoplasm (12.9%; 420/3245), nervous system (12.2%; 395/3245), cardiovascular (11.1%; 356/3245) or pathological conditions (10%; 325/3245; multiple counts per study possible). Enrollment data were skewed to the right: maximum 13,977,257; mean 16,962 (SD 288,155); median 255 (IQR 80-1000). The most common size category was 101-1000 (44.8%; 1372/3061; excluding withdrawn or missing), but large studies (n>1000) represented 24.1% (738/3061) of all studies: 29% (551/1898) of observational studies and 16.1% (187/1163) of trials. Study locations were predominantly in high-income countries (75.3%; 2340/3106), followed by upper-middle-income (21.7%; 675/3106), lower-middle-income (2.8%; 88/3106), and low-income countries (0.1%; 3/3106). The fastest-growing characteristics over time were high-income countries (location); Europe, Asia, and North America (location); diagnosis and treatment (primary purpose); hospital/clinic and academia (lead sponsor); randomized and prospective designs; and the 1-100 and 101-1000 size categories. Only 5.6% (47/842) of completed studies had results available on ClinicalTrials.gov, and this pattern persisted. Over time, there was an increase in not only the number of newly initiated studies, but also the number of completed studies without posted results. CONCLUSIONS: Much of the rapid growth in AI/ML studies comes from high-income countries in high-resource settings, albeit with a modest increase in upper-middle-income countries (mostly China). Lower-middle-income or low-income countries remain poorly represented. The increase in randomized or prospective designs, along with 738 large studies (n>1000), mostly ongoing, may indicate that enough studies are shifting from an in silico evaluation stage toward a prospective comparative evaluation stage. However, the ongoing limited availability of basic results on ClinicalTrials.gov contrasts with this field's rapid advancements and the public registry's role in reducing publication and outcome reporting biases.

Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study.

BACKGROUND: New-onset atrial fibrillation (NOAF) is the most common arrhythmia in critically ill patients admitted to intensive care and is associated with poor prognosis and disease burden. Identifying high-risk individuals early is crucial. This study aims to create and validate a NOAF prediction model for critically ill patients using machine learning (ML). METHODS: The data came from two non-overlapping datasets from the Medical Information Mart for Intensive Care (MIMIC), with MIMIC-IV used for training and subset of MIMIC-III used as external validation. LASSO regression was used for feature selection. Eight ML algorithms were employed to construct the prediction model. Model performance was evaluated based on identification, calibration, and clinical application. The SHapley Additive exPlanations (SHAP) method was used for visualizing model characteristics and individual case predictions. RESULTS: Among 16,528 MIMIC-IV patients, 1520 (9.2%) developed AF post-ICU admission. A model with 23 variables was built, with XGBoost performing best, achieving an AUC of 0.891 (0.873-0.888) in validation and 0.769 (0.756-0.782) in external validation. Key predictors included age, mechanical ventilation, urine output, sepsis, blood urea nitrogen, percutaneous arterial oxygen saturation, continuous renal replacement therapy and weight. A risk probability greater than 0.6 was defined as high risk. A friendly user interface had been developed for clinician use. CONCLUSION: We developed a ML model to predict the risk of NOAF in critically ill patients without cardiac surgery and validated its potential as a clinically reliable tool. SHAP improves the interpretability of the model, enables clinicians to better understand the causes of NOAF, helps clinicians to prevent it in advance and improves patient outcomes.

The challenges of using machine learning models in psychiatric research and clinical practice.

To understand the complex nature of heterogeneous psychiatric disorders, scientists and clinicians are required to employ a wide range of clinical, endophenotypic, neuroimaging, genomic, and environmental data to understand the biological mechanisms of psychiatric illness before this knowledge is applied into clinical setting. Machine learning (ML) is an automated process that can detect patterns from large multidimensional datasets and can supersede conventional statistical methods as it can detect both linear and non-linear relationships. Due to this advantage, ML has potential to enhance our understanding, improve diagnosis, prognosis and treatment of psychiatric disorders. The current review provides an in-depth examination of, and offers practical guidance for, the challenges encountered in the application of ML models in psychiatric research and clinical practice. These challenges include the curse of dimensionality, data quality, the 'black box' problem, hyperparameter tuning, external validation, class imbalance, and data representativeness. These challenges are particularly critical in the context of psychiatry as it is expected that researchers will encounter them during the stages of ML model development and deployment. We detail practical solutions and best practices to effectively mitigate the outlined challenges. These recommendations have the potential to improve reliability and interpretability of ML models in psychiatry.

Comparison of machine learning models to predict complications of bariatric surgery: A systematic review.

Background and aim: Due to changes in lifestyle, bariatric surgery is expanding worldwide. However, this surgery has numerous complications, and early identification of these complications could be essential in assisting patients to have a higher-quality surgery. Machine learning has a significant role in prediction tasks. So far, no systematic review has been carried out on leveraging ML techniques for predicting complications of bariatric surgery. Therefore, this study aims to perform a systematic review for better prediction insight. Materials and methods: This review was conducted in 2023 based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). We searched scientific databases using the inclusion and exclusion criteria to obtain articles. The data extraction form was used to gather data. To analyze the data, we leveraged the narrative synthesis of the quantitative data. Results: Ensemble algorithms outperformed others in large databases, especially at the national registries. Artificial Neural Networks (ANN) performed better than others based on one-single-center database. Also, Deep Belief Networks (DBN) and ANN obtained favorable performance for complications such as diabetes, dyslipidemia, hypertension, thrombosis, leakage, and depression. Conclusion: This review gave us insight into using ensemble and non-ensemble algorithms based on the types of datasets and complications.

Translational Connectomics: overview of machine learning in macroscale Connectomics for clinical insights.

Connectomics is a neuroscience paradigm focused on noninvasively mapping highly intricate and organized networks of neurons. The advent of neuroimaging has led to extensive mapping of the brain functional and structural connectome on a macroscale level through modalities such as functional and diffusion MRI. In parallel, the healthcare field has witnessed a surge in the application of machine learning and artificial intelligence for diagnostics, especially in imaging. While reviews covering machine learn ing and macroscale connectomics exist for specific disorders, none provide an overview that captures their evolving role, especially through the lens of clinical application and translation. The applications include understanding disorders, classification, identifying neuroimaging biomarkers, assessing severity, predicting outcomes and intervention response, identifying potential targets for brain stimulation, and evaluating the effects of stimulation intervention on the brain and connectome mapping in patients before neurosurgery. The covered studies span neurodegenerative, neurodevelopmental, neuropsychiatric, and neurological disorders. Along with applications, the review provides a brief of common ML methods to set context. Conjointly, limitations in ML studies within connectomics and strategies to mitigate them have been covered.

Development of a Predictive Model to Determine Appropriate Length of Profile.

INTRODUCTION: Musculoskeletal injuries are one of the primary causes of Soldiers' inability to be medically ready, comprising over 80% of such causes. The electronic profile (e-Profile) is the way that musculoskeletal injuries are documented so that commanders will know the type of injury as well as the length of the time that the Soldier will need limited duty. A previous study of e-Profiles in an Army MTF Integrated Pain Management Center showed that the median length of an e-Profile was 30 days. It is in the best interest of the Army to have the Soldier out of the fight the minimum amount of time for recovery to ensure the unit readiness. The goal of this study was to utilize e-Profile data to see if a machine learning model can be developed to determine the appropriate time a Soldier needs to be on profile for a given diagnoses. MATERIALS AND METHODS: Institutional Review Board approval was obtained from the USAMRDC (protocol #M-10966). The initial dataset provided to the research team consisted of a single pipe delimited ("|") text file containing 2.9 million rows of e-Profile data. Linear regression, decision trees, and random forests (RFs) were evaluated to see which model would best predict the number of days needed for an e-Profile. RESULTS: Linear regression had an adjusted R-squared of 0.165. The positive predictive value of decision trees (0-to-30-day range of e-Profiles) was 73.6%, and the negative predictive value (30-90 days) was 60.9% with an area under the receiver operating characteristic curve (AUC) of 0.694 for the model. The positive predictive value of RFs was 85.3% (for the 0-30 range), and the negative predictive value was 58.7% (for the 30-90 range) with an AUC of 0.794. An AUC that approaches 1 indicates a more accurate prediction. CONCLUSIONS: The 3 models (linear regression, decision trees, and RF) studied as part of this project did not predict the days on e-Profile with a high degree of certainty. Future research will focus on adding additional data to the e-Profile dataset in order to improve model accuracy.

Engineering Features From Advanced Medical Technology Initiative Submissions to Enable Predictive Modeling for Proposal Success.

INTRODUCTION: The U.S. Army Telemedicine and Advanced Technology Research Center Advanced Medical Technology Initiative (AMTI) demonstrate key emerging technologies related to military medicine. AMTI invites researchers to submit proposals for short-term funding opportunities that support this goal. AMTI proposal selection is guided by a time-intensive peer review process, where proposals are rated on innovation, military relevance, metrics for success, and return on investment. Utilizing machine learning (ML) could assist in proposal evaluations by learning relationships between proposal performance and proposal features. This research explores the viability of artificial intelligence/ML for predicting proposal ratings given content-based proposal features. Although not meant to replace experts, a model-based approach to evaluating proposal quality could work alongside experts to provide a fast, minimally biased estimate of proposal performance. This article presents initial stages of a project aiming to use ML to prioritize research proposals. MATERIALS AND METHODS: The initial steps included a literature review to identify potential features. Then, these features were extracted from a dataset consisting of past proposals submissions. The dataset includes 824 proposals submitted to the AMTI program from 2010 to 2022. The analysis will inform a discussion of anticipated next steps toward developing a ML model. The following features were created for future modeling: requested funds; word count by section; readability by section; citations and partners identified; and term frequency-inverse document frequency word vectors. RESULTS: This initial process identified the top ranked words (data, health, injury, device, treatment, technology, etc.) among the abstract, problem to be solved, military relevance, and metrics/outcomes text proposal fields. The analysis also evaluated the text fields for readability using the Flesch readability scale. Most proposals text fields were categorized as "college graduate," indicating a challenging readability level. Finally, citations and partners were reviewed as an indicator of proposal successfulness. CONCLUSIONS: This research was the first stage of a larger project to explore the use of ML to predict proposal ratings for the purpose of providing automated support to proposal reviewers and to reveal the preferences and values of AMTI proposal reviewers and other decision-makers. The result of this work will provide practical insights regarding the review process for the AMTI program. This will facilitate reduction in bias for AMTI innovators and a streamlined and subjective process for AMTI administrators, which benefits the military health system overall.

Disease Trajectories from Healthcare Data: Methodologies, Key Results, and Future Perspectives.

Disease trajectories, defined as sequential, directional disease associations, have become an intense research field driven by the availability of electronic population-wide healthcare data and sufficient computational power. Here, we provide an overview of disease trajectory studies with a focus on European work, including ontologies used as well as computational methodologies for the construction of disease trajectories. We also discuss different applications of disease trajectories from descriptive risk identification to disease progression, patient stratification, and personalized predictions using machine learning. We describe challenges and opportunities in the area that eventually will benefit from initiatives such as the European Health Data Space, which, with time, will make it possible to analyze data from cohorts comprising hundreds of millions of patients.

Data-driven prediction of spinal cord injury recovery: An exploration of current status and future perspectives.

Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is a promising approach to enhance the prediction of recovery trajectories, but its integration into clinical practice requires a thorough understanding of its efficacy and applicability. We systematically reviewed the current literature on data-driven models of SCI recovery prediction. The included studies were evaluated based on a range of criteria assessing the approach, implementation, input data preferences, and the clinical outcomes aimed to forecast. We observe a tendency to utilize routinely acquired data, such as International Standards for Neurological Classification of SCI (ISNCSCI), imaging, and demographics, for the prediction of functional outcomes derived from the Spinal Cord Independence Measure (SCIM) III and Functional Independence Measure (FIM) scores with a focus on motor ability. Although there has been an increasing interest in data-driven studies over time, traditional machine learning architectures, such as linear regression and tree-based approaches, remained the overwhelmingly popular choices for implementation. This implies ample opportunities for exploring architectures addressing the challenges of predicting SCI recovery, including techniques for learning from limited longitudinal data, improving generalizability, and enhancing reproducibility. We conclude with a perspective, highlighting possible future directions for data-driven SCI recovery prediction and drawing parallels to other application fields in terms of diverse data types (imaging, tabular, sequential, multimodal), data challenges (limited, missing, longitudinal data), and algorithmic needs (causal inference, robustness).

Digital innovations for monitoring sustainability in food systems.

Monitoring systems that incentivize, track and verify compliance with social and environmental standards are widespread in food systems. In particular, digital monitoring approaches using remote sensing, machine learning, big data, smartphones, platforms and blockchain are proliferating. The increasing use and availability of these technologies put us at a critical juncture to leverage these innovations for enhanced transparency, fairness and open access, rather than descending into a dystopian landscape of digital surveillance and division perpetuated by a powerful few. Here we discuss opportunities and risks, and highlight research gaps linked to the ongoing digitalization of monitoring approaches.

Clinical Deployment of Machine Learning Tools in Transplant Medicine: What Does the Future Hold?

Medical applications of machine learning (ML) have shown promise in analyzing patient data to support clinical decision-making and provide patient-specific outcomes. In transplantation, several applications of ML exist which include pretransplant: patient prioritization, donor-recipient matching, organ allocation, and posttransplant outcomes. Numerous studies have shown the development and utility of ML models, which have the potential to augment transplant medicine. Despite increasing efforts to develop robust ML models for clinical use, very few of these tools are deployed in the healthcare setting. Here, we summarize the current applications of ML in transplant and discuss a potential clinical deployment framework using examples in organ transplantation. We identified that creating an interdisciplinary team, curating a reliable dataset, addressing the barriers to implementation, and understanding current clinical evaluation models could help in deploying ML models into the transplant clinic setting.

Artificial intelligence in total and unicompartmental knee arthroplasty.

The application of Artificial intelligence (AI) and machine learning (ML) tools in total (TKA) and unicompartmental knee arthroplasty (UKA) emerges with the potential to improve patient-centered decision-making and outcome prediction in orthopedics, as ML algorithms can generate patient-specific risk models. This review aims to evaluate the potential of the application of AI/ML models in the prediction of TKA outcomes and the identification of populations at risk.An extensive search in the following databases: MEDLINE, Scopus, Cinahl, Google Scholar, and EMBASE was conducted using the PIOS approach to formulate the research question. The PRISMA guideline was used for reporting the evidence of the data extracted. A modified eight-item MINORS checklist was employed for the quality assessment. The databases were screened from the inception to June 2022.Forty-four out of the 542 initially selected articles were eligible for the data analysis; 5 further articles were identified and added to the review from the PUBMED database, for a total of 49 articles included. A total of 2,595,780 patients were identified, with an overall average age of the patients of 70.2 years ± 7.9 years old. The five most common AI/ML models identified in the selected articles were: RF, in 38.77% of studies; GBM, in 36.73% of studies; ANN in 34.7% of articles; LR, in 32.65%; SVM in 26.53% of articles.This systematic review evaluated the possible uses of AI/ML models in TKA, highlighting their potential to lead to more accurate predictions, less time-consuming data processing, and improved decision-making, all while minimizing user input bias to provide risk-based patient-specific care.