The role of machine learning in clinical research: transforming the future of evidence generation

Machine learning approach as an early warning system to prevent foodborne Salmonella outbreaks in northwestern Italy

Salmonellosis, one of the most common foodborne infections in Europe, is monitored by food safety surveillance programmes, resulting in the generation of extensive databases. By leveraging tree-based machine learning (ML) algorithms, we exploited data from food safety audits to predict spatiotemporal patterns of salmonellosis in northwestern Italy. Data on human cases confirmed in 2015-2018 (n = 1969) and food surveillance data collected in 2014-2018 were used to develop ML algorithms. We integrated the monthly municipal human incidence with 27 potential predictors, including the observed prevalence of Salmonella in food. We applied the tree regression, random forest and gradient boosting algorithms considering different scenarios and evaluated their predictivity in terms of the mean absolute percentage error (MAPE) and R2. Using a similar dataset from the year 2019, spatiotemporal predictions and their relative sensitivities and specificities were obtained. Random forest and gradient boosting (R2 = 0.55, MAPE = 7.5%) outperformed the tree regression algorithm (R2 = 0.42, MAPE = 8.8%). Salmonella prevalence in food; spatial features; and monitoring efforts in ready-to-eat milk, fruits and vegetables, and pig meat products contributed the most to the models' predictivity, reducing the variance by 90.5%. Conversely, the number of positive samples obtained for specific food matrices minimally influenced the predictions (2.9%). Spatiotemporal predictions for 2019 showed sensitivity and specificity levels of 46.5% (due to the lack of some infection hotspots) and 78.5%, respectively. This study demonstrates the added value of integrating data from human and veterinary health services to develop predictive models of human salmonellosis occurrence, providing early warnings useful for mitigating foodborne disease impacts on public health.

Predictors of compulsive cyberporn use: A machine learning analysis

Introduction

Compulsive cyberporn use (CCU) has previously been reported among people who use cyberporn. However, most of the previous studies included convenience samples of students or samples of the general adult population. Research examining the factors that predict or are associated with CCU are still scarce.In this study, we aimed to (a) assess compulsive cyberporn consumption in a broad sample of people who had used cyberporn and (b) determine, among a diverse range of predictor variables, which are most important in CCU scores, as assessed with the eight-item Compulsive Internet Use Scale adapted for cyberporn.

Materials and Methods

Overall, 1584 adult English speakers (age: 18-75 years, M = 33.18; sex: 63.1 % male, 35.2 % female, 1.7 % nonbinary) who used cyberporn during the last 6 months responded to an online questionnaire that assessed sociodemographic, sexual, psychological, and psychosocial variables. Their responses were subjected to correlation analysis, analysis of variance, and machine learning analysis.

Results

Among the participants, 21.96% (in the higher quartile) presented CCU symptoms in accordance with their CCU scores. The five most important predictors of CCU scores were related to the users' strength of craving for pornography experiences, suppression of negative emotions porn use motive, frequency of cyberporn use over the past year, acceptance of rape myths, and anxious attachment style.

Conclusions

From a large and diverse pool of variables, we determined the most important predictors of CCU scores. The findings contribute to a better understanding of problematic pornography use and could enrich compulsive cyberporn treatment and prevention.

A joint physics and radiobiology DREAM team vision - Towards better response prediction models to advance radiotherapy

Radiotherapy developed empirically through experience balancing tumour control and normal tissue toxicities. Early simple mathematical models formalized this practical knowledge and enabled effective cancer treatment to date. Remarkable advances in technology, computing, and experimental biology now create opportunities to incorporate this knowledge into enhanced computational models. The ESTRO DREAM (Dose Response, Experiment, Analysis, Modelling) workshop brought together experts across disciplines to pursue the vision of personalized radiotherapy for optimal outcomes through advanced modelling. The ultimate vision is leveraging quantitative models dynamically during therapy to ultimately achieve truly adaptive and biologically guided radiotherapy at the population as well as individual patient-based levels. This requires the generation of models that inform response-based adaptations, individually optimized delivery and enable biological monitoring to provide decision support to clinicians. The goal is expanding to models that can drive the realization of personalized therapy for optimal outcomes. This position paper provides their propositions that describe how innovations in biology, physics, mathematics, and data science including AI could inform models and improve predictions. It consolidates the DREAM team's consensus on scientific priorities and organizational requirements. Scientifically, it stresses the need for rigorous, multifaceted model development, comprehensive validation and clinical applicability and significance. Organizationally, it reinforces the prerequisites of interdisciplinary research and collaboration between physicians, medical physicists, radiobiologists, and computational scientists throughout model development. Solely by a shared understanding of clinical needs, biological mechanisms, and computational methods, more informed models can be created. Future research environment and support must facilitate this integrative method of operation across multiple disciplines.

Online application for the diagnosis of atherosclerosis by six genes

BACKGROUND

Atherosclerosis (AS) is a primary contributor to cardiovascular disease, leading to significant global mortality rates. Developing effective diagnostic indicators and models for AS holds the potential to substantially reduce the fatalities and disabilities associated with cardiovascular disease. Blood sample analysis has emerged as a promising avenue for facilitating diagnosis and assessing disease prognosis. Nonetheless, it lacks an accurate model or tool for AS diagnosis. Hence, the principal objective of this study is to develop a convenient, simple, and accurate model for the early detection of AS.

METHODS

We downloaded the expression data of blood samples from GEO databases. By dividing the mean values of housekeeping genes (meanHGs) and applying the comBat function, we aimed to reduce the batch effect. After separating the datasets into training, evaluation, and testing sets, we applied differential expression analyses (DEA) between AS and control samples from the training dataset. Then, a gradient-boosting model was used to evaluate the importance of genes and identify the hub genes. Using different machine learning algorithms, we constructed a prediction model with the highest accuracy in the testing dataset. Finally, we make the machine learning models publicly accessible by shiny app construction.

RESULTS

Seven datasets (GSE9874, GSE12288, GSE20129, GSE23746, GSE27034, GSE90074, and GSE202625), including 403 samples with AS and 325 healthy subjects, were obtained by comprehensive searching and filtering by specific requirements. The batch effect was successfully removed by dividing the meanHGs and applying the comBat function. 331 genes were found to be related to atherosclerosis by the DEA analysis between AS and health samples. The top 6 genes with the highest importance values from the gradient boosting model were identified. Out of the seven machine learning algorithms tested, the random forest model exhibited the most impressive performance in the testing datasets, achieving an accuracy exceeding 0.8. While the batch effect reduction analysis in our study could have contributed to the increased accuracy values, our comparison results further highlight the superiority of our model over the genes provided in published studies. This underscores the effectiveness of our approach in delivering superior predictive performance. The machine-learning models were then uploaded to the Shiny app's server, making it easy for users to distinguish AS samples from normal samples.

CONCLUSIONS

A prognostic Shiny application, built upon six potential atherosclerosis-associated genes, has been developed, offering an accurate diagnosis of atherosclerosis.

Integrating clinical pharmacology and artificial intelligence: potential benefits, challenges, and role of clinical pharmacologists

INTRODUCTION

The integration of artificial intelligence (AI) into clinical pharmacology could be a potential approach for accelerating drug discovery and development, improving patient care, and streamlining medical research processes.

AREAS COVERED

We reviewed the current state of AI applications in clinical pharmacology, focusing on drug discovery and development, precision medicine, pharmacovigilance, and other ventures. Key AI applications in clinical pharmacology are examined, including machine learning, natural language processing, deep learning, and reinforcement learning etc. Additionally, the evolving role of clinical pharmacologists, ethical considerations, and challenges in implementing AI in clinical pharmacology are discussed.

EXPERT OPINION

The AI could be instrumental in accelerating drug discovery, predicting drug safety and efficacy, and optimizing clinical trial designs. It can play a vital role in precision medicine by helping in personalized drug dosing, treatment selection, and predicting drug response based on genetic, clinical, and environmental factors. The role of AI in pharmacovigilance, such as signal detection and adverse event prediction, is also promising. The collaboration between clinical pharmacologists and AI experts also poses certain ethical and practical challenges. Clinical pharmacologists can be instrumental in shaping the future of AI-driven clinical pharmacology and contribute to the improvement of healthcare systems.

Artificial Intelligence Tools for Improving Manometric Diagnosis of Esophageal Dysmotility

PURPOSE OF REVIEW

Artificial intelligence (AI) is a broad term that pertains to a computer's ability to mimic and sometimes surpass human intelligence in interpretation of large datasets. The adoption of AI in gastrointestinal motility has been slower compared to other areas such as polyp detection and interpretation of histopathology.

RECENT FINDINGS

Within esophageal physiologic testing, AI can automate interpretation of image-based tests, especially high resolution manometry (HRM) and functional luminal imaging probe (FLIP) studies. Basic tasks such as identification of landmarks, determining adequacy of the HRM study and identification from achalasia from non-achalasia patterns are achieved with good accuracy. However, existing AI systems compare AI interpretation to expert analysis rather than to clinical outcome from management based on AI diagnosis. The use of AI methods is much less advanced within the field of ambulatory reflux monitoring, where challenges exist in assimilation of data from multiple impedance and pH channels. There remains potential for replication of the AI successes within esophageal physiologic testing to HRM of the anorectum, and to innovative and novel methods of evaluating gastric electrical activity and motor function. The use of AI has tremendous potential to improve detection of dysmotility within the esophagus using esophageal physiologic testing, as well as in other regions of the gastrointestinal tract. Eventually, integration of patient presentation, demographics and alternate test results to individual motility test interpretation will improve diagnostic precision and prognostication using AI tools.

Performance discrepancy mitigation in heart disease prediction for multisensory inter-datasets

Heart disease is one of the primary causes of morbidity and death worldwide. Millions of people have had heart attacks every year, and only early-stage predictions can help to reduce the number. Researchers are working on designing and developing early-stage prediction systems using different advanced technologies, and machine learning (ML) is one of them. Almost all existing ML-based works consider the same dataset (intra-dataset) for the training and validation of their method. In particular, they do not consider inter-dataset performance checks, where different datasets are used in the training and testing phases. In inter-dataset setup, existing ML models show a poor performance named the inter-dataset discrepancy problem. This work focuses on mitigating the inter-dataset discrepancy problem by considering five available heart disease datasets and their combined form. All potential training and testing mode combinations are systematically executed to assess discrepancies before and after applying the proposed methods. Imbalance data handling using SMOTE-Tomek, feature selection using random forest (RF), and feature extraction using principle component analysis (PCA) with a long preprocessing pipeline are used to mitigate the inter-dataset discrepancy problem. The preprocessing pipeline builds on missing value handling using RF regression, log transformation, outlier removal, normalization, and data balancing that convert the datasets to more ML-centric. Support vector machine, K-nearest neighbors, decision tree, RF, eXtreme Gradient Boosting, Gaussian naive Bayes, logistic regression, and multilayer perceptron are used as classifiers. Experimental results show that feature selection and classification using RF produce better results than other combination strategies in both single- and inter-dataset setups. In certain configurations of individual datasets, RF demonstrates 100% accuracy and 96% accuracy during the feature selection phase in an inter-dataset setup, exhibiting commendable precision, recall, F1 score, specificity, and AUC score. The results indicate that an effective preprocessing technique has the potential to improve the performance of the ML model without necessitating the development of intricate prediction models. Addressing inter-dataset discrepancies introduces a novel research avenue, enabling the amalgamation of identical features from various datasets to construct a comprehensive global dataset within a specific domain.

Using an Interpretable Amino Acid-Based Machine Learning Method to Enhance the Diagnosis of Major Depressive Disorder

Background: Major depressive disorder (MDD) is a leading cause of disability worldwide. At present, however, there are no established biomarkers that have been validated for diagnosing and treating MDD. This study sought to assess the diagnostic and predictive potential of the differences in serum amino acid concentration levels between MDD patients and healthy controls (HCs), integrating them into interpretable machine learning models. Methods: In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. Serum amino acid profiling was conducted by means of chromatography-mass spectrometry. A total of 21 metabolites were analysed, with 17 from a preset amino acid panel and the remaining 4 from a preset kynurenine panel. Logistic regression was applied to differentiate MDD patients from HCs. Results: The best-performing model utilised both feature selection and hyperparameter optimisation and yielded a moderate area under the receiver operating curve (AUC) classification value of 0.76 on the testing data. The top five metabolites identified as potential biomarkers for MDD were 3-hydroxy-kynurenine, valine, kynurenine, glutamic acid, and xanthurenic acid. Conclusions: Our study highlights the potential of using an interpretable machine learning analysis model based on amino acids to aid and increase the diagnostic accuracy of MDD in clinical practice.

Development and use of machine learning algorithms in vaccine target selection

Computer-aided discovery of vaccine targets has become a cornerstone of rational vaccine design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in rational vaccine design concerned with the identification of B and T cell epitopes and correlates of protection. I provide examples of ML models, as well as types of data and predictions for which they are built. I argue that interpretable ML has the potential to improve the identification of immunogens also as a tool for scientific discovery, by helping elucidate the molecular processes underlying vaccine-induced immune responses. I outline the limitations and challenges in terms of data availability and method development that need to be addressed to bridge the gap between advances in ML predictions and their translational application to vaccine design.

Inference of social cognition in schizophrenia patients with neurocognitive domains and neurocognitive tests using automated machine learning

AIM

It has been suggested that single neurocognitive domain or neurocognitive test can be used to determine the overall cognitive function in schizophrenia using machine learning algorithms. It is unknown whether social cognition in schizophrenia patients can be estimated with machine learning based on neurocognitive domains or neurocognitive tests.

METHODS

To predict social cognition in schizophrenia, we applied an automated machine learning (AutoML) framework resulting from the analysis of predictive factors such as six neurocognitive domain scores and nine neurocognitive test scores of 380 schizophrenia patients in the Taiwanese population. Four clinical parameters (i.e., age, gender, subgroup, and education) were also used as predictive factors. We utilized an AutoML framework called Tree-based Pipeline Optimization Tool (TPOT) to generate predictive pipelines automatically.

RESULTS

The analysis revealed that all neurocognitive domains and tests except the reasoning and problem solving domain/test showed significant associations with social cognition. In addition, a TPOT-generated pipeline can best predict social cognition in schizophrenia using seven predictive factors, including five neurocognitive domains (i.e., speed of processing, sustained attention, working memory, verbal learning and memory, and visual learning and memory) and two clinical parameters (i.e., age and gender). This predictive pipeline consists of machine learning algorithms such as function transformers, an approximate feature map, independent component analysis, and linear regression.

CONCLUSION

The study indicates that an AutoML framework such as TPOT may provide a promising way to produce truly effective machine learning pipelines for predicting social cognition in schizophrenia using neurocognitive domains and/or neurocognitive tests.

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

BACKGROUND

The utilization of artificial intelligence and machine learning as diagnostic and predictive tools in perioperative medicine holds great promise. Indeed, many studies have been performed in recent years to explore the potential. The purpose of this systematic review is to assess the current state of machine learning in perioperative medicine, its utility in prediction of complications and prognostication, and limitations related to bias and validation.

METHODS

A multidisciplinary team of clinicians and engineers conducted a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol. Multiple databases were searched, including Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, PubMed, Medline, Embase, and Web of Science. The systematic review focused on study design, type of machine learning model used, validation techniques applied, and reported model performance on prediction of complications and prognostication. This review further classified outcomes and machine learning applications using an ad hoc classification system. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess risk of bias and applicability of the studies.

RESULTS

A total of 103 studies were identified. The models reported in the literature were primarily based on single-center validations (75%), with only 13% being externally validated across multiple centers. Most of the mortality models demonstrated a limited ability to discriminate and classify effectively. The PROBAST assessment indicated a high risk of systematic errors in predicted outcomes and artificial intelligence or machine learning applications.

CONCLUSIONS

The findings indicate that the development of this field is still in its early stages. This systematic review indicates that application of machine learning in perioperative medicine is still at an early stage. While many studies suggest potential utility, several key challenges must be first overcome before their introduction into clinical practice.

EDITOR’S PERSPECTIVE

Generative artificial intelligence empowers digital twins in drug discovery and clinical trials

INTRODUCTION

The concept of Digital Twins (DTs) translated to drug development and clinical trials describes virtual representations of systems of various complexities, ranging from individual cells to entire humans, and enables in silico simulations and experiments. DTs increase the efficiency of drug discovery and development by digitalizing processes associated with high economic, ethical, or social burden. The impact is multifaceted: DT models sharpen disease understanding, support biomarker discovery and accelerate drug development, thus advancing precision medicine. One way to realize DTs is by generative artificial intelligence (AI), a cutting-edge technology that enables the creation of novel, realistic and complex data with desired properties.

AREAS COVERED

The authors provide a brief introduction to generative AI and describe how it facilitates the modeling of DTs. In addition, they compare existing implementations of generative AI for DTs in drug discovery and clinical trials. Finally, they discuss technical and regulatory challenges that should be addressed before DTs can transform drug discovery and clinical trials.

EXPERT OPINION

The current state of DTs in drug discovery and clinical trials does not exploit the entire power of generative AI yet and is limited to simulation of a small number of characteristics. Nonetheless, generative AI has the potential to transform the field by leveraging recent developments in deep learning and customizing models for the needs of scientists, physicians and patients.

Predicting Phase 1 Lymphoma Clinical Trial Durations Using Machine Learning: An In-Depth Analysis and Broad Application Insights

Lymphoma diagnoses in the US are substantial, with an estimated 89,380 new cases in 2023, necessitating innovative treatment approaches. Phase 1 clinical trials play a pivotal role in this context. We developed a binary predictive model to assess trial adherence to expected average durations, analyzing 1089 completed Phase 1 lymphoma trials from clinicaltrials.gov. Using machine learning, the Random Forest model demonstrated high efficacy with an accuracy of 0.7248 and an ROC-AUC of 0.7677 for lymphoma trials. The difference in the accuracy level of the Random Forest is statistically significant compared to the other alternative models, as determined by a 95% confidence interval on the testing set. Importantly, this model maintained an ROC-AUC of 0.7701 when applied to lung cancer trials, showcasing its versatility. A key insight is the correlation between higher predicted probabilities and extended trial durations, offering nuanced insights beyond binary predictions. Our research contributes to enhanced clinical research planning and potential improvements in patient outcomes in oncology.

Atopic March or Atopic Multimorbidity-Overview of Current Research

The atopic march encompasses a sequence of allergic conditions, including atopic dermatitis, food allergy, allergic rhinitis, and asthma, that frequently develop in a sequential pattern within the same individual. It was introduced as a conceptual framework aimed at elucidating the developmental trajectory of allergic conditions during childhood. Following the introduction of this concept, it was initially believed that the atopic march represented the sole and definitive trajectory of the development of allergic diseases. However, this perspective evolved with the emergence of new longitudinal studies, which revealed that the evolution of allergic diseases is far more intricate. It involves numerous immunological pathological mechanisms and may not align entirely with the traditional concept of the atopic march. The objective of our review is to portray the atopic march alongside other patterns in the development of childhood allergic diseases, with a specific emphasis on the potential for a personalized approach to the prevention, diagnosis, and treatment of atopic conditions.

AI/ML advances in non-small cell lung cancer biomarker discovery

Lung cancer is the leading cause of cancer deaths among both men and women, representing approximately 25% of cancer fatalities each year. The treatment landscape for non-small cell lung cancer (NSCLC) is rapidly evolving due to the progress made in biomarker-driven targeted therapies. While advancements in targeted treatments have improved survival rates for NSCLC patients with actionable biomarkers, long-term survival remains low, with an overall 5-year relative survival rate below 20%. Artificial intelligence/machine learning (AI/ML) algorithms have shown promise in biomarker discovery, yet NSCLC-specific studies capturing the clinical challenges targeted and emerging patterns identified using AI/ML approaches are lacking. Here, we employed a text-mining approach and identified 215 studies that reported potential biomarkers of NSCLC using AI/ML algorithms. We catalogued these studies with respect to BEST (Biomarkers, EndpointS, and other Tools) biomarker sub-types and summarized emerging patterns and trends in AI/ML-driven NSCLC biomarker discovery. We anticipate that our comprehensive review will contribute to the current understanding of AI/ML advances in NSCLC biomarker research and provide an important catalogue that may facilitate clinical adoption of AI/ML-derived biomarkers.

Artificial intelligence revolutionizing drug development: Exploring opportunities and challenges

By harnessing artificial intelligence (AI) algorithms and machine learning techniques, the entire drug discovery process stands to undergo a profound transformation, offering a myriad of advantages. Foremost among these is the ability of AI to conduct swift and efficient screenings of expansive compound libraries, significantly augmenting the identification of potential drug candidates. Moreover, AI algorithms can prove instrumental in predicting the efficacy and safety profiles of candidate compounds, thus endowing invaluable insights and reducing reliance on extensive preclinical and clinical testing. This predictive capacity of AI has the potential to streamline the drug development pipeline and enhance the success rate of clinical trials, ultimately resulting in the emergence of more efficacious and safer therapeutic agents. However, the deployment of AI in drug discovery introduces certain challenges that warrant attention. A primary hurdle entails the imperative acquisition of high-quality and diverse data. Furthermore, ensuring the interpretability of AI models assumes critical importance in securing regulatory endorsement and cultivating trust within scientific and medical communities. Addressing ethical considerations, including data privacy and mitigating bias, represents an additional momentous challenge, requiring assiduous navigation. In this review, we provide an intricate and comprehensive overview of the multifaceted challenges intrinsic to conventional drug development paradigms, while simultaneously interrogating the efficacy of AI in effectively surmounting these formidable obstacles.

Oncologic Outcomes in Nipple-sparing Mastectomy with Immediate Reconstruction and Total Mastectomy with Immediate Reconstruction in Women with Breast Cancer: A Machine-Learning Analysis

BACKGROUND

This study used a single-institution cohort, the Severance dataset, validated the results by using the surveillance, epidemiology, and end results (SEER) database, adjusted with propensity-score matching (PSM), and analyzed by using a machine learning method. To determine whether the 5-year, disease-free survival (DFS) and overall survival (OS) of patients undergoing nipple-sparing mastectomy (NSM) with immediate breast reconstruction (IBR) are not inferior to those of women treated with total mastectomy/skin-sparing mastectomy (TM/SSM).

METHODS

The Severance dataset enrolled 611 patients with early, invasive breast cancer from 2010 to 2017. The SEER dataset contained data for 485,245 patients undergoing TM and 14,770 patients undergoing NSM between 2000 and 2018. All patients underwent mastectomy and IBR. Intraoperative, frozen-section biopsy for the retro-areolar tissue was performed in the NSM group. The SEER dataset was extracted by using operation types, including TM/SSM and NSM. The primary outcome was DFS for the Severance dataset and OS for the SEER dataset. PSM analysis was applied. Survival outcomes were analyzed by using the Kaplan-Meier method and Cox proportional hazard (Cox PH) regression model. We implemented XGBSE to predict mortality with high accuracy and evaluated model prediction performance using a concordance index. The final model inspected the impact of relevant predictors on the model output using shapley additive explanation (SHAP) values.

RESULTS

In the Severance dataset, 151 patients underwent NSM with IBR and 460 patients underwent TM/SSM with IBR. No significant differences were found between the groups. In multivariate analysis, NSM was not associated with reduced oncologic outcomes. The same results were observed in PSM analysis. In the SEER dataset, according to the SHAP values, the individual feature contribution suggested that AJCC stage ranks first. Analyses from the two datasets confirmed no impact on survival outcomes from the two surgical methods.

CONCLUSIONS

NSM with IBR is a safe and feasible procedure in terms of oncologic outcomes. Analysis using machine learning methods can be successfully applied to identify significant risk factors for oncologic outcomes.

AF and in-hospital mortality in COVID-19 patients

Background

There are conflicting data on whether new-onset atrial fibrillation (AF) is independently associated with poor outcomes in COVID-19 patients. This study represents the largest dataset curated by manual chart review comparing clinical outcomes between patients with sinus rhythm, pre-existing AF, and new-onset AF.

Objective

The primary aim of this study was to assess patient outcomes in COVID-19 patients with sinus rhythm, pre-existing AF, and new-onset AF. The secondary aim was to evaluate predictors of new-onset AF in patients with COVID-19 infection.

Methods

This was a single-center retrospective study of patients with a confirmed diagnosis of COVID-19 admitted between March and September 2020. Patient demographic data, medical history, and clinical outcome data were manually collected. Adjusted comparisons were performed following propensity score matching between those with pre-existing or new-onset AF and those without AF.

Results

The study population comprised of 1241 patients. A total of 94 (7.6%) patients had pre-existing AF and 42 (3.4%) patients developed new-onset AF. New-onset AF was associated with increased in-hospital mortality before (odds ratio [OR] 3.58, 95% confidence interval [CI] 1.78-7.06, P < .005) and after (OR 2.80, 95% CI 1.01-7.77, P < .005) propensity score matching compared with the no-AF group. However, pre-existing AF was not independently associated with in-hospital mortality compared with patients with no AF (postmatching OR: 1.13, 95% CI 0.57-2.21, P = .732).

Conclusion

New-onset AF, but not pre-existing AF, was independently associated with elevated mortality in patients hospitalised with COVID-19. This observation highlights the need for careful monitoring of COVID-19 patients with new-onset AF. Further research is needed to explain the mechanistic relationship between new-onset AF and clinical outcomes in COVID-19 patients.

In-hospital fall prediction using machine learning algorithms and the Morse fall scale in patients with acute stroke: a nested case-control study

BACKGROUND

Falls are one of the most common accidents in medical institutions, which can threaten the safety of inpatients and negatively affect their prognosis. Herein, we developed a machine learning (ML) model for fall prediction in patients with acute stroke and compared its accuracy with that of the existing fall risk prediction tool, the Morse Fall Scale (MFS).

METHODS

This is a retrospective nested case-control study. The initial sample size was 8462 admitted to a single cerebrovascular specialty hospital with acute stroke. A total of 156 fall events occurred, and each fall case was randomly matched with six control cases. Six ML algorithms were used, namely, regularized logistic regression, support vector machine, naïve Bayes (NB), k-nearest neighbors, random forest, and extreme-gradient boosting (XGB).

RESULTS

We included 156 in the fall group and 934 in the non-fall group. The mean ages of the fall and non-fall groups were 68.3 (± 12.2) and 65.3 (± 12.9) years old, respectively. The MFS total score was significantly higher in the fall group (54.3 ± 18.3) than in the non-fall group (37.7 ± 14.7). The area under the receiver operating curve (AUROC) of the MFS in predicting falls was 0.76 (0.73-0.79). XGB had the highest AUROC of 0.85 (0.78-0.92), and XGB and NB had the highest F1 score of 0.44.

CONCLUSIONS

The AUROC values of all of ML algorithms were similar to those of the MFS in predicting fall risk in patients with acute stroke, allowing for accurate and efficient fall screening.

Exploring the association of metal mixture in blood to the kidney function and tumor necrosis factor alpha using machine learning methods

This research aimed to approach relationships between metal mixture in blood and kidney function, tumor necrosis factor alpha (TNF-α) by machine learning. Metals levels were measured by Inductively Couple Plasma Mass Spectrometry in blood from 421 participants. We applied K Nearest Neighbor (KNN), Naive Bayes classifier (NB), Support Vector Machines (SVM), random forest (RF), Gradient Boosting Decision Tree (GBDT), Categorical boosting (CatBoost), eXtreme Gradient Boosting (XGBoost), Whale Optimization-based XGBoost (WXGBoost) to identify the effect of plasma metals, TNF-α, and estimated glomerular filtration rate (eGFR by CKD-EPI equation). We conducted not only toxic metals, lead (Pb), arsenic (As), cadmium (Cd) but also included trace essential metals, selenium (Se), copper (Cu), zinc (Zn), cobalt (Co), to predict the interaction of TNF-α, TNF-α/white blood count, and eGFR. The high average TNF-α level group was observed among subjects with higher Pb, As, Cd, Cu, and Zn levels in blood. No associations were shown between the low and high TNF-α level group in blood Se and Co levels. Those with lower eGFR group had high Pb, As, Cd, Co, Cu, and Zn levels. The crucial predictor of TNF-α level in metals was blood Pb, and then Cd, As, Cu, Se, Zn and Co. The machine learning revealed that As was the major role among predictors of eGFR after feature selection. The levels of kidney function and TNF-α were modified by co-exposure metals. We were able to acquire highest accuracy of over 85% in the multi-metals exposure model. The higher Pb and Zn levels had strongest interaction with declined eGFR. In addition, As and Cd had synergistic with prediction model of TNF-α. We explored the potential of machine learning approaches for predicting health outcomes with multi-metal exposure. XGBoost model added SHAP could give an explicit explanation of individualized and precision risk prediction and insight of the interaction of key features in the multi-metal exposure.

Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials

BACKGROUND

Whether there is a subset of patients with heart failure with preserved ejection fraction (HFpEF) that benefit from spironolactone therapy is unclear. We applied a machine learning approach to identify responders and non-responders to spironolactone among patients with HFpEF in two large randomized clinical trials.

METHODS

Using a reiterative cluster allocating permutation approach, patients from the derivation cohort (Aldo-DHF) were identified according to their treatment response to spironolactone with respect to improvement in E/e'. Heterogenous features of response ('responders' and 'non-responders') were characterized by an extreme gradient boosting (XGBoost) algorithm. XGBoost was used to predict treatment response in the validation cohort (TOPCAT). The primary endpoint of the validation cohort was a combined endpoint of cardiovascular mortality, aborted cardiac arrest, or heart failure hospitalization. Patients with missing variables for the XGboost model were excluded from the validation analysis.

FINDINGS

Out of 422 patients from the derivation cohort, reiterative cluster allocating permutation identified 159 patients (38%) as spironolactone responders, in whom E/e' significantly improved (p = 0.005). Within the validation cohort (n = 525) spironolactone treatment significantly reduced the occurrence of the primary outcome among responders (n = 185, p log rank = 0.008), but not among patients in the non-responder group (n = 340, p log rank = 0.52).

INTERPRETATION

Machine learning approaches might aid in identifying HFpEF patients who are likely to show a favorable therapeutic response to spironolactone.

FUNDING

See Acknowledgements section at the end of the manuscript.

Association between SYVN1 and SEL1 genetic polymorphisms and remission in rheumatoid arthritis patients treated with TNF-α inhibitors: a machine learning approach

Rheumatoid arthritis (RA) is a severe chronic inflammatory condition that affects joint synovium. Suppressor/enhancer of lin-12-like (SEL1L)-Synoviolin 1 (SYVN1)-mediated endoplasmic reticulum-associated degradation (ERAD) is highly associated with RA development. Although targeting SEL1L-SYVN1-mediated ERAD can be beneficial, studies that evaluate the association between polymorphisms in their genes and remission from the disease in RA patients taking tumor necrosis factor (TNF)-α inhibitors have yet to be carried out. Hence, the purpose of this study was to investigate the association between SYVN1 and SEL1L polymorphisms and TNF-α inhibitor response using various machine learning models. A total of 12 single-nucleotide polymorphisms (SNPs), including 5 SNPs in SYVN1 and 7 SNPs of SEL1L were investigated. Logistic regression analysis was used to examine the relationship between genetic polymorphisms and response to treatment. Various machine learning methods were employed to evaluate factors associated with remission in patients receiving TNF-α inhibitors. After adjusting for covariates, we found that sulfasalazine and rs2025214 in SEL1L increase the remission rates by approximately 3.3 and 2.8 times, respectively (95% confidence intervals 1.126-9.695 and 1.074-7.358, respectively). Machine learning approaches showed acceptable prediction estimates for remission in RA patients receiving TNF-α inhibitors, with the area under the receiver-operating curve (AUROC) values ranging from 0.60 to 0.65. A polymorphism of the SEL1L gene (rs2025214) and sulfasalazine were found to be associated with treatment response in RA patients receiving TNF-α inhibitors. These preliminary data could be used to tailor treatment for RA patients using TNF-α inhibitors.

The Coming of Age of AI/ML in Drug Discovery, Development, Clinical Testing, and Manufacturing: The FDA Perspectives

Artificial intelligence (AI) and machine learning (ML) represent significant advancements in computing, building on technologies that humanity has developed over millions of years-from the abacus to quantum computers. These tools have reached a pivotal moment in their development. In 2021 alone, the U.S. Food and Drug Administration (FDA) received over 100 product registration submissions that heavily relied on AI/ML for applications such as monitoring and improving human performance in compiling dossiers. To ensure the safe and effective use of AI/ML in drug discovery and manufacturing, the FDA and numerous other U.S. federal agencies have issued continuously updated, stringent guidelines. Intriguingly, these guidelines are often generated or updated with the aid of AI/ML tools themselves. The overarching goal is to expedite drug discovery, enhance the safety profiles of existing drugs, introduce novel treatment modalities, and improve manufacturing compliance and robustness. Recent FDA publications offer an encouraging outlook on the potential of these tools, emphasizing the need for their careful deployment. This has expanded market opportunities for retraining personnel handling these technologies and enabled innovative applications in emerging therapies such as gene editing, CRISPR-Cas9, CAR-T cells, mRNA-based treatments, and personalized medicine. In summary, the maturation of AI/ML technologies is a testament to human ingenuity. Far from being autonomous entities, these are tools created by and for humans designed to solve complex problems now and in the future. This paper aims to present the status of these technologies, along with examples of their present and future applications.

Treatment of pulmonary arterial hypertension: recent progress and a look to the future

Pulmonary arterial hypertension (PAH) is a severe but treatable form of pre-capillary pulmonary hypertension caused by pulmonary vascular remodelling. As a result of basic science discoveries, randomised controlled trials, studies of real-world data, and the development of clinical practice guidelines, considerable progress has been made in the treatment options and outcomes for patients with PAH, underscoring the importance of seamless translation of information from bench to bedside and, ultimately, to patients. However, PAH still carries a high mortality rate, which emphasises the urgent need for transformative innovations in the field. In this Series paper, written by a group of clinicians, researchers, and a patient with PAH, we review therapeutic approaches and treatment options for PAH. We summarise current knowledge of the cellular and molecular mechanisms of PAH, with an emphasis on emerging treatable pathways and optimisation of current management strategies. In considering future directions for the field, our ambition is to identify therapies with the potential to stall or reverse pulmonary vascular remodelling. We highlight novel therapeutic approaches, the important role of patients as partners in research, and innovative approaches to PAH clinical trials.

Artificial intelligence for predicting acute appendicitis: a systematic review

BACKGROUND

Paediatric appendicitis may be challenging to diagnose, and outcomes difficult to predict. While diagnostic and prognostic scores exist, artificial intelligence (AI) may be able to assist with these tasks.

METHOD

A systematic review was conducted aiming to evaluate the currently available evidence regarding the use of AI in the diagnosis and prognostication of paediatric appendicitis. In accordance with the PRISMA guidelines, the databases PubMed, EMBASE, and Cochrane Library were searched. This review was prospectively registered on PROSPERO.

RESULTS

Ten studies met inclusion criteria. All studies described the derivation and validation of AI models, and none described evaluation of the implementation of these models. Commonly used input parameters included varying combinations of demographic, clinical, laboratory, and imaging characteristics. While multiple studies used histopathological examination as the ground truth for a diagnosis of appendicitis, less robust techniques, such as the use of ICD10 codes, were also employed. Commonly used algorithms have included random forest models and artificial neural networks. High levels of model performance have been described for diagnosis of appendicitis and, to a lesser extent, subtypes of appendicitis (such as complicated versus uncomplicated appendicitis). Most studies did not provide all measures of model performance required to assess clinical usability.

CONCLUSIONS

The available evidence suggests the creation of prediction models for diagnosis and classification of appendicitis using AI techniques, is being increasingly explored. However, further implementation studies are required to demonstrate benefit in system or patient-centred outcomes with model deployment and to progress these models to the stage of clinical usability.

FHIR-PYrate: a data science friendly Python package to query FHIR servers

BACKGROUND

We present FHIR-PYrate, a Python package to handle the full clinical data collection and extraction process. The software is to be plugged into a modern hospital domain, where electronic patient records are used to handle the entire patient's history. Most research institutes follow the same procedures to build study cohorts, but mainly in a non-standardized and repetitive way. As a result, researchers spend time writing boilerplate code, which could be used for more challenging tasks.

METHODS

The package can improve and simplify existing processes in the clinical research environment. It collects all needed functionalities into a straightforward interface that can be used to query a FHIR server, download imaging studies and filter clinical documents. The full capacity of the search mechanism of the FHIR REST API is available to the user, leading to a uniform querying process for all resources, thus simplifying the customization of each use case. Additionally, valuable features like parallelization and filtering are included to make it more performant.

RESULTS

As an exemplary practical application, the package can be used to analyze the prognostic significance of routine CT imaging and clinical data in breast cancer with tumor metastases in the lungs. In this example, the initial patient cohort is first collected using ICD-10 codes. For these patients, the survival information is also gathered. Some additional clinical data is retrieved, and CT scans of the thorax are downloaded. Finally, the survival analysis can be computed using a deep learning model with the CT scans, the TNM staging and positivity of relevant markers as input. This process may vary depending on the FHIR server and available clinical data, and can be customized to cover even more use cases.

CONCLUSIONS

FHIR-PYrate opens up the possibility to quickly and easily retrieve FHIR data, download image data, and search medical documents for keywords within a Python package. With the demonstrated functionality, FHIR-PYrate opens an easy way to assemble research collectives automatically.

Development and Validation of an Electronic Health Record-Based Risk Assessment Tool for Hypoglycemia in Patients With Type 2 Diabetes Mellitus

BACKGROUND

The recent availability of high-quality data from clinical trials, together with machine learning (ML) techniques, presents exciting opportunities for developing prediction models for clinical outcomes.

METHODS

As a proof-of-concept, we translated a hypoglycemia risk model derived from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) study into the HypoHazardScore, a risk assessment tool applicable to electronic health record (EHR) data. To assess its performance, we conducted a 16-week clinical study at the University of Minnesota where participants (N = 40) with type 2 diabetes mellitus (T2DM) had hypoglycemia assessed prospectively by continuous glucose monitoring (CGM).

RESULTS

The HypoHazardScore combines 16 risk factors commonly found within the EHR. The HypoHazardScore successfully predicted (area under the curve [AUC] = 0.723) whether participants experienced least one CGM-assessed hypoglycemic event (glucose <54 mg/dL for ≥15 minutes from two CGMs) while significantly correlating with frequency of CGM-assessed hypoglycemic events (r = 0.38) and percent time experiencing CGM-assessed hypoglycemia (r = 0.39). Compared to participants with a low HypoHazardScore (N = 19, score <4, median score of 4), participants with a high HypoHazardScore (N = 21, score ≥4) had more frequent CGM-assessed hypoglycemic events (high: 1.6 ± 2.2 events/week; low: 0.3 ± 0.5 events/week) and experienced more CGM-assessed hypoglycemia (high: 1.4% ± 2.0%; low: 0.2% ± 0.4% time) during the 16-week follow-up.

CONCLUSIONS

We demonstrated that a hypoglycemia risk model can be successfully adapted from the ACCORD data to the EHR, with validation by a prospective study using CGM-assessed hypoglycemia. The HypoHazardScore represents a significant advancement toward implementing an EHR-based decision support system that can help reduce hypoglycemia in patients with T2DM.

Leveraging electronic health records to streamline the conduct of cardiovascular clinical trials

Conventional randomized controlled trials (RCTs) can be expensive, time intensive, and complex to conduct. Trial recruitment, participation, and data collection can burden participants and research personnel. In the past two decades, there have been rapid technological advances and an exponential growth in digitized healthcare data. Embedding RCTs, including cardiovascular outcome trials, into electronic health record systems or registries may streamline screening, consent, randomization, follow-up visits, and outcome adjudication. Moreover, wearable sensors (i.e. health and fitness trackers) provide an opportunity to collect data on cardiovascular health and risk factors in unprecedented detail and scale, while growing internet connectivity supports the collection of patient-reported outcomes. There is a pressing need to develop robust mechanisms that facilitate data capture from diverse databases and guidance to standardize data definitions. Importantly, the data collection infrastructure should be reusable to support multiple cardiovascular RCTs over time. Systems, processes, and policies will need to have sufficient flexibility to allow interoperability between different sources of data acquisition. Clinical research guidelines, ethics oversight, and regulatory requirements also need to evolve. This review highlights recent progress towards the use of routinely generated data to conduct RCTs and discusses potential solutions for ongoing barriers. There is a particular focus on methods to utilize routinely generated data for trials while complying with regional data protection laws. The discussion is supported with examples of cardiovascular outcome trials that have successfully leveraged the electronic health record, web-enabled devices or administrative databases to conduct randomized trials.

Clinical Trial Data Transparency in the EU: Is the New Clinical Trials Regulation a Game-Changer?

The benefits of access to clinical trial data are related to their inestimable value from the perspective of clinical trial participants, society as a whole, public health systems and scientific progress. In light of the development of innovative data analysis technologies, access to raw clinical trial data opens up an ever-widening array of possibilities: it can profoundly facilitate machine data analysis for, inter alia, hypothesis generation, risk modelling, counterfactual simulation and - finally - drug repurposing and development. The enactment of the new Clinical Trials Regulation (EU) No. 536/2014 (CTR) and introduction of the Clinical Trials Information System (CTIS) were heralded as ensuring a level of transparency in clinical trials that is sufficient to contribute to protecting public health and fostering the innovation capacity of European medical research, while recognizing the legitimate economic interests of sponsors. This paper presents the hitherto binding rules for the disclosure of clinical trial data and, against this background, their new framework, introduced by the CTR. In addition to assessing whether the CTR's objectives are fulfilled, this paper examines whether the latest changes impact the hitherto existing rules on protection of regulatory data via regulatory exclusivities. Finally, it points out concerns regarding whether data gathered in the CTIS can be efficiently used by innovative data analysis technologies for further processing for both commercial and non-commercial purposes.

The Clinical Researcher Journey in the Artificial Intelligence Era: The PAC-MAN’s Challenge

Artificial intelligence (AI) is a powerful tool that can assist researchers and clinicians in various settings. However, like any technology, it must be used with caution and awareness as there are numerous potential pitfalls. To provide a creative analogy, we have likened research to the PAC-MAN classic arcade video game. Just as the protagonist of the game is constantly seeking data, researchers are constantly seeking information that must be acquired and managed within the constraints of the research rules. In our analogy, the obstacles that researchers face are represented by “ghosts”, which symbolize major ethical concerns, low-quality data, legal issues, and educational challenges. In short, clinical researchers need to meticulously collect and analyze data from various sources, often navigating through intricate and nuanced challenges to ensure that the data they obtain are both precise and pertinent to their research inquiry. Reflecting on this analogy can foster a deeper comprehension of the significance of employing AI and other powerful technologies with heightened awareness and attentiveness.

How can machine learning and multiscale modeling benefit ocular drug development?

The eyes possess sophisticated physiological structures, diverse disease targets, limited drug delivery space, distinctive barriers, and complicated biomechanical processes, requiring a more in-depth understanding of the interactions between drug delivery systems and biological systems for ocular formulation development. However, the tiny size of the eyes makes sampling difficult and invasive studies costly and ethically constrained. Developing ocular formulations following conventional trial-and-error formulation and manufacturing process screening procedures is inefficient. Along with the popularity of computational pharmaceutics, non-invasive in silico modeling & simulation offer new opportunities for the paradigm shift of ocular formulation development. The current work first systematically reviews the theoretical underpinnings, advanced applications, and unique advantages of data-driven machine learning and multiscale simulation approaches represented by molecular simulation, mathematical modeling, and pharmacokinetic (PK)/pharmacodynamic (PD) modeling for ocular drug development. Following this, a new computer-driven framework for rational pharmaceutical formulation design is proposed, inspired by the potential of in silico explorations in understanding drug delivery details and facilitating drug formulation design. Lastly, to promote the paradigm shift, integrated in silico methodologies were highlighted, and discussions on data challenges, model practicality, personalized modeling, regulatory science, interdisciplinary collaboration, and talent training were conducted in detail with a view to achieving more efficient objective-oriented pharmaceutical formulation design.

Proteomic Applications and Considerations: From Research to Patient Care

Despite technological advancements in the field of proteomics, the rate at which serum and plasma biomarkers identified using proteomic approaches are translated into clinical use remains extremely low. In this chapter, we describe recent technological advancements and analytical strategies in proteomic methods. We also describe the progress of proteomic blood-based biomarkers to date and discuss what the future of proteomics might entail with the use of multi-omic approaches and implementing machine learning on large proteomic datasets. Lastly, we provide several key considerations for biomarker studies, ranging from sample type to the use of reference samples, in order to achieve progress from bench to bedside, ultimately improving patient diagnosis, disease, and/or therapeutic monitoring and care.

Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning

In the field of computer science, known as artificial intelligence, algorithms imitate reasoning tasks that are typically performed by humans. The techniques that allow machines to learn and get better at tasks such as recognition and prediction, which form the basis of clinical practice, are referred to as machine learning, which is a subfield of artificial intelligence. The number of artificial intelligence-and machine learnings-related publications in clinical journals has grown exponentially, driven by recent developments in computation and the accessibility of simple tools. However, clinicians are often not included in data science teams, which may limit the clinical relevance, explanability, workflow compatibility, and quality improvement of artificial intelligence solutions. Thus, this results in the language barrier between clinicians and artificial intelligence developers. Healthcare practitioners sometimes lack a basic understanding of artificial intelligence research because the approach is difficult for non-specialists to understand. Furthermore, many editors and reviewers of medical publications might not be familiar with the fundamental ideas behind these technologies, which may prevent journals from publishing high-quality artificial intelligence studies or, worse still, could allow for the publication of low-quality works. In this review, we aim to improve readers’ artificial intelligence literacy and critical thinking. As a result, we concentrated on what we consider the 10 most important qualities of artificial intelligence research: valid scientific purpose, high-quality data set, robust reference standard, robust input, no information leakage, optimal bias-variance tradeoff, proper model evaluation, proven clinical utility, transparent reporting, and open science. Before designing a study, one should have defined a sound scientific purpose. Then, it should be backed by a high-quality data set, robust input, and a solid reference standard. The artificial intelligence development pipeline should prevent information leakage. For the models, optimal bias-variance tradeoff should be achieved, and generalizability assessment must be adequately performed. The clinical value of the final models must also be established. After the study, thought should be given to transparency in publishing the process and results as well as open science for sharing data, code, and models. We hope this work may improve the artificial intelligence literacy and mindset of the readers.

Application of the program for artificial intelligence analytics of paper text and segmentation by specified parameters in clinical practice

The development of novel technologies using elements of artificial intelligence (AI) in medicine is addressed to practical clinical implementation and provision of key issues, including improvement in the use of routine clinical data, aimed at practical relevance, standardization, confidentiality and patient safety.

Aim. To evaluate the effectiveness of the RuPatient electronic heart record (EHR) system in real clinical practice for extracting and structuring medical data.

Material and methods. Extraction and recognition of data using EHR from various following sources: outpatient records, statements, routine medical reports, epicrisis and other structured and unstructured medical information based on the developed technology of intelligent text analytics, optical character recognition, for specified words and phrases, and the use of machine learning elements. A particular criterion for evaluating the effectiveness of EHR is the time spent on filling out electronic medical records compared to real clinical practice.

Results. The time of entering and processing information by the recognition system of medical documentation included in the RuPatient EHR was shorter than in standard practice (20,3±1,4 minutes, 25,1±1,5 minutes, respectively, p<0,001), the average time of recognition of documents was 30±4,3 seconds. During the ROC analysis, we determined that the threshold value that allows high accuracy to recognize images of discharge epicrisis using the RuPatient system was 83,5% with an area under the curve (AUC) value of 0,76.

Conclusions. The developed RuPatient EHR has a medical documentation recognition module for creating structured data based on AI technology elements and can be used in creating an electronic medical history and accumulation of structured data for the implementation of tasks for the practical and scientific use of big data and AI projects in medicine. When using the RuPatient system, the burden on medical staff during document management can be reduced and access to primary medical information simplified.

The next generation of evidence-based medicine

Recently, advances in wearable technologies, data science and machine learning have begun to transform evidence-based medicine, offering a tantalizing glimpse into a future of next-generation 'deep' medicine. Despite stunning advances in basic science and technology, clinical translations in major areas of medicine are lagging. While the COVID-19 pandemic exposed inherent systemic limitations of the clinical trial landscape, it also spurred some positive changes, including new trial designs and a shift toward a more patient-centric and intuitive evidence-generation system. In this Perspective, I share my heuristic vision of the future of clinical trials and evidence-based medicine.

Artificial Intelligence Applied to clinical trials: opportunities and challenges

Background

Clinical Trials (CTs) remain the foundation of safe and effective drug development. Given the evolving data-driven and personalized medicine approach in healthcare, it is imperative for companies and regulators to utilize tailored Artificial Intelligence (AI) solutions that enable expeditious and streamlined clinical research. In this paper, we identified opportunities, challenges, and potential implications of AI in CTs.

Methods

Following an extensive search in relevant databases and websites, we gathered publications tackling the use of AI and Machine Learning (ML) in CTs from the past 5 years in the US and Europe, including Regulatory Authorities' documents.

Results

Documented applications of AI commonly concern the oncology field and are mostly being applied in the area of recruitment. Main opportunities discussed aim to create efficiencies across CT activities, including the ability to reduce sample sizes, improve enrollment and conduct faster, more optimized adaptive CTs. While AI is an area of enthusiastic development, the identified challenges are ethical in nature and relate to data availability, standards, and most importantly, lack of regulatory guidance hindering the acceptance of AI tools in drug development. However, future implications are significant and are anticipated to improve the probability of success, reduce trial burden and overall, speed up research and regulatory approval.

Conclusion

The use of AI in CTs is in its relative infancy; however, it is a fast-evolving field. As regulators provide more guidance on the acceptability of AI in specific areas, we anticipate the scope of use to broaden and the volume of implementation to increase rapidly.

AI-Powered Blockchain Technology for Public Health: A Contemporary Review, Open Challenges, and Future Research Directions

Blockchain technology has been growing at a substantial growth rate over the last decade. Introduced as the backbone of cryptocurrencies such as Bitcoin, it soon found its application in other fields because of its security and privacy features. Blockchain has been used in the healthcare industry for several purposes including secure data logging, transactions, and maintenance using smart contracts. Great work has been carried out to make blockchain smart, with the integration of Artificial Intelligence (AI) to combine the best features of the two technologies. This review incorporates the conceptual and functional aspects of the individual technologies and innovations in the domains of blockchain and artificial intelligence and lays down a strong foundational understanding of the domains individually and also rigorously discusses the various ways AI has been used along with blockchain to power the healthcare industry including areas of great importance such as electronic health record (EHR) management, distant-patient monitoring and telemedicine, genomics, drug research, and testing, specialized imaging and outbreak prediction. It compiles various algorithms from supervised and unsupervised machine learning problems along with deep learning algorithms such as convolutional/recurrent neural networks and numerous platforms currently being used in AI-powered blockchain systems and discusses their applications. The review also presents the challenges still faced by these systems which they inherit from the AI and blockchain algorithms used at the core of them and the scope of future work.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Development and Validation of a Prediction Model for Need for Massive Transfusion During Surgery Using Intraoperative Hemodynamic Monitoring Data

Importance

Massive transfusion is essential to prevent complications during uncontrolled intraoperative hemorrhage. As massive transfusion requires time for blood product preparation and additional medical personnel for a team-based approach, early prediction of massive transfusion is crucial for appropriate management.

Objective

To evaluate a real-time prediction model for massive transfusion during surgery based on the incorporation of preoperative data and intraoperative hemodynamic monitoring data.

Design, Setting, and Participants

This prognostic study used data sets from patients who underwent surgery with invasive blood pressure monitoring at Seoul National University Hospital (SNUH) from 2016 to 2019 and Boramae Medical Center (BMC) from 2020 to 2021. SNUH represented the development and internal validation data sets (n = 17 986 patients), and BMC represented the external validation data sets (n = 494 patients). Data were analyzed from November 2020 to December 2021.

Exposures

A deep learning-based real-time prediction model for massive transfusion.

Main Outcomes and Measures

Massive transfusion was defined as a transfusion of 3 or more units of red blood cells over an hour. A preoperative prediction model for massive transfusion was developed using preoperative variables. Subsequently, a real-time prediction model using preoperative and intraoperative parameters was constructed to predict massive transfusion 10 minutes in advance. A prediction model, the massive transfusion index, calculated the risk of massive transfusion in real time.

Results

Among 17 986 patients at SNUH (mean [SD] age, 58.65 [14.81] years; 9036 [50.2%] female), 416 patients (2.3%) underwent massive transfusion during the operation (mean [SD] duration of operation, 170.99 [105.03] minutes). The real-time prediction model constructed with the use of preoperative and intraoperative parameters significantly outperformed the preoperative prediction model (area under the receiver characteristic curve [AUROC], 0.972; 95% CI, 0.968-0.976 vs AUROC, 0.824; 95% CI, 0.813-0.834 in the SNUH internal validation data set; P < .001). Patients with the highest massive transfusion index (ie, >90th percentile) had a 47.5-fold increased risk for a massive transfusion compared with those with a lower massive transfusion index (ie, <80th percentile). The real-time prediction model also showed excellent performance in the external validation data set (AUROC of 0.943 [95% CI, 0.919-0.961] in BMC).

Conclusions and Relevance

The findings of this prognostic study suggest that the real-time prediction model for massive transfusion showed high accuracy of prediction performance, enabling early intervention for high-risk patients. It suggests strong confidence in artificial intelligence-assisted clinical decision support systems in the operating field.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Sociodemographic and psychological characteristics influencing patients' willingness to participate in clinical trials

BACKGROUND/AIMS

Clinical trials are fundamental for the development of new medicines and patient participation is based on free consent. Our study sought to identify psychological characteristics that may influence patient willingness to participate in a clinical trial.

METHODS

A total of 100 participants were invited to participate with 80% positive response rate. The psychological characteristics of each patient were evaluated using the following validated psychometric scales: Self-Efficacy Scale, Curiosity, Exploration Inventory-Trait, Social Support Satisfaction, State-Trait Anxiety Inventory and Social Avoidance and Distress, and Fear of Negative Evaluation.

RESULTS

Patients who agreed to participate in the clinical trial were significantly younger than those who refused (p=0.028). There were no differences in sex, lifestyle, employment status, monthly income or education. After adjusting for age and sex, patients who agreed to participate scored significantly higher in the following: self-efficacy total score (p<0.001), effectiveness in adversity (p<0.001), social effectiveness (p<0.001) and initiation and persistence (p<0.001); social support total score (p<0.001), family satisfaction (p=0.015), friendship satisfaction (p<0.001), social activities satisfaction (p=0.002) and intimacy (p<0.001); total curiosity score (p<0.001), absorption (p<0.001) and exploration (p<0.001). Compared with patients who agreed to participate, those who refused scored significantly higher for both state (p<0.001) and trait anxiety (p<0.001), fear of negative evaluation (p<0.001) and social avoidance and distress (p<0.001).

CONCLUSIONS

Patients who were willing to participate in clinical trials exhibited different psychological characteristics to patients who refused. Specifically, they were more curious and self-efficacious, less anxious and reported a higher level of social support than patients who declined to participate. Identifying characteristics that condition the individual's decision to participate in a clinical trial has important implications for the development of patient-focused communication strategies and improved recruitment approaches.

A machine learning approach to characterize patients with asthma exacerbation attending an acute care setting

BACKGROUND

One of the main problems in poorly controlled asthma is the access to the Emergency Department (ED). Using a machine learning (ML) approach, the aim of our study was to identify the main predictors of severe asthma exacerbations requiring hospital admission.

METHODS

Consecutive patients with asthma exacerbation were screened for inclusion within 48 hours of ED discharge. A k-means clustering algorithm was implemented to evaluate a potential distinction of different phenotypes. K-Nearest Neighbor (KNN) as instance-based algorithm and Random Forest (RF) as tree-based algorithm were implemented in order to classify patients, based on the presence of at least one additional access to the ED in the previous 12 months.

RESULTS

To train our model, we included 260 patients (31.5% males, mean age 47.6 years). Unsupervised ML identified two groups, based on eosinophil count. A total of 86 patients with eosinophiles ≥370 cells/µL were significantly older, had a longer disease duration, more restrictions to daily activities, and lower rate of treatment compared to 174 patients with eosinophiles <370 cells/μL. In addition, they reported lower values of predicted FEV₁ (64.8±12.3% vs. 83.9±17.3%) and FEV₁/FVC (71.3±9.3 vs. 78.5±6.8), with a higher amount of exacerbations/year. In supervised ML, KNN achieved the best performance in identifying frequent exacerbators (AUROC: 96.7%), confirming the importance of spirometry parameters and eosinophil count, along with the number of prior exacerbations and other clinical and demographic variables.

CONCLUSIONS

This study confirms the key prognostic value of eosinophiles in asthma, suggesting the usefulness of ML in defining biological pathways that can help plan personalized pharmacological and rehabilitation strategies.

Bioinformatics: From NGS Data to Biological Complexity in Variant Detection and Oncological Clinical Practice

The use of next-generation sequencing (NGS) techniques for variant detection has become increasingly important in clinical research and in clinical practice in oncology. Many cancer patients are currently being treated in clinical practice or in clinical trials with drugs directed against specific genomic alterations. In this scenario, the development of reliable and reproducible bioinformatics tools is essential to derive information on the molecular characteristics of each patient’s tumor from the NGS data. The development of bioinformatics pipelines based on the use of machine learning and statistical methods is even more relevant for the determination of complex biomarkers. In this review, we describe some important technologies, computational algorithms and models that can be applied to NGS data from Whole Genome to Targeted Sequencing, to address the problem of finding complex cancer-associated biomarkers. In addition, we explore the future perspectives and challenges faced by bioinformatics for precision medicine both at a molecular and clinical level, with a focus on an emerging complex biomarker such as homologous recombination deficiency (HRD).

Scoping review of the current landscape of AI-based applications in clinical trials

Background

Clinical trials are essential for bringing new drugs, technologies and procedures to the market and clinical practice. Considering the design and the four-phase development, only 10% of them complete the entire process, partly due to the increasing costs and complexity of clinical trials. This low completion rate has a huge negative impact in terms of population health, quality of care and health economics and sustainability. Automating some of the process' tasks with artificial intelligence (AI) tools could optimize some of the most burdensome ones, like patient selection, matching and enrollment; better patient selection could also reduce harmful treatment side effects. Although the pharmaceutical industry is embracing artificial AI tools, there is little evidence in the literature of their application in clinical trials.

Methods

To address this issue, we performed a scoping review. Following the PRISMA-ScR guidelines, we performed a search on PubMed for articles on the implementation of AI in the development of clinical trials.

Results

The search yielded 772 articles, of which 15 were included. The articles were published between 2019 and 2022 and the results were presented descriptively. About half of the studies addressed the topic of patient recruitment; 12 articles reported specific examples of AI applications; five studies presented a quantitative estimate of the effectiveness of these tools.

Conclusion

All studies present encouraging results on the implementation of AI-based applications to the development of clinical trials. AI-based applications have a lot of potential, but more studies are needed to validate these tools and facilitate their adoption.

StarGazer: A Hybrid Intelligence Platform for Drug Target Prioritization and Digital Drug Repositioning Using Streamlit

Target prioritization is essential for drug discovery and repositioning. Applying computational methods to analyze and process multi-omics data to find new drug targets is a practical approach for achieving this. Despite an increasing number of methods for generating datasets such as genomics, phenomics, and proteomics, attempts to integrate and mine such datasets remain limited in scope. Developing hybrid intelligence solutions that combine human intelligence in the scientific domain and disease biology with the ability to mine multiple databases simultaneously may help augment drug target discovery and identify novel drug-indication associations. We believe that integrating different data sources using a singular numerical scoring system in a hybrid intelligent framework could help to bridge these different omics layers and facilitate rapid drug target prioritization for studies in drug discovery, development or repositioning. Herein, we describe our prototype of the StarGazer pipeline which combines multi-source, multi-omics data with a novel target prioritization scoring system in an interactive Python-based Streamlit dashboard. StarGazer displays target prioritization scores for genes associated with 1844 phenotypic traits, and is available via https://github.com/AstraZeneca/StarGazer.

A Survey on the Role of Artificial Intelligence in Biobanking Studies: A Systematic Review

Introduction: In biobanks, participants' biological samples are stored for future research. The application of artificial intelligence (AI) involves the analysis of data and the prediction of any pathological outcomes. In AI, models are used to diagnose diseases as well as classify and predict disease risks. Our research analyzed AI's role in the development of biobanks in the healthcare industry, systematically. Methods: The literature search was conducted using three digital reference databases, namely PubMed, CINAHL, and WoS. Guidelines for preferred reporting elements for systematic reviews and meta-analyses (PRISMA)-2020 in conducting the systematic review were followed. The search terms included "biobanks", "AI", "machine learning", and "deep learning", as well as combinations such as "biobanks with AI", "deep learning in the biobanking field", and "recent advances in biobanking". Only English-language papers were included in the study, and to assess the quality of selected works, the Newcastle-Ottawa scale (NOS) was used. The good quality range (NOS ≥ 7) is only considered for further review. Results: A literature analysis of the above entries resulted in 239 studies. Based on their relevance to the study's goal, research characteristics, and NOS criteria, we included 18 articles for reviewing. In the last decade, biobanks and artificial intelligence have had a relatively large impact on the medical system. Interestingly, UK biobanks account for the highest percentage of high-quality works, followed by Qatar, South Korea, Singapore, Japan, and Denmark. Conclusions: Translational bioinformatics probably represent a future leader in precision medicine. AI and machine learning applications to biobanking research may contribute to the development of biobanks for the utility of health services and citizens.

Advancing an agile regulatory ecosystem to respond to the rapid development of innovative technologies

Technological advancements are dramatically changing the landscape of therapeutic development. The convergence of advances in computing power, analytical methods, artificial intelligence, novel digital health tools, and cloud‐based platforms has the potential to power an exponential acceleration of evidence generation. For regulatory agencies responsible for evidence evaluation and oversight of medical products, these advances present both promises and challenges. Ultimately, realizing the translation and impact of these innovations that could potentially enhance therapeutic development and improve the health of individuals and the public will require a nimble and responsive regulatory approach. Supporting an adaptive policy‐making infrastructure that is poised to address novel regulatory considerations, creating a workforce to ensure relevant expertise, and fostering more diverse collaborations with a broader group of stakeholders are steps toward the goal of modernizing the regulatory ecosystem. This article outlines approaches that can help provide the flexibility and tools needed to foster innovation, while ensuring the safety and effectiveness of medical products.

Computational Models for Clinical Applications in Personalized Medicine—Guidelines and Recommendations for Data Integration and Model Validation

The future development of personalized medicine depends on a vast exchange of data from different sources, as well as harmonized integrative analysis of large-scale clinical health and sample data. Computational-modelling approaches play a key role in the analysis of the underlying molecular processes and pathways that characterize human biology, but they also lead to a more profound understanding of the mechanisms and factors that drive diseases; hence, they allow personalized treatment strategies that are guided by central clinical questions. However, despite the growing popularity of computational-modelling approaches in different stakeholder communities, there are still many hurdles to overcome for their clinical routine implementation in the future. Especially the integration of heterogeneous data from multiple sources and types are challenging tasks that require clear guidelines that also have to comply with high ethical and legal standards. Here, we discuss the most relevant computational models for personalized medicine in detail that can be considered as best-practice guidelines for application in clinical care. We define specific challenges and provide applicable guidelines and recommendations for study design, data acquisition, and operation as well as for model validation and clinical translation and other research areas.