Machine learning in medicine: a practical introduction

Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data

Objective

Classification tasks are an open challenge in the field of biomedicine. While several machine-learning techniques exist to accomplish this objective, several peculiarities associated with biomedical data, especially when it comes to omics measurements, prevent their use or good performance achievements. Omics approaches aim to understand a complex biological system through systematic analysis of its content at the molecular level. On the other hand, omics data are heterogeneous, sparse and affected by the classical "curse of dimensionality" problem, i.e. having much fewer observation, samples (n) than omics features (p). Furthermore, a major problem with multi-omics data is the imbalance either at the class or feature level. The objective of this work is to study whether feature extraction and/or feature selection techniques can improve the performances of classification machine-learning algorithms on omics measurements.

Methods

Among all omics, metabolomics has emerged as a powerful tool in cancer research, facilitating a deeper understanding of the complex metabolic landscape associated with tumorigenesis and tumor progression. Thus, we selected three publicly available metabolomics datasets, and we applied several feature extraction techniques both linear and non-linear, coupled or not with feature selection methods, and evaluated the performances regarding patient classification in the different configurations for the three datasets.

Results

We provide general workflow and guidelines on when to use those techniques depending on the characteristics of the data available. To further test the extension of our approach to other omics data, we have included a transcriptomics and a proteomics data. Overall, for all datasets, we showed that applying supervised feature selection improves the performances of feature extraction methods for classification purposes. Scripts used to perform all analyses are available at: https://github.com/Plant-Net/Metabolomic_project/.

Machine learning applied to the prediction of relapse, hospitalization, and suicide in bipolar disorder using neuroimaging and clinical data: A systematic review

BACKGROUND

Bipolar disorder (BD) is associated with increased morbidity/mortality. Adverse outcome prediction might help with the management of patients with BD.

METHODS

We systematically reviewed the performance of machine learning (ML) studies in predicting adverse outcomes (relapse or recurrence, hospital admission, and suicide-related events) in patients with BD. Demographic, clinical, and neuroimaging-related poor outcome predictors were also reviewed. Three databases (PubMed, Scopus, and Web of Science) were explored from inception to July 2023.

RESULTS

Eighteen studies, accounting for >30,000 patients, were included. Support vector machine, decision trees, random forest, and logistic regression were the most frequently used ML algorithms. ML models' area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity ranged from 0.71 to 0.98, 72.7-92.8 %, and 59.0-95.2 % for relapse/recurrence prediction (4 studies (3 on relapses and 1 on recurrences). The corresponding values were 0.78-0.88, 21.4-100 %, and 77.0-99.7 % for hospital admissions (3 studies, 21,266 patients), and 0.71-0.99, 44.4-97.9 %, and 38.9-95.0 % for suicide-related events (10 studies, 5558 patients). Also, one study addressed a combination of the interest outcomes. Adverse outcome predictors included early onset BD, BD type I, comorbid psychiatric or substance use disorder, circadian rhythm disruption, hospitalization characteristics, and neuroimaging parameters, including increased dynamic amplitude of low-frequency fluctuation, decreased frontolimbic functional connectivity and aberrant dynamic functional connectivity in corticostriatal circuitry.

CONCLUSIONS

ML models can predict adverse outcomes of BD with relatively acceptable performance measures. Future studies with larger samples and nested cross-validation validation should be conducted to reach more reliable results.

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.

A risk prediction model based on machine learning algorithm for parastomal hernia after permanent colostomy

OBJECTIVE

To develop a machine learning-based risk prediction model for postoperative parastomal hernia (PSH) in colorectal cancer patients undergoing permanent colostomy, assisting nurses in identifying high-risk groups and devising preventive care strategies.

METHODS

A case-control study was conducted on 495 colorectal cancer patients who underwent permanent colostomy at the Second Affiliated Hospital of Anhui Medical University from June 2017 to June 2023, with a 1-year follow-up period. Patients were categorized into PSH and non-PSH groups based on PSH occurrence within 1-year post-operation. Data were split into training (70%) and testing (30%) sets. Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, and binary classification prediction models were established using Logistic Regression (LR), Support Vector Classification (SVC), K Nearest Neighbor (KNN), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XgBoost). The binary classification label denoted 1 for PSH occurrence and 0 for no PSH occurrence. Parameters were optimized via 5-fold cross-validation. Model performance was evaluated using Area Under Curve (AUC), specificity, sensitivity, accuracy, positive predictive value, negative predictive value, and F1-score. Clinical utility was evaluated using decision curve analysis (DCA), model explanation was enhanced using shapley additive explanation (SHAP), and model visualization was achieved using a nomogram.

RESULTS

The incidence of PSH within 1 year was 29.1% (144 patients). Among the models tested, the RF model demonstrated the highest discrimination capability with an AUC of 0.888 (95% CI: 0.881-0.935), along with superior specificity, accuracy, sensitivity, and F1 score. It also showed the highest clinical net benefit on the DCA curve. SHAP analysis identified the top 10 influential variables associated with PSH risk: body mass index (BMI), operation duration, history and status of chronic obstructive pulmonary disease (COPD), prealbumin, tumor node metastasis (TNM) staging, stoma site, thickness of rectus abdominis muscle (TRAM), C-reactive protein CRP, american society of anesthesiologists physical status classification (ASA), and stoma diameter. These insights from SHAP plots illustrated how these factors influence individual PSH outcomes. The nomogram was used for model visualization.

CONCLUSION

The Random Forest model demonstrated robust predictive performance and clinical relevance in forecasting colonic PSH. This model aids in early identification of high-risk patients and guides preventive care.

Application of the Unbalanced Ensemble Algorithm for Prognostic Prediction Outcomes of All-Cause Mortality in Coronary Heart Disease Patients Comorbid with Hypertension

Purpose

This study sought to develop an unbalanced-ensemble model that could accurately predict death outcomes of patients with comorbid coronary heart disease (CHD) and hypertension and evaluate the factors contributing to death.

Patients and Methods

Medical records of 1058 patients with coronary heart disease combined with hypertension and excluding those acute coronary syndrome were collected. Patients were followed-up at the first, third, sixth, and twelfth months after discharge to record death events. Follow-up ended two years after discharge. Patients were divided into survival and nonsurvival groups. According to medical records, gender, smoking, drinking, COPD, cerebral stroke, diabetes, hyperhomocysteinemia, heart failure and renal insufficiency of the two groups were sorted and compared and other influencing factors of the two groups, feature selection was carried out to construct models. Owing to data unbalance, we developed four unbalanced-ensemble prediction models based on Balanced Random Forest (BRF), EasyEnsemble, RUSBoost, SMOTEBoost and the two base classification algorithms based on AdaBoost and Logistic. Each model was optimised using hyperparameters based on GridSearchCV and evaluated using area under the curve (AUC), sensitivity, recall, Brier score, and geometric mean (G-mean). Additionally, to understand the influence of variables on model performance, we constructed a SHapley Additive explanation (SHAP) model based on the optimal model.

Results

There were significant differences in age, heart rate, COPD, cerebral stroke, heart failure and renal insufficiency in the nonsurvival group compared with the survival group. Among all models, BRF yielded the highest AUC (0.810; 95% CI, 0.778-0.839), sensitivity (0.990; 95% CI, 0.981-1.000), recall (0.990; 95% CI, 0.981-1.000), and G-mean (0.806; 95% CI, 0.778-0.827), and the lowest Brier score (0.181; 95% CI, 0.178-0.185). Therefore, we identified BRF as the optimal model. Furthermore, red blood cell count (RBC), body mass index (BMI), and lactate dehydrogenase were found to be important mortality-associated risk factors.

Conclusion

BRF combined with advanced machine learning methods and SHAP is highly effective and accurately predicts mortality in patients with CHD comorbid with hypertension. This model has the potential to assist clinicians in modifying treatment strategies to improve patient outcomes.

From data to decisions: AI and functional connectivity for diagnosis, prognosis, and recovery prediction in stroke

Stroke is a severe medical condition which may lead to permanent disability conditions. The initial 8 weeks following a stroke are crucial for rehabilitation, as most recovery occurs during this period. Personalized approaches and predictive biomarkers are needed for tailored rehabilitation. In this context, EEG brain connectivity and Artificial Intelligence (AI) can play a crucial role in diagnosing and predicting stroke outcomes efficiently. In the present study, 127 patients with subacute ischemic lesions and 90 age- and gender-matched healthy controls were enrolled. EEG recordings were obtained from each participant within 15 days of stroke onset. Clinical evaluations were performed at baseline and at 40-days follow-up using the National Institutes of Health Stroke Scale (NIHSS). Functional connectivity analysis was conducted using Total Coherence (TotCoh) and Small Word (SW). Quadratic support vector machines (SVM) algorithms were implemented to classify healthy subjects compared to stroke patients (Healthy vs Stroke), determine the affected hemisphere (Left vs Right Hemisphere), and predict functional recovery (Functional Recovery Prediction). In the classification for Functional Recovery Prediction, an accuracy of 94.75%, sensitivity of 96.27% specificity of 92.33%, and AUC of 0.95 were achieved; for Healthy vs Stroke, an accuracy of 99.09%, sensitivity of 100%, specificity of 98.46%, and AUC of 0.99 were achieved. For Left vs Right Hemisphere classification, accuracy was 86.77%, sensitivity was 91.44%, specificity was 80.33%, and AUC was 0.87. These findings highlight the potential of utilizing functional connectivity measures based on EEG in combination with AI algorithms to improve patient outcomes by targeted rehabilitation interventions.

Discrimination of multiple sclerosis using scanning laser ophthalmoscopy images with autoencoder-based feature extraction

OBJECTIVE

Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.

METHODS

We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).

RESULTS

The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).

CONCLUSIONS

We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice.

Artificial intelligence and headache

BACKGROUND AND METHODS

In this narrative review, we introduce key artificial intelligence (AI) and machine learning (ML) concepts, aimed at headache clinicians and researchers. Thereafter, we thoroughly review the use of AI in headache, based on a comprehensive literature search across PubMed, Embase and IEEExplore. Finally, we discuss limitations, as well as ethical and political perspectives.

RESULTS

We identified six main research topics. First, natural language processing can be used to effectively extract and systematize unstructured headache research data, such as from electronic health records. Second, the most common application of ML is for classification of headache disorders, typically based on clinical record data, or neuroimaging data, with accuracies ranging from around 60% to well over 90%. Third, ML is used for prediction of headache disease trajectories. Fourth, ML shows promise in forecasting of headaches using self-reported data such as triggers and premonitory symptoms, data from wearable sensors and external data. Fifth and sixth, ML can be used for prediction of treatment responses and inference of treatment effects, respectively, aiming to optimize and individualize headache management.

CONCLUSIONS

The potential uses of AI and ML in headache are broad, but, at present, many studies suffer from poor reporting and lack out-of-sample evaluation, and most models are not validated in a clinical setting.

Machine learning for antidepressant treatment selection in depression

Finding the right antidepressant for the individual patient with major depressive disorder can be a difficult endeavor and is mostly based on trial-and-error. Machine learning (ML) is a promising tool to personalize antidepressant prescription. In this review, we summarize the current evidence of ML in the selection of antidepressants and conclude that its value for clinical practice is still limited. Apart from the current focus on effectiveness, several other factors should be taken into account to make ML-based prediction models useful for clinical application.

Machine Learning for Predicting Stillbirth: A Systematic Review

Stillbirth is a major global issue, with over 5 million cases each year. The multifactorial nature of stillbirth makes it difficult to predict. Artificial intelligence (AI) and machine learning (ML) have the potential to enhance clinical decision-making and enable precise assessments. This study reviewed the literature on predictive ML models for stillbirth highlighting input characteristics, performance metrics, and validation. The PubMed, Cochrane, and Web of Science databases were searched for studies using AI to develop predictive models for stillbirth. Findings were analyzed qualitatively using narrative synthesis and graphics. Risk of bias and the applicability of the studies were assessed using PROBAST. Model design and performance were discussed. Eight studies involving 14,840,654 women with gestational ages ranging from 20 weeks to full term were included in the qualitative analysis. Most studies used neural networks, random forests, and logistic regression algorithms. The number of predictive features varied from 14 to 53. Only 50% of studies validated the models. Cross-validation was commonly employed, and only 25% of studies performed external validation. All studies reported area under the curve as a performance metric (range 0.54-0.9), and five studies reported sensitivity (range, 60- 90%) and specificity (range, 64 - 93.3%). A stacked ensemble model that analyzed 53 features performed better than other models (AUC = 0.9; sensitivity and specificity > 85%). Available ML models can attain a considerable degree of accuracy for prediction of stillbirth; however, these models require further development before they can be applied in a clinical setting.

Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions

In recent years, there has been explosive development in artificial intelligence (AI), which has been widely applied in the health care field. As a typical AI technology, machine learning models have emerged with great potential in predicting cardiovascular diseases by leveraging large amounts of medical data for training and optimization, which are expected to play a crucial role in reducing the incidence and mortality rates of cardiovascular diseases. Although the field has become a research hot spot, there are still many pitfalls that researchers need to pay close attention to. These pitfalls may affect the predictive performance, credibility, reliability, and reproducibility of the studied models, ultimately reducing the value of the research and affecting the prospects for clinical application. Therefore, identifying and avoiding these pitfalls is a crucial task before implementing the research. However, there is currently a lack of a comprehensive summary on this topic. This viewpoint aims to analyze the existing problems in terms of data quality, data set characteristics, model design, and statistical methods, as well as clinical implications, and provide possible solutions to these problems, such as gathering objective data, improving training, repeating measurements, increasing sample size, preventing overfitting using statistical methods, using specific AI algorithms to address targeted issues, standardizing outcomes and evaluation criteria, and enhancing fairness and replicability, with the goal of offering reference and assistance to researchers, algorithm developers, policy makers, and clinical practitioners.

The hospital emigration to another region in the light of the environmental, social and governance model in Italy during the period 2004-2021

The following article presents an analysis of the impact of the Environmental, Social and Governance-ESG determinants on Hospital Emigration to Another Region-HEAR in the Italian regions in the period 2004-2021. The data are analysed using Panel Data with Random Effects, Panel Data with Fixed Effects, Pooled Ordinary Least Squares-OLS, Weighted Least Squares-WLS, and Dynamic Panel at 1 Stage. Furthermore, to control endogeneity we also created instrumental variable models for each component of the ESG model. Results show that HEAR is negatively associated to the E, S and G component within the ESG model. The data were subjected to clustering with a k-Means algorithm optimized with the Silhouette coefficient. The optimal clustering with k=2 is compared to the sub-optimal cluster with k=3. The results suggest a negative relationship between the resident population and hospital emigration at regional level. Finally, a prediction is proposed with machine learning algorithms classified based on statistical performance. The results show that the Artificial Neural Network-ANN algorithm is the best predictor. The ANN predictions are critically analyzed in light of health economic policy directions.

Prognostic significance of exportin-5 in hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related deaths worldwide. As liver cancer often presents no noticeable symptoms in its early stages, most patients are diagnosed at an advanced stage, complicating treatment. Therefore, the identification of new biomarkers is crucial for the early detection and treatment of HCC. Research on exportin-5 (XPO5) could offer new avenues for early diagnosis and improve treatment strategies.

AIM

To explore the role of XPO5 in HCC progression and its potential as a prognostic biomarker.

METHODS

This study assessed XPO5 mRNA expression in HCC using The Cancer Genome Atlas, TIMER, and International Cancer Genome Consortium databases, correlating it with clinical profiles and disease progression. We performed in vitro experiments to examine the effect of XPO5 on liver cell growth. Gene Set Enrichment Analysis, Kyoto Encyclopedia of Genes and Genomes, and Gene Ontology were used to elucidate the biological roles and signaling pathways. We also evaluated XPO5's impact on immune cell infiltration and validated its prognostic potential using machine learning.

RESULTS

XPO5 was significantly upregulated in HCC tissues, correlating with tumor grade, T-stage, and overall survival, indicating poor prognosis. Enrichment analyses linked high XPO5 expression with tumor immunity, particularly CD4 T cell memory activation and macrophage M0 infiltration. Drug sensitivity tests identified potential therapeutic agents such as MG-132, paclitaxel, and WH-4-023. Overexpression of XPO5 in HCC cells, compared to normal liver cells, was confirmed by western blotting and quantitative real-time polymerase chain reaction. The lentiviral transduction-mediated knockdown of XPO5 significantly reduced cell proliferation and metastasis. Among the various machine learning algorithms, the C5.0 decision tree algorithm achieved accuracy rates of 95.5% in the training set and 92.0% in the validation set.

CONCLUSION

Our analysis shows that XPO5 expression is a reliable prognostic indicator for patients with HCC and is significantly associated with immune cell infiltration.

Role of artificial intelligence, machine learning and deep learning models in corneal disorders - A narrative review

In the last decade, artificial intelligence (AI) has significantly impacted ophthalmology, particularly in managing corneal diseases, a major reversible cause of blindness. This review explores AI's transformative role in the corneal subspecialty, which has adopted advanced technology for superior clinical judgment, early diagnosis, and personalized therapy. While AI's role in anterior segment diseases is less documented compared to glaucoma and retinal pathologies, this review highlights its integration into corneal diagnostics through imaging techniques like slit-lamp biomicroscopy, anterior segment optical coherence tomography (AS-OCT), and in vivo confocal biomicroscopy. AI has been pivotal in refining decision-making and prognosis for conditions such as keratoconus, infectious keratitis, and dystrophies. Multi-disease deep learning neural networks (MDDNs) have shown diagnostic ability in classifying corneal diseases using AS-OCT images, achieving notable metrics like an AUC of 0.910. AI's progress over two decades has significantly improved the accuracy of diagnosing conditions like keratoconus and microbial keratitis. For instance, AI has achieved a 90.7% accuracy rate in classifying bacterial and fungal keratitis and an AUC of 0.910 in differentiating various corneal diseases. Convolutional neural networks (CNNs) have enhanced the analysis of color-coded corneal maps, yielding up to 99.3% diagnostic accuracy for keratoconus. Deep learning algorithms have also shown robust performance in detecting fungal hyphae on in vivo confocal microscopy, with precise quantification of hyphal density. AI models combining tomography scans and visual acuity have demonstrated up to 97% accuracy in keratoconus staging according to the Amsler-Krumeich classification. However, the review acknowledges the limitations of current AI models, including their reliance on binary classification, which may not capture the complexity of real-world clinical presentations with multiple coexisting disorders. Challenges also include dependency on data quality, diverse imaging protocols, and integrating multimodal images for a generalized AI diagnosis. The need for interpretability in AI models is emphasized to foster trust and applicability in clinical settings. Looking ahead, AI has the potential to unravel the intricate mechanisms behind corneal pathologies, reduce healthcare's carbon footprint, and revolutionize diagnostic and management paradigms. Ethical and regulatory considerations will accompany AI's clinical adoption, marking an era where AI not only assists but augments ophthalmic care.

Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method?

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is associated with poor clinical outcomes and remains under-monitored. Automated PVA detection would enable complete monitoring standard observational methods do not allow. While model-based and machine learning PVA approaches exist, they have variable performance and can miss specific PVA events. This study compares a model and rule-based algorithm with a machine learning PVA method by retrospectively validating both methods using an independent patient cohort.

METHODS

Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison.

RESULTS

Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN.

CONCLUSION

The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.

Longitudinal Risk Analysis of Second Primary Cancer after Curative Treatment in Patients with Rectal Cancer

Predicting and improving the response of rectal cancer to second primary cancers (SPCs) remains an active and challenging field of clinical research. Identifying predictive risk factors for SPCs will help guide more personalized treatment strategies. In this study, we propose that experience data be used as evidence to support patient-oriented decision-making. The proposed model consists of two main components: a pipeline for extraction and classification and a clinical risk assessment. The study includes 4402 patient datasets, including 395 SPC patients, collected from three cancer registry databases at three medical centers; based on literature reviews and discussion with clinical experts, 10 predictive variables were considered risk factors for SPCs. The proposed extraction and classification pipelines that classified patients according to importance were age at diagnosis, chemotherapy, smoking behavior, combined stage group, and sex, as has been proven in previous studies. The C5 method had the highest predicted AUC (84.88%). In addition, the proposed model was associated with a classification pipeline that showed an acceptable testing accuracy of 80.85%, a recall of 79.97%, a specificity of 88.12%, a precision of 85.79%, and an F1 score of 79.88%. Our results indicate that chemotherapy is the most important prognostic risk factor for SPCs in rectal cancer survivors. Furthermore, our decision tree for clinical risk assessment illuminates the possibility of assessing the effectiveness of a combination of these risk factors. This proposed model may provide an essential evaluation and longitudinal change for personalized treatment of rectal cancer survivors in the future.

Advances in methods for characterizing dietary patterns: A scoping review

There is a growing focus on better understanding the complexity of dietary patterns and how they relate to health and other factors. Approaches that have not traditionally been applied to characterize dietary patterns, such as machine learning algorithms and latent class analysis methods, may offer opportunities to measure and characterize dietary patterns in greater depth than previously considered. However, there has not been a formal examination of how this wide range of approaches has been applied to characterize dietary patterns. This scoping review synthesized literature from 2005-2022 applying methods not traditionally used to characterize dietary patterns, referred to as novel methods. MEDLINE, CINAHL, and Scopus were searched using keywords including machine learning, latent class analysis, and least absolute shrinkage and selection operator (LASSO). Of 5274 records identified, 24 met the inclusion criteria. Twelve of 24 articles were published since 2020. Studies were conducted across 17 countries. Nine studies used approaches that have applications in machine learning to identify dietary patterns. Fourteen studies assessed associations between dietary patterns that were characterized using novel methods and health outcomes, including cancer, cardiovascular disease, and asthma. There was wide variation in the methods applied to characterize dietary patterns and in how these methods were described. The extension of reporting guidelines and quality appraisal tools relevant to nutrition research to consider specific features of novel methods may facilitate complete and consistent reporting and enable evidence synthesis to inform policies and programs aimed at supporting healthy dietary patterns.

Rapid detection of lung cancer based on serum Raman spectroscopy and a support vector machine: a case-control study

BACKGROUND

Early screening and detection of lung cancer is essential for the diagnosis and prognosis of the disease. In this paper, we investigated the feasibility of serum Raman spectroscopy for rapid lung cancer screening.

METHODS

Raman spectra were collected from 45 patients with lung cancer, 45 with benign lung lesions, and 45 healthy volunteers. And then the support vector machine (SVM) algorithm was applied to build a diagnostic model for lung cancer. Furthermore, 15 independent individuals were sampled for external validation, including 5 lung cancer patients, 5 benign lung lesion patients, and 5 healthy controls.

RESULTS

The diagnostic sensitivity, specificity, and accuracy were 91.67%, 92.22%, 90.56% (lung cancer vs. healthy control), 92.22%,95.56%,93.33% (benign lung lesion vs. healthy) and 80.00%, 83.33%, 80.83% (lung cancer vs. benign lung lesion), repectively. In the independent validation cohort, our model showed that all the samples were classified correctly.

CONCLUSION

Therefore, this study demonstrates that the serum Raman spectroscopy analysis technique combined with the SVM algorithm has great potential for the noninvasive detection of lung cancer.

Artificial intelligence and machine learning in axial spondyloarthritis

PURPOSE OF REVIEW

To evaluate the current applications and prospects of artificial intelligence and machine learning in diagnosing and managing axial spondyloarthritis (axSpA), focusing on their role in medical imaging, predictive modelling, and patient monitoring.

RECENT FINDINGS

Artificial intelligence, particularly deep learning, is showing promise in diagnosing axSpA assisting with X-ray, computed tomography (CT) and MRI analyses, with some models matching or outperforming radiologists in detecting sacroiliitis and markers. Moreover, it is increasingly being used in predictive modelling of disease progression and personalized treatment, and could aid risk assessment, treatment response and clinical subtype identification. Variable study designs, sample sizes and the predominance of retrospective, single-centre studies still limit the generalizability of results.

SUMMARY

Artificial intelligence technologies have significant potential to advance the diagnosis and treatment of axSpA, providing more accurate, efficient and personalized healthcare solutions. However, their integration into clinical practice requires rigorous validation, ethical and legal considerations, and comprehensive training for healthcare professionals. Future advances in artificial intelligence could complement clinical expertise and improve patient care through improved diagnostic accuracy and tailored therapeutic strategies, but the challenge remains to ensure that these technologies are validated in prospective multicentre trials and ethically integrated into patient care.

Clinical prediction models in children that use repeated measurements with time-varying covariates: a scoping review

BACKGROUND

Emerging evidence suggests that clinical prediction models that use repeated (time-varying) measurements within each patient may have higher predictive accuracy than models that use patient information from a single measurement.

OBJECTIVE

To determine the breadth of the published literature reporting the development of clinical prediction models in children that use time-varying predictors.

DATA SOURCES

MEDLINE, EMBASE and Cochrane databases.

ELIGIBILITY CRITERIA

We included studies reporting the development of a multivariable clinical prediction model in children, with or without validation, to predict a repeatedly measured binary or time-to-event outcome and utilizing at least one repeatedly measured predictor.

SYNTHESIS METHODS

We categorized included studies by the method used to model time-varying predictors.

RESULTS

Of 99 clinical prediction model studies that had a repeated measurements data structure, only 27 (27%) used methods that incorporated the repeated measurements as time-varying predictors in a single model. Among these 27 time-varying prediction model studies, we grouped model types into nine categories: time-dependent Cox regression, generalized estimating equations, random effects model, landmark model, joint model, neural network, K-nearest neighbor, support vector machine and tree-based algorithms. Where there was comparison of time-varying models to single measurement models, using time-varying predictors improved predictive accuracy.

CONCLUSIONS

Various methods have been used to develop time-varying prediction models in children, but there is a paucity of pediatric time-varying models in the literature. Incorporating time-varying covariates in pediatric prediction models may improve predictive accuracy. Future research in pediatric prediction model development should further investigate whether incorporation of time-varying covariates improves predictive accuracy.

Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring

Aim: The aim of this study was to develop and validate a prediction model based on continuous glucose monitoring (CGM) data to identify a week-to-week risk profile of excessive hypoglycemia. Methods: We analyzed, trained, and internally tested two prediction models using CGM data from 205 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach (XGBoost) combined with feature engineering deployed on the CGM signals was utilized to predict excessive hypoglycemia risk defined by two targets (time below range [TBR] >4% and the upper TBR 90th percentile limit) of TBR the following week. The models were validated in two independent cohorts with a total of 253 additional patients. Results: A total of 61,470 weeks of CGM data were included in the analysis. The XGBoost models had an area under the receiver operating characteristic curve (ROC-AUC) of 0.83-0.87 (95% confidence interval; 0.83-0.88) in the test dataset. The external validation showed ROC-AUCs of 0.81-0.90. The most discriminative features included the low blood glucose index, the glycemic risk assessment diabetes equation (GRADE), hypoglycemia, the TBR, waveform length, the coefficient of variation and mean glucose during the previous week. This highlights that the pattern of hypoglycemia combined with glucose variability during the past week contains information on the risk of future hypoglycemia. Conclusion: Prediction models based on real-world CGM data can be used to predict the risk of hypoglycemia in the forthcoming week. The models showed good performance in both the internal and external validation cohorts.

Establishment of prediction model for mortality risk of pancreatic cancer: a retrospective study

BACKGROUND AND AIM

Pancreatic cancer possesses a high prevalence and mortality rate among other cancers. Despite the low survival rate of this cancer type, the early prediction of this disease has a crucial role in decreasing the mortality rate and improving the prognosis. So, this study.

MATERIALS AND METHODS

In this retrospective study, we used 654 alive and dead PC cases to establish the prediction model for PC. The six chosen machine learning algorithms and prognostic factors were utilized to build the prediction models. The importance of the predictive factors was assessed using the relative importance of a high-performing algorithm.

RESULTS

The XG-Boost with AU-ROC of 0.933 (95% CI= [0.906-0.958]) and AU-ROC of 0.836 (95% CI= [0.789-0.865] in internal and external validation modes were considered as the best-performing model for predicting the mortality risk of PC. The factors, including tumor size, smoking, and chemotherapy, were considered the most influential for prediction.

CONCLUSION

The XG-Boost gained more performance efficiency in predicting the mortality risk of PC patients, so this model can promote the clinical solutions that doctors can achieve in healthcare environments to decrease the mortality risk of these patients.

A machine learning model to predict spontaneous vaginal delivery failure for term nulliparous women: An observational study

OBJECTIVE

This study aims to construct and evaluate a model to predict spontaneous vaginal delivery (SVD) failure in term nulliparous women based on machine learning algorithms.

METHODS

In this retrospective observational study, data on nulliparous women without contraindications for vaginal delivery with a singleton pregnancy ≥37 weeks and before the onset of labor from September 2020 to September 2021 were divided into a training set and a temporal validation set. Transperineal ultrasound was performed to collect angle of progression, head-perineum distance, subpubic arch angle, and their levator hiatal dimensions. The cervical length was measured via transvaginal ultrasound. The delivery methods were later recorded. Through LASSO regression analysis, indicators that can affect SVD failure were selected. Seven common machine learning algorithms were selected for model training, and the optimal algorithm was selected based on the area under the curve (AUC) to evaluate the effectiveness of the validation model.

RESULTS

Four indicators related to SVD failure were identified through LASSO regression screening: angle of progression, cervical length, subpubic arch angle, and estimated fetal weight. The Gaussian NB algorithm was found to yield the highest AUC (0.82, 95% confidence interval [CI] 0.65-0.98) during model training, and hence it was chosen for verification with the temporal validation set, in which an AUC of 0.79 (95% CI 0.64-0.95) was obtained with accuracy, sensitivity, and specificity rates of 80.9%, 72.7%, and 75.0%, respectively.

CONCLUSION

The Gaussian NB model showed good predictive effect, proving its potential as a clinical reference for predicting SVD failure of term nulliparous women before actual delivery.

Machine Learning-Based Models for Advanced Fibrosis and Cirrhosis Diagnosis in Chronic Hepatitis B Patients With Hepatic Steatosis

BACKGROUND AND AIMS

The global rise of chronic hepatitis B (CHB) superimposed on hepatic steatosis (HS) warrants noninvasive, precise tools for assessing fibrosis progression. This study leveraged machine learning (ML) to develop diagnostic models for advanced fibrosis and cirrhosis in this patient population.

METHODS

Treatment-naive CHB patients with concurrent HS who underwent liver biopsy in 10 medical centers were enrolled as a training cohort and an independent external validation cohort (NCT05766449). Six ML models were implemented to predict advanced fibrosis and cirrhosis. The final models, derived from SHAP (Shapley Additive exPlanations), were compared with Fibrosis-4 Index, nonalcoholic fatty liver disease Fibrosis Score, and aspartate aminotransferase-to-platelet ratio index using the area under receiver-operating characteristic curve (AUROC) and decision curve analysis (DCA).

RESULTS

Of 1,198 eligible patients, the random forest model achieved AUROCs of 0.778 (95% confidence interval [CI], 0.749-0.807) for diagnosing advanced fibrosis (random forest advanced fibrosis model) and 0.777 (95% CI, 0.748-0.806) for diagnosing cirrhosis (random forest cirrhosis model) in the training cohort, and maintained high AUROCs in the validation cohort. In the training cohort, the random forest advanced fibrosis model obtained an AUROC of 0.825 (95% CI, 0.787-0.862) in patients with hepatitis B virus DNA ≥105 IU/mL, and the random forest cirrhosis model had an AUROC of 0.828 (95% CI, 0.774-0.883) in female patients. The 2 models outperformed Fibrosis-4 Index, nonalcoholic fatty liver disease Fibrosis Score, and aspartate aminotransferase-to-platelet ratio index in the training cohort, and also performed well in the validation cohort.

CONCLUSIONS

The random forest models provide reliable, noninvasive tools for identifying advanced fibrosis and cirrhosis in CHB patients with concurrent HS, offering a significant advancement in the comanagement of the 2 diseases.

CLINICALTRIALS

gov, Number: NCT05766449.

Development and validation of a machine learning-based readmission risk prediction model for non-ST elevation myocardial infarction patients after percutaneous coronary intervention

To investigate the factors that influence readmissions in patients with acute non-ST elevation myocardial infarction (NSTEMI) after percutaneous coronary intervention (PCI) by using multiple machine learning (ML) methods to establish a predictive model. In this study, 1576 NSTEMI patients who were hospitalized at the Affiliated Hospital of North Sichuan Medical College were selected as the research subjects. They were divided into two groups: the readmitted group and the non-readmitted group. The division was based on whether the patients experienced complications or another incident of myocardial infarction within one year after undergoing PCI. Common variables selected by univariate and multivariate logistic regression, LASSO regression, and random forest were used as independent influencing factors for NSTEMI patients' readmissions after PCI. Six different ML models were constructed using these common variables. The area under the ROC curve, accuracy, sensitivity, and specificity were used to evaluate the performance of the six ML models. Finally, the optimal model was selected, and a nomogram was created to visually represent its clinical effectiveness. Three different methods were used to select seven representative common variables. These variables were then utilized to construct six different ML models, which were subsequently compared. The findings indicated that the LR model exhibited the most optimal performance in terms of AUC, accuracy, sensitivity, and specificity. The outcome, admission mode (walking and non-walking), communication ability, CRP, TC, HDL, and LDL were identified as independent predicators of readmissions in NSTEMI patients after PCI. The prediction model constructed by the LR algorithm was the best. The established column graph model established proved to be effective in identifying high-risk groups with high accuracy and differentiation. It holds a specific predictive value for the occurrence of readmissions after direct PCI in NSTEMI patients.

Identification of important symptoms and diagnostic hypothyroidism patients using machine learning algorithms

Background

Hypothyroidism is one of the most common endocrine diseases. It is, however, usually challenging for physicians to diagnose due to nonspecific symptoms. The usual procedure for diagnosis of Hypothyroidism is a blood test. In recent years, machine learning algorithms have proved to be powerful tools in medicine due to their diagnostic accuracy. In this study, the authors aim to predict and identify the most important symptoms of Hypothyroidism using machine learning algorithms.

Method

In this cross-sectional, single-center study, 1296 individuals who visited an endocrinologist for the first time with symptoms of Hypothyroidism were studied, 676 of whom were identified as patients through thyroid-stimulating hormone testing. The outcome was binary (with Hypothyroidism /without Hypothyroidism). In a comparative analysis, random forest, decision tree, and logistic regression methods were used to diagnose primary Hypothyroidism.

Results

Symptoms such as tiredness, unusual cold feeling, yellow skin (jaundice), cold hands and feet, numbness of hands, loss of appetite, and weight Hypothyroidism gain were recognized as the most important symptoms in identifying Hypothyroidism. Among the studied algorithms, random forest had the best performance in identifying these symptoms (accuracy=0.83, kappa=0.46, sensitivity=0.88, specificity=0.88).

Conclusions

The findings suggest that machine learning methods can identify Hypothyroidism patients who show relatively simple symptoms with acceptable accuracy without the need for a blood test. Greater familiarity and utilization of such methods by physicians may, therefore, reduce the expense and stress burden of clinical testing.

A machine learning model to predict therapeutic inertia in type 2 diabetes using electronic health record data

OBJECTIVE

To estimate the therapeutic inertia prevalence for patients with type 2 diabetes, develop and validate a machine learning model predicting therapeutic inertia, and determine the added predictive value of area-level social determinants of health (SDOH).

METHODS

This prognostic study with a retrospective cohort design used OneFlorida data (linked electronic health records (EHRs) from 1240 practices/clinics in Florida). The study cohort included adults (aged ≥ 18) with type 2 diabetes, HbA1C ≥ 7% (53 mmol/mol), ≥one ambulatory visit, and ≥one antihyperglycemic medication prescribed (excluded patients prescribed insulin before HbA1C). The outcome was therapeutic inertia, defined as absence of treatment intensification within six months after HbA1C ≥ 7% (53 mmol/mol). The predictors were patient, provider, and healthcare system factors. Machine learning methods included gradient boosting machines (GBM), random forests (RF), elastic net (EN), and least absolute shrinkage and selection operator (LASSO). The DeLong test compared the discriminative ability (represented by C-statistics) between models.

RESULTS

The cohort included 31,087 patients with type 2 diabetes (mean age = 58.89 (SD = 13.27) years, 50.50% male, 58.89% White). The therapeutic inertia prevalence was 39.80% among the 68,445 records. GBM outperformed (C-statistic from testing sample = 0.84, 95% CI = 0.83-0.84) RF (C-statistic = 0.80, 95% CI = 0.79-0.80), EN (C-statistic = 0.80, 95% CI = 0.80-0.81), and LASSO (C-statistic = 0.80, 95% CI = 0.80-0.81), p < 0.05. Area-level SDOH significantly increased the discriminative ability versus models without SDOH (C-statistic for GBM = 0.84, 95% CI = 0.84-0.85 vs. 0.84, 95% CI = 0.83-0.84), p < 0.05.

CONCLUSIONS

Using EHRs of patients with type 2 diabetes from a large state, machine learning predicted therapeutic inertia (prevalence = 40%). The model's ability to predict patients at high risk of therapeutic inertia is clinically applicable to diabetes care.

[Artificial intelligence-enhanced electrocardiography : Will it revolutionize diagnosis and management of our patients?]

The use of artificial intelligence (AI) in healthcare has made significant progress in the last 10 years. Many experts believe that utilization of AI technologies, especially deep learning, will bring about drastic changes in how physicians understand, diagnose, and treat diseases. One aspect of this development is AI-enhanced electrocardiography (ECG) analysis. It involves not only optimizing the traditional ECG analysis by the physician and improving the accuracy of automatic interpretation by the ECG device but also introducing entirely new diagnostic options enabled by AI. Examples include assessing left ventricular function, predicting atrial fibrillation, and diagnosing both cardiac and noncardiac conditions. Through AI, the ECG becomes a comprehensive tool for screening, diagnosis, and patient management, potentially revolutionizing clinical practices. This paper provides an overview of the current state of this development, discusses existing limitations, and explores the challenges that may arise for healthcare professionals in this context.

Enhanced Runge-Kutta-driven feature selection model for early detection of gastroesophageal reflux disease

Gastroesophageal reflux disease (GERD) profoundly compromises the quality of life, with prolonged untreated cases posing a heightened risk of severe complications such as esophageal injury and esophageal carcinoma. The imperative for early diagnosis is paramount in averting progressive pathological developments. This study introduces a wrapper-based feature selection model based on the enhanced Runge Kutta algorithm (SCCRUN) and fuzzy k-nearest neighbors (FKNN) for GERD prediction, named bSCCRUN-FKNN-FS. Runge Kutta algorithm (RUN) is a metaheuristic algorithm designed based on the Runge-Kutta method. However, RUN's effectiveness in local search capabilities is insufficient, and it exhibits insufficient convergence accuracy. To enhance the convergence accuracy of RUN, spiraling communication and collaboration (SCC) is introduced. By facilitating information exchange among population individuals, SCC expands the solution search space, thereby improving convergence accuracy. The optimization capabilities of SCCRUN are experimentally validated through comparisons with classical and state-of-the-art algorithms on the IEEE CEC 2017 benchmark. Subsequently, based on SCCRUN, the bSCCRUN-FKNN-FS model is proposed. During the period from 2019 to 2023, a dataset comprising 179 cases of GERD, including 110 GERD patients and 69 healthy individuals, was collected from Zhejiang Provincial People's Hospital. This dataset was utilized to compare our proposed model against similar algorithms in order to evaluate its performance. Concurrently, it was determined that features such as the internal diameter of the esophageal hiatus during distention, esophagogastric junction diameter during distention, and external diameter of the esophageal hiatus during non-distention play crucial roles in influencing GERD prediction. Experimental findings demonstrate the outstanding performance of the proposed model, with a predictive accuracy reaching as high as 93.824 %. These results underscore the significant advantage of the proposed model in both identifying and predicting GERD patients.

Artificial intelligence to advance acute and intensive care medicine

PURPOSE OF REVIEW

This review explores recent key advancements in artificial intelligence for acute and intensive care medicine. As artificial intelligence rapidly evolves, this review aims to elucidate its current applications, future possibilities, and the vital challenges that are associated with its integration into emergency medical dispatch, triage, medical consultation and ICUs.

RECENT FINDINGS

The integration of artificial intelligence in emergency medical dispatch (EMD) facilitates swift and accurate assessment. In the emergency department (ED), artificial intelligence driven triage models leverage diverse patient data for improved outcome predictions, surpassing human performance in retrospective studies. Artificial intelligence can streamline medical documentation in the ED and enhances medical imaging interpretation. The introduction of large multimodal generative models showcases the future potential to process varied biomedical data for comprehensive decision support. In the ICU, artificial intelligence applications range from early warning systems to treatment suggestions.

SUMMARY

Despite promising academic strides, widespread artificial intelligence adoption in acute and critical care is hindered by ethical, legal, technical, organizational, and validation challenges. Despite these obstacles, artificial intelligence's potential to streamline clinical workflows is evident. When these barriers are overcome, future advancements in artificial intelligence have the potential to transform the landscape of patient care for acute and intensive care medicine.

Prediction Models for Intravenous Immunoglobulin Non-Responders of Kawasaki Disease Using Machine Learning

BACKGROUND AND OBJECTIVE: Intravenous immunoglobulin (IVIG) is a prominent therapeutic agent for Kawasaki disease (KD) that significantly reduces the incidence of coronary artery anomalies. Various methodologies, including machine learning, have been employed to develop IVIG non-responder prediction models; however, their validation and reproducibility remain unverified. This study aimed to develop a predictive scoring system for identifying IVIG nonresponders and rigorously test the accuracy and reliability of this system. METHODS: The study included an exposure group of 228 IVIG non-responders and a control group of 997 IVIG responders. Subsequently, a predictive machine learning model was constructed. The Shizuoka score, including variables such as the "initial treatment date" (cutoff: < 4 days), sodium level (cutoff: < 133 mEq/L), total bilirubin level (cutoff: ≥ 0.5 mg/dL), and neutrophil-to-lymphocyte ratio (cutoff: ≥ 2.6), was established. Patients meeting two or more of these criteria were grouped as high-risk IVIG non-responders. Using the Shizuoka score to stratify IVIG responders, propensity score matching was used to analyze 85 patients each for IVIG and IVIG-added prednisolone treatment in the high-risk group. In the IVIG plus prednisolone group, the IVIG non-responder count significantly decreased (p < 0.001), with an odds ratio of 0.192 (95% confidence interval 0.078-0.441). CONCLUSIONS: Intravenous immunoglobulin non-responders were predicted using machine learning models and validated using propensity score matching. The initiation of initial IVIG-added prednisolone treatment in the high-risk group identified by the Shizuoka score, crafted using machine learning models, appears useful for predicting IVIG non-responders.

Development of a machine learning-based prediction model for clinical pregnancy of intrauterine insemination in a large Chinese population

PURPOSE

This study aimed to evaluate the effectiveness of a random forest (RF) model in predicting clinical pregnancy outcomes from intrauterine insemination (IUI) and identifying significant factors affecting IUI pregnancy in a large Chinese population.

METHODS

RESULTS: A total of 11 variables, including eight from female (age, body mass index, duration of infertility, prior miscarriage, and spontaneous abortion), hormone levels (anti-Müllerian hormone, follicle-stimulating hormone, luteinizing hormone), and three from male (smoking, semen volume, and sperm concentration), were identified as the significant variables associated with IUI clinical pregnancy in our Chinese dataset. The RF-based prediction model presents an area under the receiver operating characteristic curve (AUC) of 0.716 (95% confidence interval, 0.6914-0.7406), an accuracy rate of 0.6081, a sensitivity rate of 0.7113, and a specificity rate of 0.505. Importance analysis indicated that semen volume was the most vital variable in predicting IUI clinical pregnancy.

CONCLUSIONS

The machine learning-based IUI clinical pregnancy prediction model showed a promising predictive efficacy that could provide a potent tool to guide selecting targeted infertile couples beneficial from IUI treatment, and also identify which parameters are most relevant in IUI clinical pregnancy.

Application of Artificial Intelligence in Shoulder Pathology

Artificial intelligence (AI) refers to the science and engineering of creating intelligent machines for imitating and expanding human intelligence. Given the ongoing evolution of the multidisciplinary integration trend in modern medicine, numerous studies have investigated the power of AI to address orthopedic-specific problems. One particular area of investigation focuses on shoulder pathology, which is a range of disorders or abnormalities of the shoulder joint, causing pain, inflammation, stiffness, weakness, and reduced range of motion. There has not yet been a comprehensive review of the recent advancements in this field. Therefore, the purpose of this review is to evaluate current AI applications in shoulder pathology. This review mainly summarizes several crucial stages of the clinical practice, including predictive models and prognosis, diagnosis, treatment, and physical therapy. In addition, the challenges and future development of AI technology are also discussed.

An interpretable predictive deep learning platform for pediatric metabolic diseases

OBJECTIVES

Metabolic disease in children is increasing worldwide and predisposes a wide array of chronic comorbid conditions with severe impacts on quality of life. Tools for early detection are needed to promptly intervene to prevent or slow the development of these long-term complications.

MATERIALS AND METHODS

No clinically available tools are currently in widespread use that can predict the onset of metabolic diseases in pediatric patients. Here, we use interpretable deep learning, leveraging longitudinal clinical measurements, demographical data, and diagnosis codes from electronic health record data from a large integrated health system to predict the onset of prediabetes, type 2 diabetes (T2D), and metabolic syndrome in pediatric cohorts.

RESULTS

The cohort included 49 517 children with overweight or obesity aged 2-18 (54.9% male, 73% Caucasian), with a median follow-up time of 7.5 years and mean body mass index (BMI) percentile of 88.6%. Our model demonstrated area under receiver operating characteristic curve (AUC) accuracies up to 0.87, 0.79, and 0.79 for predicting T2D, metabolic syndrome, and prediabetes, respectively. Whereas most risk calculators use only recently available data, incorporating longitudinal data improved AUCs by 13.04%, 11.48%, and 11.67% for T2D, syndrome, and prediabetes, respectively, versus models using the most recent BMI (P < 2.2 × 10-16).

DISCUSSION

Despite most risk calculators using only the most recent data, incorporating longitudinal data improved the model accuracies because utilizing trajectories provides a more comprehensive characterization of the patient's health history. Our interpretable model indicated that BMI trajectories were consistently identified as one of the most influential features for prediction, highlighting the advantages of incorporating longitudinal data when available.

Utility of artificial intelligence in the diagnosis and management of keratoconus: a systematic review

Introduction

The application of artificial intelligence (AI) systems in ophthalmology is rapidly expanding. Early detection and management of keratoconus is important for preventing disease progression and the need for corneal transplant. We review studies regarding the utility of AI in the diagnosis and management of keratoconus and other corneal ectasias.

Methods

We conducted a systematic search for relevant original, English-language research studies in the PubMed, Web of Science, Embase, and Cochrane databases from inception to October 31, 2023, using a combination of the following keywords: artificial intelligence, deep learning, machine learning, keratoconus, and corneal ectasia. Case reports, literature reviews, conference proceedings, and editorials were excluded. We extracted the following data from each eligible study: type of AI, input used for training, output, ground truth or reference, dataset size, availability of algorithm/model, availability of dataset, and major study findings.

Results

Ninety-three original research studies were included in this review, with the date of publication ranging from 1994 to 2023. The majority of studies were regarding the use of AI in detecting keratoconus or subclinical keratoconus (n=61). Among studies regarding keratoconus diagnosis, the most common inputs were corneal topography, Scheimpflug-based corneal tomography, and anterior segment-optical coherence tomography. This review also summarized 16 original research studies regarding AI-based assessment of severity and clinical features, 7 studies regarding the prediction of disease progression, and 6 studies regarding the characterization of treatment response. There were only three studies regarding the use of AI in identifying susceptibility genes involved in the etiology and pathogenesis of keratoconus.

Discussion

Algorithms trained on Scheimpflug-based tomography seem promising tools for the early diagnosis of keratoconus that can be particularly applied in low-resource communities. Future studies could investigate the application of AI models trained on multimodal patient information for staging keratoconus severity and tracking disease progression.

Predictive models-assisted diagnosis of AIDS-associated Pneumocystis jirovecii pneumonia in the emergency room, based on clinical, laboratory, and radiological data

We assessed predictive models (PMs) for diagnosing Pneumocystis jirovecii pneumonia (PCP) in AIDS patients seen in the emergency room (ER), aiming to guide empirical treatment decisions. Data from suspected PCP cases among AIDS patients were gathered prospectively at a reference hospital's ER, with diagnoses later confirmed through sputum PCR analysis. We compared clinical, laboratory, and radiological data between PCP and non-PCP groups, using the Boruta algorithm to confirm significant differences. We evaluated ten PMs tailored for various ERs resource levels to diagnose PCP. Four scenarios were created, two based on X-ray findings (diffuse interstitial infiltrate) and two on CT scans ("ground-glass"), incorporating mandatory variables: lactate dehydrogenase, O2sat, C-reactive protein, respiratory rate (> 24 bpm), and dry cough. We also assessed HIV viral load and CD4 cell count. Among the 86 patients in the study, each model considered either 6 or 8 parameters, depending on the scenario. Many models performed well, with accuracy, precision, recall, and AUC scores > 0.8. Notably, nearest neighbor and naïve Bayes excelled (scores > 0.9) in specific scenarios. Surprisingly, HIV viral load and CD4 cell count did not improve model performance. In conclusion, ER-based PMs using readily available data can significantly aid PCP treatment decisions in AIDS patients.

Machine Learning for Short-Term Mortality in Acute Decompensation of Liver Cirrhosis: Better than MELD Score

Prediction of short-term mortality in patients with acute decompensation of liver cirrhosis could be improved. We aimed to develop and validate two machine learning (ML) models for predicting 28-day and 90-day mortality in patients hospitalized with acute decompensated liver cirrhosis. We trained two artificial neural network (ANN)-based ML models using a training sample of 165 out of 290 (56.9%) patients, and then tested their predictive performance against Model of End-stage Liver Disease-Sodium (MELD-Na) and MELD 3.0 scores using a different validation sample of 125 out of 290 (43.1%) patients. The area under the ROC curve (AUC) for predicting 28-day mortality for the ML model was 0.811 (95%CI: 0.714- 0.907; p < 0.001), while the AUC for the MELD-Na score was 0.577 (95%CI: 0.435-0.720; p = 0.226) and for MELD 3.0 was 0.600 (95%CI: 0.462-0.739; p = 0.117). The area under the ROC curve (AUC) for predicting 90-day mortality for the ML model was 0.839 (95%CI: 0.776- 0.884; p < 0.001), while the AUC for the MELD-Na score was 0.682 (95%CI: 0.575-0.790; p = 0.002) and for MELD 3.0 was 0.703 (95%CI: 0.590-0.816; p < 0.001). Our study demonstrates that ML-based models for predicting short-term mortality in patients with acute decompensation of liver cirrhosis perform significantly better than MELD-Na and MELD 3.0 scores in a validation cohort.

Accuracy of machine learning to predict the outcomes of shoulder arthroplasty: a systematic review

BACKGROUND

Artificial intelligence (AI) uses computer systems to simulate cognitive capacities to accomplish goals like problem-solving and decision-making. Machine learning (ML), a branch of AI, makes algorithms find connections between preset variables, thereby producing prediction models. ML can aid shoulder surgeons in determining which patients may be susceptible to worse outcomes and complications following shoulder arthroplasty (SA) and align patient expectations following SA. However, limited literature is available on ML utilization in total shoulder arthroplasty (TSA) and reverse TSA.

METHODS

A systematic literature review in accordance with PRISMA guidelines was performed to identify primary research articles evaluating ML's ability to predict SA outcomes. With duplicates removed, the initial query yielded 327 articles, and after applying inclusion and exclusion criteria, 12 articles that had at least 1 month follow-up time were included.

RESULTS

ML can predict 30-day postoperative complications with a 90% accuracy, postoperative range of motion with a higher-than-85% accuracy, and clinical improvement in patient-reported outcome measures above minimal clinically important differences with a 93%-99% accuracy. ML can predict length of stay, operative time, discharge disposition, and hospitalization costs.

CONCLUSION

ML can accurately predict outcomes and complications following SA and healthcare utilization. Outcomes are highly dependent on the type of algorithms used, data input, and features selected for the model.

LEVEL OF EVIDENCE

III.

A potential new way to facilitate HCV elimination: The prediction of viremia in anti-HCV seropositive patients using machine learning algorithms

BACKGROUND AND STUDY AIMS

The present study was undertaken to design a new machine learning (ML) model that can predict the presence of viremia in hepatitis C virus (HCV) antibody (anti-HCV) seropositive cases.

PATIENTS AND METHODS

This retrospective study was conducted between January 2012-January 2022 with 812 patients who were referred for anti-HCV positivity and were examined for HCV ribonucleic acid (HCV RNA). Models were constructed with 11 features with a predictor (presence and absence of viremia) to predict HCV viremia. To build an optimal model, this current study also examined and compared the three classifier data mining approaches: RF, SVM and XGBoost.

RESULTS

The highest performance was achieved with XGBoost (90%), which was followed by RF (89%), SVM Linear (85%) and SVM Radial (83%) algorithms, respectively. The four most important key features contributing to the models were: alanine aminotransferase (ALT), aspartate aminotransferase (AST), albumin (ALB) and anti-HCV levels, respectively, while "ALB" was replaced by the "AGE" only in the XGBoost model.

CONCLUSION

This study has shown that XGBoost and RF based ML models, incorporating anti-HCV levels and routine laboratory tests (ALT, AST, ALB), and age are capable of providing HCV viremia diagnosis with 90% and 89% accuracy, respectively. These findings highlight the potential of ML models in the early diagnosis of HCV viremia, which may be helpful in optimizing HCV elimination programs.

Machine learning combined with single-cell analysis reveals predictive capacity and immunotherapy response of T cell exhaustion-associated lncRNAs in uterine corpus endometrial carcinoma

BACKGROUND

The exhaustion of T-cells is a primary factor contributing to immune dysfunction in cancer. Long non-coding RNAs (lncRNAs) play a significant role in the advancement, survival, and treatment of Uterine Corpus Endometrial Carcinoma (UCEC). Nevertheless, there has been no investigation into the involvement of lncRNAs associated with T-cell exhaustion (TEXLs) in UCEC. The goal of this work is to establish predictive models for TEXLs in UCEC and study their related immune features.

METHODS

Using transcriptome and single-cell sequencing data from The Cancer Genome Atlas and Gene Expression Omnibus databases, we employed co-expression analysis and univariate Cox regression to identify prognostic-associated TEXLs (pTEXLs). The prognostic model was developed using the Least Absolute Contraction and Selection Operator. The immunotherapy characteristics of the prognostic model risk score were studied. Then molecular subgroups were identified through non-negative Matrix Factorization based on pTEXLs. The identification of co-expressed genes was done using a weighted correlation network analysis. Subsequently, a diagnostic model for UCEC was created. In-depth investigations, both in vitro and in vivo, were carried out to elucidate the molecular mechanism of the key gene within the diagnostic model.

RESULTS

Receiver operating characteristic curve, calibration curve, and decision curve analysis proved the validity of the predictive models established according to pTEXLs. The subgroup with lower risk scores in the prognostic model has better responses to blocking immune checkpoint therapy. Single-cell analysis suggests that the expression level of MIEN1 is relatively high in immune cells among diagnostic genes. Furthermore, the targeted suppression of MIEN1 via sh-MIEN1 diminishes the proliferative, migratory, and invasive capacities of UCEC cells, potentially associated with CD8+ T cell exhaustion.

CONCLUSIONS

The association between TEXLs and UCEC was methodically elucidated by our investigation. A stable pTEXLs risk prediction model and a diagnosis model for UCEC were also established.

A Review of Machine Learning Algorithms for Biomedical Applications

As the amount and complexity of biomedical data continue to increase, machine learning methods are becoming a popular tool in creating prediction models for the underlying biomedical processes. Although all machine learning methods aim to fit models to data, the methodologies used can vary greatly and may seem daunting at first. A comprehensive review of various machine learning algorithms per biomedical applications is presented. The key concepts of machine learning are supervised and unsupervised learning, feature selection, and evaluation metrics. Technical insights on the major machine learning methods such as decision trees, random forests, support vector machines, and k-nearest neighbors are analyzed. Next, the dimensionality reduction methods like principal component analysis and t-distributed stochastic neighbor embedding methods, and their applications in biomedical data analysis were reviewed. Moreover, in biomedical applications predominantly feedforward neural networks, convolutional neural networks, and recurrent neural networks are utilized. In addition, the identification of emerging directions in machine learning methodology will serve as a useful reference for individuals involved in biomedical research, clinical practice, and related professions who are interested in understanding and applying machine learning algorithms in their research or practice.

Machine Learning-Based Discrimination of Cardiovascular Outcomes in Patients With Hypertrophic Cardiomyopathy

Background

Current risk stratification strategies for patients with hypertrophic cardiomyopathy (HCM) are limited to traditional methodologies.

Objectives

The authors aimed to establish machine learning (ML)-based models to discriminate major cardiovascular events in patients with HCM.

Methods

We enrolled consecutive HCM patients from 2 tertiary referral centers and used 25 clinical and echocardiographic features to discriminate major adverse cardiovascular events (MACE), including all-cause death, admission for heart failure (HF-adm), and stroke. The best model was selected for each outcome using the area under the receiver operating characteristic curve (AUROC) with 20-fold cross-validation. After testing in the external validation cohort, the relative importance of features in discriminating each outcome was determined using the SHapley Additive exPlanations (SHAP) method.

Results

In total, 2,111 patients with HCM (age 61.4 ± 13.6 years; 67.6% men) were analyzed. During the median 4.0 years of follow-up, MACE occurred in 341 patients (16.2%). Among the 4 ML models, the logistic regression model achieved the best AUROC of 0.800 (95% CI: 0.760-0.841) for MACE, 0.789 (95% CI: 0.736-0.841) for all-cause death, 0.798 (95% CI: 0.736-0.860) for HF-adm, and 0.807 (95% CI: 0.754-0.859) for stroke. The discriminant ability of the logistic regression model remained excellent when applied to the external validation cohort for MACE (AUROC = 0.768), all-cause death (AUROC = 0.750), and HF-adm (AUROC = 0.806). The SHAP analysis identified left atrial diameter and hypertension as important variables for all outcomes of interest.

Conclusions

The proposed ML models incorporating various phenotypes from patients with HCM accurately discriminated adverse cardiovascular events and provided variables with high importance for each outcome.

An introduction to machine learning and generative artificial intelligence for otolaryngologists-head and neck surgeons: a narrative review

PURPOSE

Despite the robust expansion of research surrounding artificial intelligence (AI) and machine learning (ML) and their applications to medicine, these methodologies often remain opaque and inaccessible to many otolaryngologists. Especially, with the increasing ubiquity of large-language models (LLMs), such as ChatGPT and their potential implementation in clinical practice, clinicians may benefit from a baseline understanding of some aspects of AI. In this narrative review, we seek to clarify underlying concepts, illustrate applications to otolaryngology, and highlight future directions and limitations of these tools.

METHODS

Recent literature regarding AI principles and otolaryngologic applications of ML and LLMs was reviewed via search in PubMed and Google Scholar.

RESULTS

Significant recent strides have been made in otolaryngology research utilizing AI and ML, across all subspecialties, including neurotology, head and neck oncology, laryngology, rhinology, and sleep surgery. Potential applications suggested by recent publications include screening and diagnosis, predictive tools, clinical decision support, and clinical workflow improvement via LLMs. Ongoing concerns regarding AI in medicine include ethical concerns around bias and data sharing, as well as the "black box" problem and limitations in explainability.

CONCLUSIONS

Potential implementations of AI in otolaryngology are rapidly expanding. While implementation in clinical practice remains theoretical for most of these tools, their potential power to influence the practice of otolaryngology is substantial.

LEVEL OF EVIDENCE: 4

Predicting treatment outcome based on resting-state functional connectivity in internalizing mental disorders: A systematic review and meta-analysis

Predicting treatment outcome in internalizing mental disorders prior to treatment initiation is pivotal for precision mental healthcare. In this regard, resting-state functional connectivity (rs-FC) and machine learning have often shown promising prediction accuracies. This systematic review and meta-analysis evaluates these studies, considering their risk of bias through the Prediction Model Study Risk of Bias Assessment Tool (PROBAST). We examined the predictive performance of features derived from rs-FC, identified features with the highest predictive value, and assessed the employed machine learning pipelines. We searched the electronic databases Scopus, PubMed and PsycINFO on the 12th of December 2022, which resulted in 13 included studies. The mean balanced accuracy for predicting treatment outcome was 77% (95% CI: [72%- 83%]). rs-FC of the dorsolateral prefrontal cortex had high predictive value in most studies. However, a high risk of bias was identified in all studies, compromising interpretability. Methodological recommendations are provided based on a comprehensive exploration of the studies' machine learning pipelines, and potential fruitful developments are discussed.

A multiphase study protocol of identifying, and predicting cancer-related symptom clusters: applying a mixed-method design and machine learning algorithms

Objectives

In recent years, there has been increasing attention on the cluster approach to symptom management. Two significant challenges in the symptom cluster (SC) approach are identifying and predicting these clusters. This multiphase protocol aims to identify SCs in patients with advanced cancer as the primary objective, with the secondary objective of developing machine learning algorithms to predict SCs identified in the first phase.

Methods

The 2-MIXIP study consists of two main phases. The first phase involves identifying SCs, and the second phase focuses on developing predictive algorithms for the identified SCs. The identification of SCs involves a parallel mixed-method design (quantitative and qualitative). Quantitative and qualitative methods are conducted simultaneously and given equal importance. The data are collected and analyzed independently before being integrated. The quantitative part is conducted using a descriptive-analytical method. The qualitative analysis is conducted using a content analysis approach. Then, the identified SCs from both parts are integrated to determine the final clusters and use them in the second phase. In the second phase, we employ a tree-based machine learning method to create predictive algorithms for SCs using key demographic and clinical patient characteristics.

Conclusion

The findings of the 2-MIXIP study can help manage cancer patients' symptoms more effectively and enhance clinical decision-making by using SCs prediction. Furthermore, the results of this study can provide guidance for clinical trials aimed at managing symptoms.

Application of machine learning methods for predicting childhood anaemia: Analysis of Ethiopian Demographic Health Survey of 2016

Childhood anaemia is a public health problem in Ethiopia. Machine learning (ML) is a growing in medicine field to predict diseases. Diagnosis of childhood anaemia is resource intensive. The aim of this study is to apply machine learning (ML) algorithm to predict childhood anaemia using socio-demographic, economic, and maternal and child related variables. The study used data from 2016 Ethiopian demographic health survey (EDHS). We used Python software version 3.11 to apply and test ML algorithms through logistic regression, Random Forest (RF), Decision Tree, and K-Nearest Neighbours (KNN). We evaluated the performance of each of the ML algorithms using discrimination and calibration parameters. The predictive performance of the algorithms was between 60% and 66%. The logistic regression model was the best predictive model of ML with accuracy (66%), sensitivity (82%), specificity (42%), and AUC (69%), followed by RF with accuracy (64%), sensitivity (79%), specificity (42%), and AUC (63%). The logistic regression and the RF models of ML showed poorest family, child age category between 6 and 23 months, uneducated mother, unemployed mother, and stunting as high importance predictors of childhood anaemia. Applying logistic regression and RF models of ML can detect combinations of predictors of childhood anaemia that can be used in primary health care professionals.

Advancing Breast Cancer Diagnosis through Breast Mass Images, Machine Learning, and Regression Models

Breast cancer results from a disruption of certain cells in breast tissue that undergo uncontrolled growth and cell division. These cells most often accumulate and form a lump called a tumor, which may be benign (non-cancerous) or malignant (cancerous). Malignant tumors can spread quickly throughout the body, forming tumors in other areas, which is called metastasis. Standard screening techniques are insufficient in the case of metastasis; therefore, new and advanced techniques based on artificial intelligence (AI), machine learning, and regression models have been introduced, the primary aim of which is to automatically diagnose breast cancer through the use of advanced techniques, classifiers, and real images. Real fine-needle aspiration (FNA) images were collected from Wisconsin, and four classifiers were used, including three machine learning models and one regression model: the support vector machine (SVM), naive Bayes (NB), k-nearest neighbors (k-NN), and decision tree (DT)-C4.5. According to the accuracy, sensitivity, and specificity results, the SVM algorithm had the best performance; it was the most powerful computational classifier with a 97.13% accuracy and 97.5% specificity. It also had around a 96% sensitivity for the diagnosis of breast cancer, unlike the models used for comparison, thereby providing an exact diagnosis on the one hand and a clear classification between benign and malignant tumors on the other hand. As a future research prospect, more algorithms and combinations of features can be considered for the precise, rapid, and effective classification and diagnosis of breast cancer images for imperative decisions.

Bioinformatics in urology - molecular characterization of pathophysiology and response to treatment

The application of bioinformatics has revolutionized the practice of medicine in the past 20 years. From early studies that uncovered subtypes of cancer to broad efforts spearheaded by the Cancer Genome Atlas initiative, the use of bioinformatics strategies to analyse high-dimensional data has provided unprecedented insights into the molecular basis of disease. In addition to the identification of disease subtypes - which enables risk stratification - informatics analysis has facilitated the identification of novel risk factors and drivers of disease, biomarkers of progression and treatment response, as well as possibilities for drug repurposing or repositioning; moreover, bioinformatics has guided research towards precision and personalized medicine. Implementation of specific computational approaches such as artificial intelligence, machine learning and molecular subtyping has yet to become widespread in urology clinical practice for reasons of cost, disruption of clinical workflow and need for prospective validation of informatics approaches in independent patient cohorts. Solving these challenges might accelerate routine integration of bioinformatics into clinical settings.

Unveiling the best predictive models for early‑onset metastatic cancer: Insights and innovations (Review)

Cancer metastasis is the primary cause of cancer deaths. Metastasis involves the spread of cancer cells from the primary tumors to other body parts, commonly through lymphatic and vascular pathways. Key aspects include the high mutation rate and the capability of metastatic cells to form invasive tumors even without a large initial tumor mass. Particular emphasis is given to early metastasis, occurring in initial cancer stages and often leading to misdiagnosis, which adversely affects survival and prognosis. The present review highlighted the need for improved understanding and detection methods for early metastasis, which has not been effectively identified clinically. The present review demonstrated the clinicopathological and molecular characteristics of early‑onset metastatic types of cancer, noting factors such as age, race, tumor size and location as well as the histological and pathological grade as significant predictors. In conclusion, the present review underscored the importance of early detection and management of metastatic types of cancer and called for improved predictive models, including advanced techniques such as nomograms and machine learning, so as to enhance patient outcomes, acknowledging the challenges and limitations of the current research as well as the necessity for further studies.