Explainable, trustworthy, and ethical machine learning for healthcare: A survey

Development and validation of an individual weight-loss model for patients with diabetes treated with metformin

AIMS

To develop a machine learning model for predicting weight loss response to metformin in Chinese patients with type 2 diabetes.

METHODS

Data were obtained from three Chinese randomized controlled trials (RCT) screening newly diagnosed diabetes patients who received metformin monotherapy. Multiple machine learning methods, including gradient boosting regressor (GBR), were used to predict weight loss at the end of treatment based on baseline clinical characteristics and weight data collected at baseline and after up to weeks 4, 8, or 12. GBR was identified as the optimal model on the validation set according to minimum Mean Absolute Error (MAE) for subsequent analyses. Model performance on predicting categorical weight loss at 3% or 5% was measured using classification metrics, including the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

Three trials with a total of 1325 individuals with diabetes were pooled in the final analysis. We randomly selected 1126 individuals for the training and the validation group and 119 for the test group. In the test set, all AUC values exceeded 0.71 (with a maximum of 0.83). Additionally, the precision improved when weight data from the 4, 8, and 12-week time points were included in the training group. An online web-based tool was constructed based on the machine learning prediction model.

CONCLUSIONS

The developed machine learning model can be used to predict the individual weight loss responses to metformin and provide new insights for clinical practice regarding weight management in Chinese patients with diabetes.

Improving clinical decision making by creating surrogate models from health technology assessment models: A case study on Type 1 Diabetes Melitus

BACKGROUND AND OBJECTIVE

Computerized clinical decision support systems (CDSS) that incorporate the latest scientific evidence are essential for enhancing patient care quality. Such systems typically rely on some kind of model to accurately represent the knowledge required to assess the clinicians. Although the use of complex and computationally demanding simulation models is common in this field, such models limit the potential applications of CDSSs, both in real-time applications and in simulation-in-the-loop optimization tools. This paper presents a case study on Type 1 Diabetes Mellitus (T1DM) to demonstrate the development of surrogate models from health technology assessment models, with the aim of enhancing the potential of CDSSs.

METHODS

The paper details the process of developing machine learning (ML) based surrogate models, including the generation of a dataset for training and testing, and the comparison of different ML techniques. A number of distinct groupings of comorbidities were utilized in the creation of models, which were trained to predict confidence intervals for the time to develop each complication.

RESULTS

The results of the intersection over union (IoU) analysis between the simulation model output and the surrogate models output for the comorbidities under study were greater than 0.9.

CONCLUSION

The study concludes that ML-based surrogate models are a viable solution for real-time clinical decision-making, offering a substantial speedup in execution time compared to traditional simulation models.

Ethical aspects and user preferences in applying machine learning to adjust eHealth addressing substance use: A mixed-methods study

BACKGROUND

Digital health interventions targeting substance use disorders are being increasingly implemented. Data science methodology has the potential to enhance involvement and efficacy of these interventions, though application may raise ethical considerations. This study aimed to explore possible ethical aspects and preferences among users of an online digital intervention for substance use and gambling disorder regarding the application of supervised machine learning (ML) methodology.

METHODS

We recruited participants from a widely used, evidence-based online substance use and gambling intervention from the Netherlands (Jellinek Digital Self-help). Initially, we conducted two online focus groups (n = 5 each) to explore topics related to ethical considerations and user preferences regarding the application of ML for adapting unguided digital interventions. Subsequently, the findings from these focus groups informed the development of an online, quantitative, self-reported questionnaire study regarding this topic (n = 157). Data collection and analyses were guided by the principles of biomedical ethics by Beauchamp and Childress.

RESULTS

Our qualitative and quantitative results revealed that digital intervention users found the application of machine learning analyses to be ethically acceptable, although they had difficulties conceptualizing ML applications. Participants believed that it could benefit the intervention and subsequently their well-being. Both qualitative and quantitative results emphasized the importance of preserving user autonomy in applying supervised ML to adjust digital interventions. In addition, based on both data sources we found that digital intervention users trusted Jellinek's integrity to apply ML. Ethical concerns identified in the qualitative data (e.g., data security, human control), were not confirmed in our quantitative findings.

CONCLUSIONS

This mixed-methods study revealed that users of digital intervention demonstrated limited concern for ethical aspects regarding applying ML to adapt digital interventions. Ethical aspects were primarily pertained to their needs for autonomy and privacy.

Deep learning in nuclear medicine: from imaging to therapy

BACKGROUND

Deep learning, a leading technology in artificial intelligence (AI), has shown remarkable potential in revolutionizing nuclear medicine.

OBJECTIVE

This review presents recent advancements in deep learning applications, particularly in nuclear medicine imaging, lesion detection, and radiopharmaceutical therapy.

RESULTS

Leveraging various neural network architectures, deep learning has significantly enhanced the accuracy of image reconstruction, lesion segmentation, and diagnosis, improving the efficiency of disease detection and treatment planning. The integration of deep learning with functional imaging techniques such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT) enable more precise diagnostics, while facilitating the development of personalized treatment strategies. Despite its promising outlook, there are still some limitations and challenges, particularly in model interpretability, generalization across diverse datasets, multimodal data fusion, and the ethical and legal issues faced in its application.

CONCLUSION

As technological advancements continue, deep learning is poised to drive substantial changes in nuclear medicine, particularly in the areas of precision healthcare, real-time treatment monitoring, and clinical decision-making. Future research will likely focus on overcoming these challenges and further enhancing model transparency, thus improving clinical applicability.

Development and Validation of Machine Learning Models for Outcome Prediction in Patients with Poor-Grade Aneurysmal Subarachnoid Hemorrhage Following Endovascular Treatment

Background

Endovascular treatment (EVT) has been recommended as a superior modality for the treatment of intracranial aneurysm. However, there still exists a worse percentage of poor functional outcome in patients with poor-grade aneurysmal subarachnoid hemorrhage (aSAH) undergoing EVT. Therefore, it is urgently needed to investigate the risk factors and develop a critical decision model in the subtype of such patients.

Methods

We extracted the target variables from an ongoing registry cohort study, PROSAH-MPC, which was conducted in multiple centers in China. We randomly assigned these patients to training and validation cohorts with a ratio of 7:3. Univariate and multivariate logistic regressions were performed to find the potential factors, and then nine machine learning models and a stack ensemble model were developed with optimized variables. The performance of these models was evaluated through several indicators, including area under the receiver operating characteristic curve (AUC-ROC). We further use Shapley Additive Explanations (SHAP) methods for the distribution of feature visualization based on the optimal models.

Results

A total of 226 eligible patients with poor-grade aSAH undergoing EVT were enrolled, while 89 (39.4%) has a poor 12-month outcome. Age (Adjusted OR [aOR], 1.08; 95% CI: 1.03-1.13; p = 0.002), subarachnoid hemorrhage volume (aOR, 1.02; 95% CI: 1.00-1.05; p = 0.033), World Federation of Neurosurgical Societies grade (WFNS) (aOR, 2.03; 95% CI: 1.05-3.93; p = 0.035), and Hunt-Hess grade (aOR, 2.36; 95% CI: 1.13-4.93; p = 0.022) were identified as the independent risk factors of the poor outcome. Then, the prediction models developed have revealed that LightGBM algorithm has a superior performance with an AUC-ROC value of 0.842 in the validation cohort, while the SHAP results showed that age is the most important risk factor affecting functional outcomes.

Conclusion

The LightGBM model holds immense potential in facilitating risk stratification for poor-grade aSAH patients undergoing endovascular treatment who are at risk of adverse outcomes, thereby enhancing clinical decision-making processes.

Trial Registration

PROSAH-MPC. NCT05738083. Registered 16 November 2022 - Retrospectively registered, https://clinicaltrials.gov/study/NCT05738083.

Clouds on the horizon: clinical decision support systems, the control problem, and physician-patient dialogue

Artificial intelligence-based clinical decision support systems have a potential to improve clinical practice, but they may have a negative impact on the physician-patient dialogue, because of the control problem. Physician-patient dialogue depends on human qualities such as compassion, trust, and empathy, which are shared by both parties. These qualities are necessary for the parties to reach a shared understanding -the merging of horizons- about clinical decisions. The patient attends the clinical encounter not only with a malfunctioning body, but also with an 'unhomelike' experience of illness that is related to a world of values and meanings, a life-world. Making wise individual decisions in accordance with the patient's life-world requires not only scientific analysis of causal relationships, but also listening with empathy to the patient's concerns. For a decision to be made, clinical information should be interpreted considering the patient's life-world. This side of clinical practice is not a job for computers, and they cannot be final decision-makers. On the other hand, in the control problem users blindly accept system output because of over-reliance, rather than evaluating it with their own judgement. This means over-reliant parties leave their place in the dialogue to the system. In this case, the dialogue may be disrupted and mutual trust may be lost. Therefore, it is necessary to design decision support systems to avoid the control problem and to limit their use when this is not possible, in order to protect the physician-patient dialogue.

Deep Learning-Based Techniques in Glioma Brain Tumor Segmentation Using Multi-Parametric MRI: A Review on Clinical Applications and Future Outlooks

This comprehensive review explores the role of deep learning (DL) in glioma segmentation using multiparametric magnetic resonance imaging (MRI) data. The study surveys advanced techniques such as multiparametric MRI for capturing the complex nature of gliomas. It delves into the integration of DL with MRI, focusing on convolutional neural networks (CNNs) and their remarkable capabilities in tumor segmentation. Clinical applications of DL-based segmentation are highlighted, including treatment planning, monitoring treatment response, and distinguishing between tumor progression and pseudo-progression. Furthermore, the review examines the evolution of DL-based segmentation studies, from early CNN models to recent advancements such as attention mechanisms and transformer models. Challenges in data quality, gradient vanishing, and model interpretability are discussed. The review concludes with insights into future research directions, emphasizing the importance of addressing tumor heterogeneity, integrating genomic data, and ensuring responsible deployment of DL-driven healthcare technologies. EVIDENCE LEVEL: N/A TECHNICAL EFFICACY: Stage 2.

Modeling the fasting blood glucose response to basal insulin adjustment in type 2 diabetes: An explainable machine learning approach on real-world data

INTRODUCTION

Optimal basal insulin titration for people with type 2 diabetes is vital to effectively reducing the risk of complications. However, a sizeable proportion of people (30-50 %) remain in suboptimal glycemic control six months post-initiation of basal insulin. This indicates a clear need for novel titration methods that account for individual patient variability in real-world settings.

OBJECTIVE

This study aims to investigate the use of real-world data and explainable machine learning in modeling fasting glucose responses to basal insulin adjustments, focusing on identifying factors influencing fasting glucose variability.

METHODS

A three-step explanatory approach was used to develop models using multiple linear regression, forward feature selection, and three-fold cross-validation. The models were built progressively, starting with a baseline model incorporating fasting blood glucose and insulin dose adjustments, followed by iterative models that in turn included biometric data, social factors, and biochemistry data, and lastly, a comprehensive model without constraints on the feature pool.

RESULTS

The baseline model yielded an average root mean squared error (RMSE) of 1.52 [95% CI: 1.33-1.71]. The iterative models resulted in an average RMSE of 1.49 [95% CI: 1.35-1.62] (biometric data), 1.47 [95% CI: 1.36-1.58] (social factors), and 1.52 [95% CI: 1.34-1.70] (biochemistry data). The comprehensive model yielded an average RMSE of 1.44 [95% CI: 1.41-1.48].

CONCLUSION

Developing explainable machine learning models using real-world data is possible for basal insulin titration. However, model performance is influenced by data's ability to capture everyday behavior, underscoring the need for incorporating more detailed behavioral and social data to optimize future titration models.

Interpretable machine learning to evaluate relationships between DAO/DAOA (pLG72) protein data and features in clinical assessments, functional outcome, and cognitive function in schizophrenia patients

Machine learning has been proposed to utilize D-amino acid oxidase (DAO) and DAO activator (DAOA [or pLG72]) protein levels to ascertain disease status in schizophrenia. However, it remains unclear whether machine learning can effectively evaluate clinical features in relation to DAO and DAOA in schizophrenia patients. We employed an interpretable machine learning (IML) framework including linear regression, least absolute shrinkage and selection operator (Lasso) models, and generalized additive models (GAMs) to analyze DAO/DAOA levels using 380 Taiwanese schizophrenia patients. Additionally, we incorporated 27 parameters encompassing demographic variables, clinical assessments, functional outcomes, and cognitive function as features. The IML framework facilitated linear and non-linear relationships between features and DAO/DAOA. DAO levels demonstrated significant associations with the 17-item Hamilton Depression Rating Scale (HAMD17) based on linear regression. The Lasso model identified four features-HAMD17, age, working memory, and overall cognitive function (OCF)-and highlighted HAMD17 as the most significant feature, using DAO from chronically stable patients. Utilizing DAOA from acutely exacerbated patients, the Lasso model also identified four features-OCF, Scale for the Assessment of Negative Symptoms 20-item, quality of life scale (QLS), and category fluency-and emphasized OCF as the most significant feature. Furthermore, GAMs revealed a non-linear relationship between category fluency and DAO in chronically stable patients, as well as between QLS and DAOA in acutely exacerbated patients. The study suggests that an IML framework holds promise for assessing linear and non-linear relationships between DAO/DAOA and various features in clinical assessments, functional outcomes, and cognitive function in patients with schizophrenia.

An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation

Background: Early safety outcomes following transcatheter aortic valve implantation (TAVI) for severe aortic stenosis are critical for patient prognosis. Accurate prediction of adverse events can enhance patient management and improve outcomes. Aim: This study aimed to develop a machine learning model to predict early safety outcomes in patients with severe aortic stenosis undergoing TAVI. Methods: We conducted a retrospective single-centre study involving 224 patients with severe aortic stenosis who underwent TAVI. Seventy-seven clinical and biochemical variables were collected for analysis. To handle unbalanced classification problems, an adaptive synthetic (ADASYN) sampling approach was used. A fined-tuned random forest (RF) machine learning model was developed to predict early safety outcomes, defined as all-cause mortality, stroke, life-threatening bleeding, acute kidney injury (stage 2 or 3), coronary artery obstruction requiring intervention, major vascular complications, and valve-related dysfunction requiring repeat procedures. Shapley Additive Explanations (SHAPs) were used to explain the output of the machine learning model by attributing each variable's contribution to the final prediction of early safety outcomes. Results: The random forest model identified left femoral artery diameter and aortic valve calcification volume as the most influential predictors of early safety outcomes. SHAPs analysis demonstrated that smaller left femoral artery diameter and higher aortic valve calcification volume were associated with poorer early safety prognoses. Conclusions: The machine learning model highlights of early safety outcomes after TAVI. These findings suggest that incorporating these variables into pre-procedural assessments may improve risk stratification and inform clinical decision-making to enhance patient care.

Machine Learning in the Management of Patients Undergoing Catheter Ablation for Atrial Fibrillation: Scoping Review

BACKGROUND

Although catheter ablation (CA) is currently the most effective clinical treatment for atrial fibrillation, its variable therapeutic effects among different patients present numerous problems. Machine learning (ML) shows promising potential in optimizing the management and clinical outcomes of patients undergoing atrial fibrillation CA (AFCA).

OBJECTIVE

This scoping review aimed to evaluate the current scientific evidence on the application of ML for managing patients undergoing AFCA, compare the performance of various models across specific clinical tasks within AFCA, and summarize the strengths and limitations of ML in this field.

METHODS

Adhering to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, relevant studies published up to October 7, 2023, were searched from PubMed, Web of Science, Embase, the Cochrane Library, and ScienceDirect. The final included studies were confirmed based on inclusion and exclusion criteria and manual review. The PROBAST (Prediction model Risk Of Bias Assessment Tool) and QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) methodological quality assessment tools were used to review the included studies, and narrative data synthesis was performed on the modeled results provided by these studies.

RESULTS

The analysis of 23 included studies showcased the contributions of ML in identifying potential ablation targets, improving ablation strategies, and predicting patient prognosis. The patient data used in these studies comprised demographics, clinical characteristics, various types of imaging (9/23, 39%), and electrophysiological signals (7/23, 30%). In terms of model type, deep learning, represented by convolutional neural networks, was most frequently applied (14/23, 61%). Compared with traditional clinical scoring models or human clinicians, the model performance reported in the included studies was generally satisfactory, but most models (14/23, 61%) showed a high risk of bias due to lack of external validation.

CONCLUSIONS

Our evidence-based findings suggest that ML is a promising tool for improving the effectiveness and efficiency of managing patients undergoing AFCA. While guiding data preparation and model selection for future studies, this review highlights the need to address prevalent limitations, including lack of external validation, and to further explore model generalization and interpretability.

Machine learning for clinical outcome prediction in cerebrovascular and endovascular neurosurgery: systematic review and meta-analysis

BACKGROUND

Machine learning (ML) may be superior to traditional methods for clinical outcome prediction. We sought to systematically review the literature on ML for clinical outcome prediction in cerebrovascular and endovascular neurosurgery.

METHODS

A comprehensive literature search was performed, and original studies of patients undergoing cerebrovascular surgeries or endovascular procedures that developed a supervised ML model to predict a postoperative outcome or complication were included.

RESULTS

A total of 60 studies predicting 71 outcomes were included. Most cohorts were derived from single institutions (66.7%). The studies included stroke (32), subarachnoid hemorrhage ((SAH) 16), unruptured aneurysm (7), arteriovenous malformation (4), and cavernous malformation (1). Random forest was the best performing model in 12 studies (20%) followed by XGBoost (13.3%). Among 42 studies in which the ML model was compared with a standard statistical model, ML was superior in 33 (78.6%). Of 10 studies in which the ML model was compared with a non-ML clinical prediction model, ML was superior in nine (90%). External validation was performed in 10 studies (16.7%). In studies predicting functional outcome after mechanical thrombectomy the pooled area under the receiver operator characteristics curve (AUROC) of the test set performances was 0.84 (95% CI 0.79 to 0.88). For studies predicting outcomes after SAH, the pooled AUROCs for functional outcomes and delayed cerebral ischemia were 0.89 (95% CI 0.76 to 0.95) and 0.90 (95% CI 0.66 to 0.98), respectively.

CONCLUSION

ML performs favorably for clinical outcome prediction in cerebrovascular and endovascular neurosurgery. However, multicenter studies with external validation are needed to ensure the generalizability of these findings.

Local interpretable model-agnostic explanation approach for medical imaging analysis: A systematic literature review

BACKGROUND

The interpretability and explainability of machine learning (ML) and artificial intelligence systems are critical for generating trust in their outcomes in fields such as medicine and healthcare. Errors generated by these systems, such as inaccurate diagnoses or treatments, can have serious and even life-threatening effects on patients. Explainable Artificial Intelligence (XAI) is emerging as an increasingly significant area of research nowadays, focusing on the black-box aspect of sophisticated and difficult-to-interpret ML algorithms. XAI techniques such as Local Interpretable Model-Agnostic Explanations (LIME) can give explanations for these models, raising confidence in the systems and improving trust in their predictions. Numerous works have been published that respond to medical problems through the use of ML models in conjunction with XAI algorithms to give interpretability and explainability. The primary objective of the study is to evaluate the performance of the newly emerging LIME techniques within healthcare domains that require more attention in the realm of XAI research.

METHOD

A systematic search was conducted in numerous databases (Scopus, Web of Science, IEEE Xplore, ScienceDirect, MDPI, and PubMed) that identified 1614 peer-reviewed articles published between 2019 and 2023.

RESULTS

52 articles were selected for detailed analysis that showed a growing trend in the application of LIME techniques in healthcare, with significant improvements in the interpretability of ML models used for diagnostic and prognostic purposes.

CONCLUSION

The findings suggest that the integration of XAI techniques, particularly LIME, enhances the transparency and trustworthiness of AI systems in healthcare, thereby potentially improving patient outcomes and fostering greater acceptance of AI-driven solutions among medical professionals.

Trustworthiness of a machine learning early warning model in medical and surgical inpatients

Objectives

In the general hospital wards, machine learning (ML)-based early warning systems (EWSs) can identify patients at risk of deterioration to facilitate rescue interventions. We assess subpopulation performance of a ML-based EWS on medical and surgical adult patients admitted to general hospital wards.

Materials and Methods

We assessed the scores of an EWS integrated into the electronic health record and calculated every 15 minutes to predict a composite adverse event (AE): all-cause mortality, transfer to intensive care, cardiac arrest, or rapid response team evaluation. The distributions of the First Score 3 hours after admission, the Highest Score at any time during the hospitalization, and the Last Score just before an AE or dismissal without an AE were calculated. The Last Score was used to calculate the area under the receiver operating characteristic curve (ROC-AUC) and the precision-recall curve (PRC-AUC).

Results

From August 23, 2021 to March 31, 2022, 35 937 medical admissions had 2173 (6.05%) AE compared to 25 214 surgical admissions with 4984 (19.77%) AE. Medical and surgical admissions had significant different (P <.001) distributions of the First Score, Highest Score, and Last Score among those with an AE and without an AE. The model performed better in the medical group when compared to the surgical group, ROC-AUC 0.869 versus 0.677, and RPC-AUC 0.988 versus 0.878, respectively.

Discussion

Heterogeneity of medical and surgical patients can significantly impact the performance of a ML-based EWS, changing the model validity and clinical discernment.

Conclusions

Characterization of the target patient subpopulations has clinical implications and should be considered when developing models to be used in general hospital wards.

A Comprehensive Survey of Deep Learning Approaches in Image Processing

The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution from early innovations to the latest state-of-the-art developments. It also analyzes the progression of architectural designs and learning paradigms that have significantly enhanced the ability to process and interpret complex visual data. Key advancements, such as techniques improving model efficiency, generalization, and robustness, are examined, showcasing DL's ability to address increasingly sophisticated image-processing tasks across diverse domains. Metrics used for rigorous model evaluation are also discussed, underscoring the importance of performance assessment in varied application contexts. The impact of DL in image processing is highlighted through its ability to tackle complex challenges and generate actionable insights. Finally, this survey identifies potential future directions, including the integration of emerging technologies like quantum computing and neuromorphic architectures for enhanced efficiency and federated learning for privacy-preserving training. Additionally, it highlights the potential of combining DL with emerging technologies such as edge computing and explainable artificial intelligence (AI) to address scalability and interpretability challenges. These advancements are positioned to further extend the capabilities and applications of DL, driving innovation in image processing.

Artificial Intelligence in Cardiac Surgery: Transforming Outcomes and Shaping the Future

Background: Artificial intelligence (AI) has emerged as a transformative technology in healthcare, with its integration into cardiac surgery offering significant advancements in precision, efficiency, and patient outcomes. However, a comprehensive understanding of AI's applications, benefits, challenges, and future directions in cardiac surgery is needed to inform its safe and effective implementation. Methods: A systematic review was conducted following PRISMA guidelines. Literature searches were performed in PubMed, Scopus, Cochrane Library, Google Scholar, and Web of Science, covering publications from January 2000 to November 2024. Studies focusing on AI applications in cardiac surgery, including risk stratification, surgical planning, intraoperative guidance, and postoperative management, were included. Data extraction and quality assessment were conducted using standardized tools, and findings were synthesized narratively. Results: A total of 121 studies were included in this review. AI demonstrated superior predictive capabilities in risk stratification, with machine learning models outperforming traditional scoring systems in mortality and complication prediction. Robotic-assisted systems enhanced surgical precision and minimized trauma, while computer vision and augmented cognition improved intraoperative guidance. Postoperative AI applications showed potential in predicting complications, supporting patient monitoring, and reducing healthcare costs. However, challenges such as data quality, validation, ethical considerations, and integration into clinical workflows remain significant barriers to widespread adoption. Conclusions: AI has the potential to revolutionize cardiac surgery by enhancing decision making, surgical accuracy, and patient outcomes. Addressing limitations related to data quality, bias, validation, and regulatory frameworks is essential for its safe and effective implementation. Future research should focus on interdisciplinary collaboration, robust testing, and the development of ethical and transparent AI systems to ensure equitable and sustainable advancements in cardiac surgery.

Machine-learning-assisted Preoperative Prediction of Pediatric Appendicitis Severity

PURPOSE

This study evaluates the effectiveness of machine learning (ML) algorithms for improving the preoperative diagnosis of acute appendicitis in children, focusing on the accurate prediction of the severity of disease.

METHODS

An anonymized clinical and operative dataset was retrieved from the medical records of children undergoing emergency appendectomy between 2014 and 2021. We developed an ML pipeline that pre-processed the dataset and developed algorithms to predict 5 appendicitis grades (1 - non-perforated, 2 - localized perforation, 3 - abscess, 4 - generalized peritonitis, and 5 - generalized peritonitis with abscess). Imputation strategies were used for missing values and upsampling techniques for infrequent classes. Standard classifier models were tested. The best combination of imputation strategy, class balancing technique and classification model was chosen based on validation performance. Model explainability was verified by a pediatric surgeon. Our model's performance was compared to another pediatric appendicitis severity prediction tool.

RESULTS

The study used a retrospective cohort including 1980 patients (60.6 % males, average age 10.7 years). Grade of appendicitis in the cohort was as follows: grade 1-70 %; grade 2-8 %; grade 3-7 %; grade 4-7 %; grade 5-8 %. Every combination of 6 imputation strategies, 7 class-balancing techniques, and 5 classification models was tested. The best-performing combined ML pipeline distinguished non-perforated from perforated appendicitis with 82.8 ± 0.2 % NPV and 56.4 ± 0.4 % PPV, and differentiated between severity grades with 70.1 ± 0.2 % accuracy and 0.77 ± 0.00 AUROC. The other pediatric appendicitis severity prediction tool gave an accuracy of 71.4 %, AUROC of 0.54 and NPV/PPV of 71.8/64.7.

CONCLUSION

Prediction of appendiceal perforation outperforms prediction of the continuum of appendicitis grades. The variables our models primarily rely on to make predictions are consistent with clinical experience and the literature, suggesting that the ML models uncovered useful patterns in the dataset. Our model outperforms the other pediatric appendicitis prediction tools. The ML model developed for grade prediction is the first of this type, offering a novel approach for assessing appendicitis severity in children preoperatively. Following external validation and silent clinical testing, this ML model has the potential to enable personalized severity-based treatment of pediatric appendicitis and optimize resource allocation for its management.

LEVEL OF EVIDENCE: 3

Taxonomic identification of Morocco scorpions using MALDI-MS fingerprints of venom proteomes and computational modeling

The venom of scorpions has been the subject of numerous studies. However, their taxonomic identification is not a simple task, leading to misidentifications. This study aims to provide a practical approach for identifying scorpions based on the venom molecular mass fingerprint (MFP). Specimens (251) belonging to fifteen species were collected from different regions in Morocco. Their MFPs were acquired using MALDI-MS. These were used as a training dataset to generate predictive models and a library of mean spectral profiles using software programs based on machine learning. The computational model achieved an overall recognition capability of 99 % comprising 32 molecular signatures. The models and the library were tested using a new dataset for external validation and to evaluate their capability of identification. We recorded an accuracy classification with an average of 97 % and 98 % for the computational models and the library, respectively. To our knowledge, this is the first attempt to demonstrate the potential of MALDI-MS and MFPs to generate predictive models capable of discriminating scorpions from family to species levels, and to build a library of species-specific spectra. These promising results may represent a proof of concept towards developing a reliable approach for rapid molecular identification of scorpions in Morocco. SIGNIFICANCE OF THE STUDY: With their clinical importance, scorpions may constitute a desirable study model for many researchers. The first step in studying scorpion is systematically identifying the species of interest. However, it can be a difficult task, especially for the non-experts. The taxonomy of scorpions is primarily based on morphometric characters. In Morocco, the high number of species and subspecies mainly endemic, and the morphological similarities between different species may result in false identifications. This was observed in many reports according to the scorpion experts. In this study, we describe a reliable practical approach for identifying scorpions based on the venom molecular mass fingerprints (MFPs). By using two software programs based on machine learning, we have demonstrated that these MFPs contains sufficient inter-specific variation to differentiate between the scorpion species mentioned in this study with a good accuracy. Using a drop of venom, this new approach could be a rapid, accurate and cost saving method for taxonomic identification of scorpions in Morocco.

Uncertainty Quantification in Automated Detection of Vertebral Metastasis Using Ensemble Monte Carlo Dropout

The accurate and early detection of vertebral metastases is crucial for improving patient outcomes. Although deep-learning models have shown potential in this area, their lack of prediction reliability and robustness limits their clinical utility. To address these challenges, we propose a novel technique called Ensemble Monte Carlo Dropout (EMCD) for uncertainty quantification (UQ), which combines the Monte Carlo dropout and deep ensembles. In this retrospective study, we analyzed 11,468 abdominal computed tomography images from 116 patients diagnosed with vertebral metastases and 957 images from 11 healthy controls. Uncertainty was quantified and visualized using single number, predictive probability interval, posterior distribution and uncertainty class activation maps to provide a detailed understanding of prediction confidence. The EMCD model demonstrated superior performance compared with traditional UQ methods, achieving an area under the receiver operating characteristic curve (AUC) of 0.93 and an expected calibration error of 0.09, indicating high predictive accuracy and reliability. In addition, the model exhibited strong performance in handling out-of-distribution data. When data retention was applied based on uncertainty values, the AUC of the model improved to 0.96, highlighting the potential of uncertainty-driven data selection to enhance performance. The EMCD model represents a significant advancement in the automated detection of vertebral metastases, providing superior diagnostic accuracy and introducing a robust UQ framework to aid clinicians in making informed decisions.

Artificial intelligence: clinical applications and future advancement in gastrointestinal cancers

One of the foremost causes of global healthcare burden is cancer of the gastrointestinal tract. The medical records, lab results, radiographs, endoscopic images, tissue samples, and medical histories of patients with gastrointestinal malignancies provide an enormous amount of medical data. There are encouraging signs that the advent of artificial intelligence could enhance the treatment of gastrointestinal issues with this data. Deep learning algorithms can swiftly and effectively analyze unstructured, high-dimensional data, including texts, images, and waveforms, while advanced machine learning approaches could reveal new insights into disease risk factors and phenotypes. In summary, artificial intelligence has the potential to revolutionize various features of gastrointestinal cancer care, such as early detection, diagnosis, therapy, and prognosis. This paper highlights some of the many potential applications of artificial intelligence in this domain. Additionally, we discuss the present state of the discipline and its potential future developments.

Synthetic MRI in action: A novel framework in data augmentation strategies for robust multi-modal brain tumor segmentation

Brain tumor diagnostics rely heavily on Magnetic Resonance Imaging (MRI) for accurate diagnosis and treatment planning due to its non-invasive nature and detailed soft tissue visualization. Integrating multiple MRI modalities enhances diagnostic precision by providing complementary perspectives on tumor characteristics and spatial relationships. However, acquiring specific modalities like T1 Contrast Enhanced (T1CE) can be challenging, as they require contrast agents and longer scan times, which can cause discomfort, particularly in vulnerable patient groups such as the elderly, pregnant women, and infants. In the medical imaging domain, researchers face significant challenges in developing robust models due to data scarcity and data sparsity. Data scarcity, arising from limited access to diverse datasets, complex annotation processes, privacy concerns, and the difficulty of acquiring certain modalities in some patient groups, impedes the development of comprehensive brain tumor segmentation models. Data sparsity, driven by the highly imbalanced distribution between tumor subregions and background levels in annotated labels, complicates accurate segmentation. The study addresses these challenges by generating synthetic T1CE scans from T1 using an image-to-image translation framework, thereby reducing the reliance on hard-to-acquire modalities. A novel patch-based data sampling approach, Adaptive Random Patch Selection (ARPS), is introduced to combat data sparsity, ensuring detailed segmentation of intricate tumor structures while maintaining context through overlapping patches and context-aware sampling strategies. The impact of these synthetic images on segmentation performance is also assessed, emphasizing their role in addressing situations where certain modalities cannot be acquired. When integrated into the nnUNet model, this approach achieves a dice similarity coefficient (DSC) of 86.47, demonstrating its efficacy in handling complex MRI scans of brain tumors. An ablation study is also conducted to assess the individual contributions of the translated images and the proposed data sampling approach. This comprehensive evaluation allows us to understand the effectiveness of ARPS and the potential synergy between multi-modal translation and brain tumor segmentation.

Using Vital Signs for the Early Prediction of Necrotizing Enterocolitis in Preterm Neonates with Machine Learning

BACKGROUND/OBJECTIVES

Necrotizing enterocolitis (NEC), a devastating neonatal gastrointestinal disease mostly seen in preterm infants, lacks accurate prediction despite known risk factors. This hinders the possibility of applying targeted preventive therapies. This study explores the use of vital signs, including cerebral and splanchnic oxygenation, measured with near-infrared spectroscopy in early NEC prediction.

METHODS

Several machine learning algorithms were trained on data from very preterm patients (<30 weeks gestational age). Time Series FeatuRe Extraction on the basis of scalable hypothesis tests (TSFRESH) extracted significant features from the vital signs of the first 5 postnatal days. We present the F1-scores and area under the precision-recall curve (AUC-PR) of the models. The contribution of separate vital signs to the selected TSFRESH features was also determined.

RESULTS

Among 267 patients, 32 developed NEC Bell's stage > 1. Using a 1:4 NEC:control ratio, support vector machine and logistic regression predicted NEC better than extreme gradient boosting regarding the F1-score (0.82, 0.82, 0.76, resp., p = 0.001) and AUC-PR (0.82, 0.83, 0.77, resp., p < 0.001). Splanchnic and cerebral oxygenation contributed most to the prediction (40.1% and 24.8%, resp.).

CONCLUSIONS

Using vital signs, we predicted NEC in the first 5 postnatal days with an F1-score up to 0.82. Splanchnic and cerebral oxygenation were the most contributing vital predictors. This pioneering effort in early NEC prediction using vital signs underscores the potential for targeted preventive measures and also emphasizes the need for additional data in future studies.

Evolving and Novel Applications of Artificial Intelligence in Abdominal Imaging

Advancements in artificial intelligence (AI) have significantly transformed the field of abdominal radiology, leading to an improvement in diagnostic and disease management capabilities. This narrative review seeks to evaluate the current standing of AI in abdominal imaging, with a focus on recent literature contributions. This work explores the diagnosis and characterization of hepatobiliary, pancreatic, gastric, colonic, and other pathologies. In addition, the role of AI has been observed to help differentiate renal, adrenal, and splenic disorders. Furthermore, workflow optimization strategies and quantitative imaging techniques used for the measurement and characterization of tissue properties, including radiomics and deep learning, are highlighted. An assessment of how these advancements enable more precise diagnosis, tumor description, and body composition evaluation is presented, which ultimately advances the clinical effectiveness and productivity of radiology. Despite the advancements of AI in abdominal imaging, technical, ethical, and legal challenges persist, and these challenges, as well as opportunities for future development, are highlighted.

Health Risk Assessment Using Machine Learning: Systematic Review

According to the World Health Organization, chronic illnesses account for over 70% of deaths globally, underscoring the need for effective health risk assessment (HRA). While machine learning (ML) has shown potential in enhancing HRA, no systematic review has explored its application in general health risk assessments. Existing reviews typically focus on specific conditions. This paper reviews published articles that utilize ML for HRA, and it aims to identify the model development methods. A systematic review following Tranfield et al.’s three-stage approach was conducted, and it adhered to the PRISMA protocol. The literature was sourced from five databases, including PubMed. Of the included articles, 42% (11/26) addressed general health risks. Secondary data sources were most common (14/26, 53.85%), while primary data were used in eleven studies, with nine (81.81%) using data from a specific population. Random forest was the most popular algorithm, which was used in nine studies (34.62%). Notably, twelve studies implemented multiple algorithms, while seven studies incorporated model interpretability techniques. Although these studies have shown promise in addressing digital health inequities, more research is needed to include diverse sample populations, particularly from underserved communities, to enhance the generalizability of existing models. Furthermore, model interpretability should be prioritized to ensure transparent, trustworthy, and broadly applicable healthcare solutions.

From prediction to practice: mitigating bias and data shift in machine-learning models for chemotherapy-induced organ dysfunction across unseen cancers

Objectives

Routine monitoring of renal and hepatic function during chemotherapy ensures that treatment-related organ damage has not occurred and clearance of subsequent treatment is not hindered; however, frequency and timing are not optimal. Model bias and data heterogeneity concerns have hampered the ability of machine learning (ML) to be deployed into clinical practice. This study aims to develop models that could support individualised decisions on the timing of renal and hepatic monitoring while exploring the effect of data shift on model performance.

Methods and analysis

We used retrospective data from three UK hospitals to develop and validate ML models predicting unacceptable rises in creatinine/bilirubin post cycle 3 for patients undergoing treatment for the following cancers: breast, colorectal, lung, ovarian and diffuse large B-cell lymphoma.

Results

We extracted 3614 patients with no missing blood test data across cycles 1-6 of chemotherapy treatment. We improved on previous work by including predictions post cycle 3. Optimised for sensitivity, we achieve F2 scores of 0.7773 (bilirubin) and 0.6893 (creatinine) on unseen data. Performance is consistent on tumour types unseen during training (F2 bilirubin: 0.7423, F2 creatinine: 0.6820).

Conclusion

Our technique highlights the effectiveness of ML in clinical settings, demonstrating the potential to improve the delivery of care. Notably, our ML models can generalise to unseen tumour types. We propose gold-standard bias mitigation steps for ML models: evaluation on multisite data, thorough patient population analysis, and both formalised bias measures and model performance comparisons on patient subgroups. We demonstrate that data aggregation techniques have unintended consequences on model bias.

Valuing good health care: How medical doctors, scientists and patients relate ethical challenges with artificial intelligence decision-making support tools in prostate cancer diagnostics to good health care

Artificial intelligence (AI) is increasingly used in health care to improve diagnostics and treatment. Decision-making tools intended to help professionals in diagnostic processes are developed in a variety of medical fields. Despite the imagined benefits, AI in health care is contested. Scholars point to ethical and social issues related to the development, implementation, and use of AI in diagnostics. Here, we investigate how three relevant groups construct ethical challenges with AI decision-making tools in prostate cancer (PCa) diagnostics: scientists developing AI decision support tools for interpreting MRI scans for PCa, medical doctors working with PCa and PCa patients. This qualitative study is based on participant observation and interviews with the abovementioned actors. The analysis focuses on how each group draws on their understanding of 'good health care' when discussing ethical challenges, and how they mobilise different registers of valuing in this process. Our theoretical approach is inspired by scholarship on evaluation and justification. We demonstrate how ethical challenges in this area are conceptualised, weighted and negotiated among these participants as processes of valuing good health care and compare their perspectives.

Adversarial Examples on XAI-Enabled DT for Smart Healthcare Systems

There have recently been rapid developments in smart healthcare systems, such as precision diagnosis, smart diet management, and drug discovery. These systems require the integration of the Internet of Things (IoT) for data acquisition, Digital Twins (DT) for data representation into a digital replica and Artificial Intelligence (AI) for decision-making. DT is a digital copy or replica of physical entities (e.g., patients), one of the emerging technologies that enable the advancement of smart healthcare systems. AI and Machine Learning (ML) offer great benefits to DT-based smart healthcare systems. They also pose certain risks, including security risks, and bring up issues of fairness, trustworthiness, explainability, and interpretability. One of the challenges that still make the full adaptation of AI/ML in healthcare questionable is the explainability of AI (XAI) and interpretability of ML (IML). Although the study of the explainability and interpretability of AI/ML is now a trend, there is a lack of research on the security of XAI-enabled DT for smart healthcare systems. Existing studies limit their focus to either the security of XAI or DT. This paper provides a brief overview of the research on the security of XAI-enabled DT for smart healthcare systems. It also explores potential adversarial attacks against XAI-enabled DT for smart healthcare systems. Additionally, it proposes a framework for designing XAI-enabled DT for smart healthcare systems that are secure and trusted.

s2MRI-ADNet: an interpretable deep learning framework integrating Euclidean-graph representations of Alzheimer's disease solely from structural MRI

OBJECTIVE

To establish a multi-dimensional representation solely on structural MRI (sMRI) for early diagnosis of AD.

METHODS

A total of 3377 participants' sMRI from four independent databases were retrospectively identified to construct an interpretable deep learning model that integrated multi-dimensional representations of AD solely on sMRI (called s2MRI-ADNet) by a dual-channel learning strategy of gray matter volume (GMV) from Euclidean space and the regional radiomics similarity network (R2SN) from graph space. Specifically, the GMV feature map learning channel (called GMV-Channel) was to take into consideration spatial information of both long-range spatial relations and detailed localization information, while the node feature and connectivity strength learning channel (called NFCS-Channel) was to characterize the graph-structured R2SN network by a separable learning strategy.

RESULTS

The s2MRI-ADNet achieved a superior classification accuracy of 92.1% and 91.4% under intra-database and inter-database cross-validation. The GMV-Channel and NFCS-Channel captured complementary group-discriminative brain regions, revealing a complementary interpretation of the multi-dimensional representation of brain structure in Euclidean and graph spaces respectively. Besides, the generalizable and reproducible interpretation of the multi-dimensional representation in capturing complementary group-discriminative brain regions revealed a significant correlation between the four independent databases (p < 0.05). Significant associations (p < 0.05) between attention scores and brain abnormality, between classification scores and clinical measure of cognitive ability, CSF biomarker, metabolism, and genetic risk score also provided solid neurobiological interpretation.

CONCLUSION

The s2MRI-ADNet solely on sMRI could leverage the complementary multi-dimensional representations of AD in Euclidean and graph spaces, and achieved superior performance in the early diagnosis of AD, facilitating its potential in both clinical translation and popularization.

Machine learning and artificial intelligence within pediatric autoimmune diseases: applications, challenges, future perspective

INTRODUCTION

Autoimmune disorders affect 4.5% to 9.4% of children, significantly reducing their quality of life. The diagnosis and prognosis of autoimmune diseases are uncertain because of the variety of onset and development. Machine learning can identify clinically relevant patterns from vast amounts of data. Hence, its introduction has been beneficial in the diagnosis and management of patients.

AREAS COVERED

This narrative review was conducted through searching various electronic databases, including PubMed, Scopus, and Web of Science. This study thoroughly explores the current knowledge and identifies the remaining gaps in the applications of machine learning specifically in the context of pediatric autoimmune and related diseases.

EXPERT OPINION

Machine learning algorithms have the potential to completely change how pediatric autoimmune disorders are identified, treated, and managed. Machine learning can assist physicians in making more precise and fast judgments, identifying new biomarkers and therapeutic targets, and personalizing treatment strategies for each patient by utilizing massive datasets and powerful analytics.

Deep Learning for Image Analysis in the Diagnosis and Management of Esophageal Cancer

Esophageal cancer has a dismal prognosis and necessitates a multimodal and multidisciplinary approach from diagnosis to treatment. High-definition white-light endoscopy and histopathological confirmation remain the gold standard for the definitive diagnosis of premalignant and malignant lesions. Artificial intelligence using deep learning (DL) methods for image analysis constitutes a promising adjunct for the clinical endoscopist that could effectively decrease BE overdiagnosis and unnecessary surveillance, while also assisting in the timely detection of dysplastic BE and esophageal cancer. A plethora of studies published during the last five years have consistently reported highly accurate DL algorithms with comparable or superior performance compared to endoscopists. Recent efforts aim to expand DL utilization into further aspects of esophageal neoplasia management including histologic diagnosis, segmentation of gross tumor volume, pretreatment prediction and post-treatment evaluation of patient response to systemic therapy and operative guidance during minimally invasive esophagectomy. Our manuscript serves as an introduction to the growing literature of DL applications for image analysis in the management of esophageal neoplasia, concisely presenting all currently published studies. We also aim to guide the clinician across basic functional principles, evaluation metrics and limitations of DL for image recognition to facilitate the comprehension and critical evaluation of the presented studies.

Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion

Deep learning (DL) in orthopaedics has gained significant attention in recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation of osteoarthritis severity. The utilisation of DL is expected to increase, owing to its ability to present accurate diagnoses more efficiently than traditional methods in many scenarios. This reduces the time and cost of diagnosis for patients and orthopaedic surgeons. To our knowledge, no exclusive study has comprehensively reviewed all aspects of DL currently used in orthopaedic practice. This review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, and Web of Science between 2017 and 2023. The authors begin with the motivation for using DL in orthopaedics, including its ability to enhance diagnosis and treatment planning. The review then covers various applications of DL in orthopaedics, including fracture detection, detection of supraspinatus tears using MRI, osteoarthritis, prediction of types of arthroplasty implants, bone age assessment, and detection of joint-specific soft tissue disease. We also examine the challenges for implementing DL in orthopaedics, including the scarcity of data to train DL and the lack of interpretability, as well as possible solutions to these common pitfalls. Our work highlights the requirements to achieve trustworthiness in the outcomes generated by DL, including the need for accuracy, explainability, and fairness in the DL models. We pay particular attention to fusion techniques as one of the ways to increase trustworthiness, which have also been used to address the common multimodality in orthopaedics. Finally, we have reviewed the approval requirements set forth by the US Food and Drug Administration to enable the use of DL applications. As such, we aim to have this review function as a guide for researchers to develop a reliable DL application for orthopaedic tasks from scratch for use in the market.

Exploring explainable AI features in the vocal biomarkers of lung disease

This review delves into the burgeoning field of explainable artificial intelligence (XAI) in the detection and analysis of lung diseases through vocal biomarkers. Lung diseases, often elusive in their early stages, pose a significant public health challenge. Recent advancements in AI have ushered in innovative methods for early detection, yet the black-box nature of many AI models limits their clinical applicability. XAI emerges as a pivotal tool, enhancing transparency and interpretability in AI-driven diagnostics. This review synthesizes current research on the application of XAI in analyzing vocal biomarkers for lung diseases, highlighting how these techniques elucidate the connections between specific vocal features and lung pathology. We critically examine the methodologies employed, the types of lung diseases studied, and the performance of various XAI models. The potential for XAI to aid in early detection, monitor disease progression, and personalize treatment strategies in pulmonary medicine is emphasized. Furthermore, this review identifies current challenges, including data heterogeneity and model generalizability, and proposes future directions for research. By offering a comprehensive analysis of explainable AI features in the context of lung disease detection, this review aims to bridge the gap between advanced computational approaches and clinical practice, paving the way for more transparent, reliable, and effective diagnostic tools.

Prediction of neurologic outcome after out-of-hospital cardiac arrest: An interpretable approach with machine learning

Out-of-hospital cardiac arrest (OHCA) is a critical condition with low survival rates. In patients with a return of spontaneous circulation, brain injury is a leading cause of death. In this study, we propose an interpretable machine learning approach for predicting neurologic outcome after OHCA, using information available at the time of hospital admission.

METHODS

The study population were 55 615 OHCA cases registered in the Swedish Cardiopulmonary Resuscitation Registry between 2010 and 2020. The dataset was split to training and validation sets (for model development) and test set (for evaluation of the final model). We used an XGBoost algorithm with stratified, repeated 10-fold cross-validation along with Optuna framework for hyperparameters tuning. The final model was trained on 10 features selected based on the importance scores and evaluated on the test set in terms of discrimination, calibration and bias-variance tradeoff. We used SHapley Additive exPlanations to address the 'black-box' model and align with eXplainable artificial intelligence.

RESULTS

The final model achieved: area under the receiver operating characteristic value 0.964 (95% confidence interval (CI) [0.960-0.968]), sensitivity 0.606 (95% CI [0.573-0.634]), specificity 0.975 (95% CI [0.972-0.978]), positive predictive value (PPV) 0.664 (95% CI [0.625-0.696]), negative predictive value (NPV) 0.969 (95% CI [0.966-0.972]), macro F1 0.803 (95% CI [0.788-0.816]), and showed a very good calibration. SHAP features with the highest impact on the model's output were:'ROSC on arrival to hospital', 'Initial rhythm asystole' and 'Conscious on arrival to hospital'.

CONCLUSIONS

The XGBoost machine learning model with 10 features available at the time of hospital admission showed good performance for predicting neurologic outcome after OHCA, with no apparent signs of overfitting.

Prognostic enrichment for early-stage Huntington's disease: An explainable machine learning approach for clinical trial

BACKGROUND

In Huntington's disease clinical trials, recruitment and stratification approaches primarily rely on genetic load, cognitive and motor assessment scores. They focus less on in vivo brain imaging markers, which reflect neuropathology well before clinical diagnosis. Machine learning methods offer a degree of sophistication which could significantly improve prognosis and stratification by leveraging multimodal biomarkers from large datasets. Such models specifically tailored to HD gene expansion carriers could further enhance the efficacy of the stratification process.

OBJECTIVES

To improve stratification of Huntington's disease individuals for clinical trials.

METHODS

We used data from 451 gene positive individuals with Huntington's disease (both premanifest and diagnosed) from previously published cohorts (PREDICT, TRACK, TrackON, and IMAGE). We applied whole-brain parcellation to longitudinal brain scans and measured the rate of lateral ventricular enlargement, over 3 years, which was used as the target variable for our prognostic random forest regression models. The models were trained on various combinations of features at baseline, including genetic load, cognitive and motor assessment score biomarkers, as well as brain imaging-derived features. Furthermore, a simplified stratification model was developed to classify individuals into two homogenous groups (low risk and high risk) based on their anticipated rate of ventricular enlargement.

RESULTS

The predictive accuracy of the prognostic models substantially improved by integrating brain imaging features alongside genetic load, cognitive and motor biomarkers: a 24 % reduction in the cross-validated mean absolute error, yielding an error of 530 mm3/year. The stratification model had a cross-validated accuracy of 81 % in differentiating between moderate and fast progressors (precision = 83 %, recall = 80 %).

CONCLUSIONS

This study validated the effectiveness of machine learning in differentiating between low- and high-risk individuals based on the rate of ventricular enlargement. The models were exclusively trained using features from HD individuals, which offers a more disease-specific, simplified, and accurate approach for prognostic enrichment compared to relying on features extracted from healthy control groups, as done in previous studies. The proposed method has the potential to enhance clinical utility by: i) enabling more targeted recruitment of individuals for clinical trials, ii) improving post-hoc evaluation of individuals, and iii) ultimately leading to better outcomes for individuals through personalized treatment selection.

Establishing central sensitization inventory cut-off values in Dutch-speaking patients with chronic low back pain by unsupervised machine learning

BACKGROUND

Human Assumed Central Sensitization (HACS) is involved in the development and maintenance of chronic low back pain (CLBP). The Central Sensitization Inventory (CSI) was developed to evaluate the presence of HACS, with a cut-off value of 40/100. However, various factors including pain conditions (e.g., CLBP), contexts, and gender may influence this cut-off value. Unsupervised clustering approaches can address these complexities by considering diverse factors and exploring possible HACS-related subgroups. Therefore, this study aimed to determine the cut-off values for a Dutch-speaking population with CLBP based on unsupervised machine learning.

METHODS

Questionnaire data covering pain, physical, and psychological aspects were collected from patients with CLBP and aged-matched healthy controls (HC). Four clustering approaches were applied to identify HACS-related subgroups based on the questionnaire data and gender. The clustering performance was assessed using internal and external indicators. Subsequently, receiver operating characteristic (ROC) analysis was conducted on the best clustering results to determine the optimal cut-off values.

RESULTS

The study included 63 HCs and 88 patients with CLBP. Hierarchical clustering yielded the best results, identifying three clusters: healthy group, CLBP with low HACS level, and CLBP with high HACS level groups. The cut-off value for the overall groups were 35 (sensitivity 0.76, specificity 0.76).

CONCLUSION

This study found distinct patient subgroups. An overall CSI cut-off value of 35 was suggested. This study may provide new insights into identifying HACS-related patterns and contributes to establishing accurate cut-off values.

Emergence of Artificial Intelligence and Machine Learning Models in Sudden Cardiac Arrest: A Comprehensive Review of Predictive Performance and Clinical Decision Support

Sudden cardiac death/sudden cardiac arrest (SCD/SCA) is an increasingly prevalent cause of mortality globally, particularly in individuals with preexisting cardiac conditions. The ambiguous premortem warnings and the restricted interventional window related to SCD account for the complexity of the condition. Current reports suggest SCD to be accountable for 20% of all deaths hence accurately predicting SCD risk is an imminent concern. Traditional approaches for predicting SCA, particularly "track-and-trigger" warning systems have demonstrated considerable inadequacies, including low sensitivity, false alarms, decreased diagnostic liability, reliance on clinician involvement, and human errors. Artificial intelligence (AI) and machine learning (ML) models have demonstrated near-perfect accuracy in predicting SCA risk, allowing clinicians to intervene timely. Given the constraints of current diagnostics, exploring the benefits of AI and ML models in enhancing outcomes for SCA/SCD is imperative. This review article aims to investigate the efficacy of AI and ML models in predicting and managing SCD, particularly targeting accuracy in prediction.

Application of Artificial Intelligence in Healthcare: The Need for More Interpretable Artificial Intelligence

N/a.

Interpretable machine learning model integrating clinical and elastosonographic features to detect renal fibrosis in Asian patients with chronic kidney disease

BACKGROUND

Non-invasive renal fibrosis assessment is critical for tailoring personalized decision-making and managing follow-up in patients with chronic kidney disease (CKD). We aimed to exploit machine learning algorithms using clinical and elastosonographic features to distinguish moderate-severe fibrosis from mild fibrosis among CKD patients.

METHODS

A total of 162 patients with CKD who underwent shear wave elastography examinations and renal biopsies at our institution were prospectively enrolled. Four classifiers using machine learning algorithms, including eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and K-Nearest Neighbor (KNN), which integrated elastosonographic features and clinical characteristics, were established to differentiate moderate-severe renal fibrosis from mild forms. The area under the receiver operating characteristic curve (AUC) and average precision were employed to compare the performance of constructed models, and the SHapley Additive exPlanations (SHAP) strategy was used to visualize and interpret the model output.

RESULTS

The XGBoost model outperformed the other developed machine learning models, demonstrating optimal diagnostic performance in both the primary (AUC = 0.97, 95% confidence level (CI) 0.94-0.99; average precision = 0.97, 95% CI 0.97-0.98) and five-fold cross-validation (AUC = 0.85, 95% CI 0.73-0.98; average precision = 0.90, 95% CI 0.86-0.93) datasets. The SHAP approach provided visual interpretation for XGBoost, highlighting the features' impact on the diagnostic process, wherein the estimated glomerular filtration rate provided the largest contribution to the model output, followed by the elastic modulus, then renal length, renal resistive index, and hypertension.

CONCLUSION

This study proposed an XGBoost model for distinguishing moderate-severe renal fibrosis from mild forms in CKD patients, which could be used to assist clinicians in decision-making and follow-up strategies. Moreover, the SHAP algorithm makes it feasible to visualize and interpret the feature processing and diagnostic processes of the model output.

Enhancing Internet of Medical Things security with artificial intelligence: A comprehensive review

Over the past five years, interest in the literature regarding the security of the Internet of Medical Things (IoMT) has increased. Due to the enhanced interconnectedness of IoMT devices, their susceptibility to cyber-attacks has proportionally escalated. Motivated by the promising potential of AI-related technologies to improve certain cybersecurity measures, we present a comprehensive review of this emerging field. In this review, we attempt to bridge the corresponding literature gap regarding modern cybersecurity technologies that deploy AI techniques to improve their performance and compensate for security and privacy vulnerabilities. In this direction, we have systematically gathered and classified the extensive research on this topic. Our findings highlight the fact that the integration of machine learning (ML) and deep learning (DL) techniques improves both the performance of cybersecurity measures and their speed, reliability, and effectiveness. This may be proven to be useful for improving the security and privacy of IoMT devices. Furthermore, by considering the numerous advantages of AI technologies as opposed to their core cybersecurity counterparts, including blockchain, anomaly detection, homomorphic encryption, differential privacy, federated learning, and so on, we provide a structured overview of the current scientific trends. We conclude with considerations for future research, emphasizing the promising potential of AI-driven cybersecurity in the IoMT landscape, especially in patient data protection and in data-driven healthcare.

A novel intelligent model for visualized inference of medical diagnosis: A case of TCM

How to present an intelligent model based on known diagnostic knowledge to assist medical diagnosis and display the reasoning process is an interesting issue worth exploring. This study developed a novel intelligent model for visualized inference of medical diagnosis with a case of Traditional Chinese Medicine (TCM). Four classes of TCM's diagnosis composed of Yin deficiency, Liver Yin deficiency, Kidney Yin deficiency, and Liver-Kidney Yin deficiency were selected as research examples. According to the knowledge of diagnostic points in "Diagnostics of TCM", a total of 2000 samples for training and testing were randomly generated for the four classes of TCM's diagnosis. In addition, a total of 60 clinical samples were collected from hospital clinical cases. Training samples were sent to the pre-training language model of Chinese Bert for training to generate intelligent diagnostic module. Simultaneously, a mathematical algorithm was developed to generate inferential digraphs. In order to evaluate the performance of the model, the values of accuracy, F1 score, Mse, Loss and other indicators were calculated for model training and testing. And the confusion matrices and ROC curves were plotted to estimate the predictive ability of the model. The novel model was also compared with RF and XGBOOST. And some instances of inferential digraphs with the model were displayed and analyzed. It may be a new attempt to solve the problem of interpretable and inferential intelligent models in the field of artificial intelligence on medical diagnosis of TCM.

Advancing Precision Medicine: A Review of Innovative In Silico Approaches for Drug Development, Clinical Pharmacology and Personalized Healthcare

The landscape of medical treatments is undergoing a transformative shift. Precision medicine has ushered in a revolutionary era in healthcare by individualizing diagnostics and treatments according to each patient's uniquely evolving health status. This groundbreaking method of tailoring disease prevention and treatment considers individual variations in genes, environments, and lifestyles. The goal of precision medicine is to target the "five rights": the right patient, the right drug, the right time, the right dose, and the right route. In this pursuit, in silico techniques have emerged as an anchor, driving precision medicine forward and making this a realistic and promising avenue for personalized therapies. With the advancements in high-throughput DNA sequencing technologies, genomic data, including genetic variants and their interactions with each other and the environment, can be incorporated into clinical decision-making. Pharmacometrics, gathering pharmacokinetic (PK) and pharmacodynamic (PD) data, and mathematical models further contribute to drug optimization, drug behavior prediction, and drug-drug interaction identification. Digital health, wearables, and computational tools offer continuous monitoring and real-time data collection, enabling treatment adjustments. Furthermore, the incorporation of extensive datasets in computational tools, such as electronic health records (EHRs) and omics data, is also another pathway to acquire meaningful information in this field. Although they are fairly new, machine learning (ML) algorithms and artificial intelligence (AI) techniques are also resources researchers use to analyze big data and develop predictive models. This review explores the interplay of these multiple in silico approaches in advancing precision medicine and fostering individual healthcare. Despite intrinsic challenges, such as ethical considerations, data protection, and the need for more comprehensive research, this marks a new era of patient-centered healthcare. Innovative in silico techniques hold the potential to reshape the future of medicine for generations to come.

Combining simulation models and machine learning in healthcare management: strategies and applications

Simulation models and artificial intelligence (AI) are largely used to address healthcare and biomedical engineering problems. Both approaches showed promising results in the analysis and optimization of healthcare processes. Therefore, the combination of simulation models and AI could provide a strategy to further boost the quality of health services. In this work, a systematic review of studies applying a hybrid simulation models and AI approach to address healthcare management challenges was carried out. Scopus, Web of Science, and PubMed databases were screened by independent reviewers. The main strategies to combine simulation and AI as well as the major healthcare application scenarios were identified and discussed. Moreover, tools and algorithms to implement the proposed approaches were described. Results showed that machine learning appears to be the most employed AI strategy in combination with simulation models, which mainly rely on agent-based and discrete-event systems. The scarcity and heterogeneity of the included studies suggested that a standardized framework to implement hybrid machine learning-simulation approaches in healthcare management is yet to be defined. Future efforts should aim to use these approaches to design novel intelligentin-silicomodels of healthcare processes and to provide effective translation to the clinics.

Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review

BACKGROUND

Breast cancer is the most common disease in women. Recently, explainable artificial intelligence (XAI) approaches have been dedicated to investigate breast cancer. An overwhelming study has been done on XAI for breast cancer. Therefore, this study aims to review an XAI for breast cancer diagnosis from mammography and ultrasound (US) images. We investigated how XAI methods for breast cancer diagnosis have been evaluated, the existing ethical challenges, research gaps, the XAI used and the relation between the accuracy and explainability of algorithms.

METHODS

In this work, Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist and diagram were used. Peer-reviewed articles and conference proceedings from PubMed, IEEE Explore, ScienceDirect, Scopus and Google Scholar databases were searched. There is no stated date limit to filter the papers. The papers were searched on 19 September 2023, using various combinations of the search terms 'breast cancer', 'explainable', 'interpretable', 'machine learning', 'artificial intelligence' and 'XAI'. Rayyan online platform detected duplicates, inclusion and exclusion of papers.

RESULTS

This study identified 14 primary studies employing XAI for breast cancer diagnosis from mammography and US images. Out of the selected 14 studies, only 1 research evaluated humans' confidence in using the XAI system-additionally, 92.86% of identified papers identified dataset and dataset-related issues as research gaps and future direction. The result showed that further research and evaluation are needed to determine the most effective XAI method for breast cancer.

CONCLUSION

XAI is not conceded to increase users' and doctors' trust in the system. For the real-world application, effective and systematic evaluation of its trustworthiness in this scenario is lacking.

PROSPERO REGISTRATION NUMBER

CRD42023458665.

Digital healthcare framework for patients with disabilities based on deep federated learning schemes

Utilizing digital healthcare services for patients who use wheelchairs is a vital and effective means to enhance their healthcare. Digital healthcare integrates various healthcare facilities, including local laboratories and centralized hospitals, to provide healthcare services for individuals in wheelchairs. In digital healthcare, the Internet of Medical Things (IoMT) allows local wheelchairs to connect with remote digital healthcare services and generate sensors from wheelchairs to monitor and process healthcare. Recently, it has been observed that wheelchair patients, when older than thirty, suffer from high blood pressure, heart disease, body glucose, and others due to less activity because of their disabilities. However, existing wheelchair IoMT applications are straightforward and do not consider the healthcare of wheelchair patients with their diseases during their disabilities. This paper presents a novel digital healthcare framework for patients with disabilities based on deep-federated learning schemes. In the proposed framework, we offer the federated learning deep convolutional neural network schemes (FL-DCNNS) that consist of different sub-schemes. The offloading scheme collects the sensors from integrated wheelchair bio-sensors as smartwatches such as blood pressure, heartbeat, body glucose, and oxygen. The smartwatches worked with wearable devices for disabled patients in our framework. We present the federated learning-enabled laboratories for data training and share the updated weights with the data security to the centralized node for decision and prediction. We present the decision forest for centralized healthcare nodes to decide on aggregation with the different constraints: cost, energy, time, and accuracy. We implemented a deep CNN scheme in each laboratory to train and validate the model locally on the node with the consideration of resources. Simulation results show that FL-DCNNS obtained the optimal results on the sensor data and minimized the energy by 25%, time 19%, cost 28%, and improved the accuracy of disease prediction by 99% as compared to existing digital healthcare schemes for wheelchair patients.

Are the European reference networks for rare diseases ready to embrace machine learning? A mixed-methods study

BACKGROUND

The delay in diagnosis for rare disease (RD) patients is often longer than for patients with common diseases. Machine learning (ML) technologies have the potential to speed up and increase the precision of diagnosis in this population group. We aim to explore the expectations and experiences of the members of the European Reference Networks (ERNs) for RDs with those technologies and their potential for application.

METHODS

We used a mixed-methods approach with an online survey followed by a focus group discussion. Our study targeted primarily medical professionals but also other individuals affiliated with any of the 24 ERNs.

RESULTS

The online survey yielded 423 responses from ERN members. Participants reported a limited degree of knowledge of and experience with ML technologies. They considered improved diagnostic accuracy the most important potential benefit, closely followed by the synthesis of clinical information, and indicated the lack of training in these new technologies, which hinders adoption and implementation in routine care. Most respondents supported the option that ML should be an optional but recommended part of the diagnostic process for RDs. Most ERN members saw the use of ML limited to specialised units only in the next 5 years, where those technologies should be funded by public sources. Focus group discussions concluded that the potential of ML technologies is substantial and confirmed that the technologies will have an important impact on healthcare and RDs in particular. As ML technologies are not the core competency of health care professionals, participants deemed a close collaboration with developers necessary to ensure that results are valid and reliable. However, based on our results, we call for more research to understand other stakeholders' opinions and expectations, including the views of patient organisations.

CONCLUSIONS

We found enthusiasm to implement and apply ML technologies, especially diagnostic tools in the field of RDs, despite the perceived lack of experience. Early dialogue and collaboration between health care professionals, developers, industry, policymakers, and patient associations seem to be crucial to building trust, improving performance, and ultimately increasing the willingness to accept diagnostics based on ML technologies.

Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches

As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest.

Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities

In recent years, machine learning (ML) and deep learning (DL) have been the leading approaches to solving various challenges, such as disease predictions, drug discovery, medical image analysis, etc., in intelligent healthcare applications. Further, given the current progress in the fields of ML and DL, there exists the promising potential for both to provide support in the realm of healthcare. This study offered an exhaustive survey on ML and DL for the healthcare system, concentrating on vital state of the art features, integration benefits, applications, prospects and future guidelines. To conduct the research, we found the most prominent journal and conference databases using distinct keywords to discover scholarly consequences. First, we furnished the most current along with cutting-edge progress in ML-DL-based analysis in smart healthcare in a compendious manner. Next, we integrated the advancement of various services for ML and DL, including ML-healthcare, DL-healthcare, and ML-DL-healthcare. We then offered ML and DL-based applications in the healthcare industry. Eventually, we emphasized the research disputes and recommendations for further studies based on our observations.

Neurosurgery, Explainable AI, and Legal Liability

One of the challenges of AI technologies is its "black box" nature, or the lack of explainability and interpretability of these technologies. This chapter explores whether AI systems in healthcare generally, and in neurosurgery specifically, should be explainable, for what purposes, and whether the current XAI ("explainable AI") approaches and techniques are able to achieve these purposes. The chapter concludes that XAI techniques, at least currently, are not the only and not necessarily the best way to achieve trust in AI and ensure patient autonomy or improved clinical decision, and they are of limited significance in determining liability. Instead, we argue, we need more transparency around AI systems, their training and validation, as this information is likely to better achieve these goals.

Editorial Topical Collection: "Explainable and Augmented Machine Learning for Biosignals and Biomedical Images"

Machine learning (ML) is a well-known subfield of artificial intelligence (AI) that aims at developing algorithms and statistical models able to empower computer systems to automatically adapt to a specific task through experience or learning from data [...].

Machine Learning-Based Asthma Attack Prediction Models From Routinely Collected Electronic Health Records: Systematic Scoping Review

BACKGROUND

An early warning tool to predict attacks could enhance asthma management and reduce the likelihood of serious consequences. Electronic health records (EHRs) providing access to historical data about patients with asthma coupled with machine learning (ML) provide an opportunity to develop such a tool. Several studies have developed ML-based tools to predict asthma attacks.

OBJECTIVE

This study aims to critically evaluate ML-based models derived using EHRs for the prediction of asthma attacks.

METHODS

We systematically searched PubMed and Scopus (the search period was between January 1, 2012, and January 31, 2023) for papers meeting the following inclusion criteria: (1) used EHR data as the main data source, (2) used asthma attack as the outcome, and (3) compared ML-based prediction models' performance. We excluded non-English papers and nonresearch papers, such as commentary and systematic review papers. In addition, we also excluded papers that did not provide any details about the respective ML approach and its result, including protocol papers. The selected studies were then summarized across multiple dimensions including data preprocessing methods, ML algorithms, model validation, model explainability, and model implementation.

RESULTS

Overall, 17 papers were included at the end of the selection process. There was considerable heterogeneity in how asthma attacks were defined. Of the 17 studies, 8 (47%) studies used routinely collected data both from primary care and secondary care practices together. Extreme imbalanced data was a notable issue in most studies (13/17, 76%), but only 38% (5/13) of them explicitly dealt with it in their data preprocessing pipeline. The gradient boosting-based method was the best ML method in 59% (10/17) of the studies. Of the 17 studies, 14 (82%) studies used a model explanation method to identify the most important predictors. None of the studies followed the standard reporting guidelines, and none were prospectively validated.

CONCLUSIONS

Our review indicates that this research field is still underdeveloped, given the limited body of evidence, heterogeneity of methods, lack of external validation, and suboptimally reported models. We highlighted several technical challenges (class imbalance, external validation, model explanation, and adherence to reporting guidelines to aid reproducibility) that need to be addressed to make progress toward clinical adoption.