Interpretable machine learning for early neurological deterioration prediction in atrial fibrillation-related stroke

Machine Learning Differentiation of Autism Spectrum Sub-Classifications

PURPOSE

Disorders on the autism spectrum have characteristics that can manifest as difficulties with communication, executive functioning, daily living, and more. These challenges can be mitigated with early identification. However, diagnostic criteria has changed from DSM-IV to DSM-5, which can make diagnosing a disorder on the autism spectrum complex. We evaluated machine learning to classify individuals as having one of three disorders of the autism spectrum under DSM-IV, or as non-spectrum.

METHODS

We employed machine learning to analyze retrospective data from 38,560 individuals. Inputs encompassed clinical, demographic, and assessment data.

RESULTS

The algorithm achieved AUROCs ranging from 0.863 to 0.980. The model correctly classified 80.5% individuals; 12.6% of individuals from this dataset were misclassified with another disorder on the autism spectrum.

CONCLUSION

Machine learning can classify individuals as having a disorder on the autism spectrum or as non-spectrum using minimal data inputs.

Rescue therapy of early neurological deterioration in lacunar stroke

BACKGROUND

Early neurological deterioration (END) occurs in many patients with acute ischemic stroke due to a variety of causes. Although pharmacologically induced hypertension (PIH) and anticoagulants have been investigated in several clinical trials for the treatment of END, the efficacy and safety of these treatments remain unclear. Here, we investigated whether PIH or anticoagulation is better as a rescue therapy for the progression of END in patients with lacunar stroke.

METHODS

This study included patients with lacunar stroke who received rescue therapy with END within 3 days of symptom onset between April 2014 and August 2021. In the PIH group, phenylephrine was administered intravenously for 24 h and slowly tapered when symptoms improved or after 5 days of PIH. In the anticoagulation group, argatroban was administered continuously intravenously for 2 days and twice daily for next 5 days. We compared END recovery, defined as improvement in NIHSS from baseline, excellent outcomes (0 or 1 mRS at 3 months), and safety profile.

RESULTS

Among the 4818 patients with the lacunar stroke, END occurred in 147 patients. Seventy-nine patients with END received PIH (46.9%) and 68 patients (46.3%) received anticoagulation therapy. There was no significant difference in age (P = 0.82) and sex (P = 0.87) between the two groups. Compared to the anticoagulation group, the PIH group had a higher incidence of END recovery (77.2% vs. 51.5%, P < 0.01) and excellent outcomes (34.2% vs. 16.2%, P = 0.04). PIH was associated with END (HR 2.49; 95% CI 1.06-5.81, P = 0.04). PIH remained associated with END recovery (adjusted HR 3.91; 95% CI 1.19-12.90, P = 0.02). Safety outcomes, like hemorrhagic conversion and mortality, were not significantly different between the two groups.

CONCLUSIONS

As a rescue therapy for the progression of END in lacunar stroke patients, PIH with phenylephrine was more effective with similar safety compared to anticoagulation with argatroban.

Center of Pressure- and Machine Learning-based Gait Score and Clinical Risk Factors for Predicting Functional Outcome in Acute Ischemic Stroke

OBJECTIVES

To investigate whether machine learning (ML)-based center of pressure (COP) analysis for gait assessment, when used in conjunction with clinical information, offers additive benefits in predicting functional outcomes in patients with acute ischemic stroke.

DESIGN

A prospective, single-center cohort study.

SETTING

A tertiary hospital setting.

PARTICIPANTS

A total of 185 patients with acute ischemic stroke, capable of walking 10 m with or without a gait aid by day 7 postadmission. From these patients, 10,804 pairs of consecutive footfalls were included for analysis.

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

The dependent variable was a 3-month poor functional outcome, defined as modified Rankin scale score ≥2. For independent variables, 65 clinical variables including demographics, anthropometrics, comorbidities, laboratory data, questionnaires, and drug history were included. Gait function was evaluated using a pressure-sensitive mat. Time-series COP data were parameterized into spatial and temporal variables and analyzed with logistic regression and 2 ML models (light gradient-boosting machine and multilayer perceptron [MLP]). We derived GAIT-AI output scores from the best-performing model analyzed COP data and constructed multivariable logistic regression models using clinical variables and the GAIT scores.

RESULTS

Among the included patients, 70 (37.8%) experienced unfavorable outcomes. The MLP model demonstrated the highest predictive performance with an area under the receiver operating characteristic curve (AUROC) of 0.799. Multivariable logistic regression identified age, initial National Institutes of Health Stroke Scale, and initial Fall Efficacy Scale-International as associated factors with unfavorable outcomes. The combined multivariable logistic regression incorporating COP-derived output scores improved the AUROC to 0.812.

CONCLUSIONS

Gait function, assessed through COP analysis, serves as a significant predictor of functional outcome in patients with acute ischemic stroke. ML-based COP analysis, when combined with clinical data, enhances the prediction of poor functional outcomes.

Artificial intelligence and atrial fibrillation: A bibliometric analysis from 2013 to 2023

Background

In the study of atrial fibrillation (AF), a prevalent cardiac arrhythmia, the utilization of artificial intelligence (AI) in diagnostic and therapeutic strategies holds the potential to address existing limitations. This research employs bibliometrics to objectively investigate research hotspots, development trends, and existing issues in the application of AI within the AF field, aiming to provide targeted recommendations for relevant researchers.

Methods

Relevant publications on the application of AI in AF field were retrieved from the Web of Science Core Collection (WoSCC) database from 2013 to 2023. The bibliometric analysis was conducted by the R (4.2.2) "bibliometrix" package and VOSviewer(1.6.19).

Results

Analysis of 912 publications reveals that the field of AI in AF is currently experiencing rapid development. The United States, China, and the United Kingdom have made outstanding contributions to this field. Acharya UR is a notable contributor and pioneer in the area. The following topics have been elucidated: AI's application in managing the risk of AF complications is a hot mature topic; AI-electrocardiograph for AF diagnosis and AI-assisted catheter ablation surgery are the emerging and booming topics; smart wearables for real-time AF monitoring and AI for individualized AF medication are niche and well-developed topics.

Conclusion

This study offers comprehensive analysis of the origin, current status, and future trends of AI applications in AF, aiming to advance the development of the field.

Prediction of early neurologic deterioration in patients with perforating artery territory infarction using machine learning: a retrospective study

Background

Early neurological deterioration (END) is a frequent complication in patients with perforating artery territory infarction (PAI), leading to poorer outcomes. Therefore, we aimed to apply machine learning (ML) algorithms to predict the occurrence of END in PAI and investigate related risk factors.

Methods

This retrospective study analyzed a cohort of PAI patients, excluding those with severe stenosis of the parent artery. We included demographic characteristics, clinical features, laboratory data, and imaging variables. Recursive feature elimination with cross-validation (RFECV) was performed to identify critical features. Seven ML algorithms, namely logistic regression, random forest, adaptive boosting, gradient boosting decision tree, histogram-based gradient boosting, extreme gradient boosting, and category boosting, were developed to predict END in PAI patients using these critical features. We compared the accuracy of these models in predicting outcomes. Additionally, SHapley Additive exPlanations (SHAP) values were introduced to interpret the optimal model and assess the significance of input features.

Results

The study enrolled 1,020 PAI patients with a mean age of 60.46 (range 49.11-71.81) years. Of these, 30.39% were women, and 129 (12.65%) experienced END. RFECV selected 13 critical features, including blood urea nitrogen (BUN), total cholesterol (TC), low-density-lipoprotein cholesterol (LDL-C), apolipoprotein B (apoB), atrial fibrillation, loading dual antiplatelet therapy (DAPT), single antiplatelet therapy (SAPT), argatroban, the basal ganglia, the thalamus, the posterior choroidal arteries, maximal axial infarct diameter (measured at < 15 mm), and stroke subtype. The gradient-boosting decision tree had the highest area under the curve (0.914) among the seven ML algorithms. The SHAP analysis identified apoB as the most significant variable for END.

Conclusion

Our results suggest that ML algorithms, especially the gradient-boosting decision tree, are effective in predicting the occurrence of END in PAI patients.

Predicting short-term outcomes in atrial-fibrillation-related stroke using machine learning

Background

Prognostic prediction and the identification of prognostic factors are critical during the early period of atrial-fibrillation (AF)-related strokes as AF is associated with poor outcomes in stroke patients.

Methods

Two independent datasets, namely, the Korean Atrial Fibrillation Evaluation Registry in Ischemic Stroke Patients (K-ATTENTION) and the Korea University Stroke Registry (KUSR), were used for internal and external validation, respectively. These datasets include common variables such as demographic, laboratory, and imaging findings during early hospitalization. Outcomes were unfavorable functional status with modified Rankin scores of 3 or higher and mortality at 3 months. We developed two machine learning models, namely, a tree-based model and a multi-layer perceptron (MLP), along with a baseline logistic regression model. The area under the receiver operating characteristic curve (AUROC) was used as the outcome metric. The Shapley additive explanation (SHAP) method was used to evaluate the contributions of variables.

Results

Machine learning models outperformed logistic regression in predicting both outcomes. For 3-month unfavorable outcomes, MLP exhibited significantly higher AUROC values of 0.890 and 0.859 in internal and external validation sets, respectively, than those of logistic regression. For 3-month mortality, both machine learning models exhibited significantly higher AUROC values than the logistic regression for internal validation but not for external validation. The most significant predictor for both outcomes was the initial National Institute of Health and Stroke Scale.

Conclusion

The explainable machine learning model can reliably predict short-term outcomes and identify high-risk patients with AF-related strokes.

The association of stroke risk factors with the future thickness of carotid atherosclerotic plaques

OBJECTIVES

An advancing atherosclerotic plaque is a risk factor for stroke. We conducted this study to assess the relationship between risk factors of stroke with changing in the thickness of carotid plaques thickness evident on sonography.

METHODS

We carried out a secondary analysis of data from a study on carotid bifurcation plaques. Data were collected in the sonography laboratories of two university hospitals. In total, 564 (240; 42.6% men) patients with atherosclerotic plaques in the carotid bifurcation and internal carotid artery with stenosis ≥ 30% evident on duplex sonography were included. We developed machine learning models using an extreme gradient boosting algorithm with Shapley additive explanation method to find important risk factors and their interactions. The outcome was a change in the carotid plaque thickness after 36 months, and the predictors were initial plaque thickness and the risk factors of stroke.

RESULTS

Two regression models were developed for left and right carotid arteries. The R-squared values were 0.964 for the left, and 0.993 for the right model. Overall, the three top features were BMI, age, and initial plaque thickness for both left and right plaques. However, the risk factors of stroke showed stronger interaction in predicting plaque thickening of the left carotid more than the right carotid artery.

DISCUSSION

The effect of each predictor on plaque thickness is complicated by interactions with other risk factors, particularly for the left carotid artery. The side of carotid artery involvement should be considered for stroke prevention.

Development of Machine Learning Models for Predicting Osteoporosis in Patients with Type 2 Diabetes Mellitus-A Preliminary Study

Purpose

Diagnosing osteoporosis in T2DM based on bone mineral density (BMD) remains challenging. We sought to develop prediction models employing machine learning algorithms for use as screening instruments for osteoporosis in T2DM patients.

Patients and Methods

Data were collected from 433 participants and analyzed using nine categorical machine learning algorithms to select features based on demographic and clinical variables. Multiple classification models were compared using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, sensitivity, specificity, the average precision (AP), precision, F1 score, precision-recall curves, calibration plots, and decision curve analysis (DCA) to determine the best model. In addition, 5-fold cross-validation was utilized to optimize the model, followed by an evaluation of feature significance using Shapley Additive exPlanations (SHAP). Using latent class analysis (LCA), distinct subpopulations were identified by constructing several discrete clusters.

Results

In this study, nine feature variables were identified to construct predictive models for osteoporosis in individuals with T2DM. The machine learning algorithms achieved an AP range of 0.444-1.000. The XGBoost model was selected as the final prediction model with an AUROC of 0.940 in the training set, 0.772 in the validation set for 5-fold cross-validation, and 0.872 in the test set. Using SHAP methodology, 25(OH)D was identified as the most important risk factor. Additionally, a 3-Class model was constructed using LCA, which categorized individuals into high, medium, and low-risk groups.

Conclusion

Our study developed a predictive model with high accuracy and clinical validity for predicting osteoporosis in type 2 diabetes patients. We also identified three subpopulations with varying osteoporosis risk using clustering. However, limited sample size warrants cautious interpretation of results, and validation in larger cohorts is needed.

Prediction of subjective cognitive decline after corpus callosum infarction by an interpretable machine learning-derived early warning strategy

Background and purpose

Corpus callosum (CC) infarction is an extremely rare subtype of cerebral ischemic stroke, however, the symptoms of cognitive impairment often fail to attract early attention of patients, which seriously affects the long-term prognosis, such as high mortality, personality changes, mood disorders, psychotic reactions, financial burden and so on. This study seeks to develop and validate models for early predicting the risk of subjective cognitive decline (SCD) after CC infarction by machine learning (ML) algorithms.

Methods

This is a prospective study that enrolled 213 (only 3.7%) CC infarction patients from a nine-year cohort comprising 8,555 patients with acute ischemic stroke. Telephone follow-up surveys were carried out for the patients with definite diagnosis of CC infarction one-year after disease onset, and SCD was identified by Behavioral Risk Factor Surveillance System (BRFSS) questionnaire. Based on the significant features selected by the least absolute shrinkage and selection operator (LASSO), seven ML models including Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Gaussian Naïve Bayes (GNB), Complement Naïve Bayes (CNB), and Support vector machine (SVM) were established and their predictive performances were compared by different metrics. Importantly, the SHapley Additive exPlanations (SHAP) was also utilized to examine internal behavior of the highest-performance ML classifier.

Results

The Logistic Regression (LR)-model performed better than other six ML-models in SCD predictability after the CC infarction, with the area under the receiver characteristic operator curve (AUC) of 77.1% in the validation set. Using LASSO and SHAP analysis, we found that infarction subregions of CC infarction, female, 3-month modified Rankin Scale (mRS) score, age, homocysteine, location of angiostenosis, neutrophil to lymphocyte ratio, pure CC infarction, and number of angiostenosis were the top-nine significant predictors in the order of importance for the output of LR-model. Meanwhile, we identified that infarction subregion of CC, female, 3-month mRS score and pure CC infarction were the factors which independently associated with the cognitive outcome.

Conclusion

Our study firstly demonstrated that the LR-model with 9 common variables has the best-performance to predict the risk of post-stroke SCD due to CC infarcton. Particularly, the combination of LR-model and SHAP-explainer could aid in achieving personalized risk prediction and be served as a decision-making tool for early intervention since its poor long-term outcome.

Prediction of Mortality among Patients with Isolated Traumatic Brain Injury Using Machine Learning Models in Asian Countries: An International Multi-Center Cohort Study

Traumatic brain injury (TBI) is a significant healthcare concern in several countries, accounting for a major burden of morbidity, mortality, disability, and socioeconomic losses. Although conventional prognostic models for patients with TBI have been validated, their performance has been limited. Therefore, we aimed to construct machine learning (ML) models to predict the clinical outcomes in adult patients with isolated TBI in Asian countries. The Pan-Asian Trauma Outcome Study registry was used in this study, and the data were prospectively collected from January 1, 2015, to December 31, 2020. Among a total of 6540 patients (≥ 15 years) with isolated moderate and severe TBI, 3276 (50.1%) patients were randomly included with stratification by outcomes and subgrouping variables for model evaluation, and 3264 (49.9%) patients were included for model training and validation. Logistic regression was considered as a baseline, and ML models were constructed and evaluated using the area under the precision-recall curve (AUPRC) as the primary outcome metric, area under the receiver operating characteristic curve (AUROC), and precision at fixed levels of recall. The contribution of the variables to the model prediction was measured using the SHapley Additive exPlanations (SHAP) method. The ML models outperformed logistic regression in predicting the in-hospital mortality. Among the tested models, the gradient-boosted decision tree showed the best performance (AUPRC, 0.746 [0.700-0.789]; AUROC, 0.940 [0.929-0.952]). The most powerful contributors to model prediction were the Glasgow Coma Scale, O₂ saturation, transfusion, systolic and diastolic blood pressure, body temperature, and age. Our study suggests that ML techniques might perform better than conventional multi-variate models in predicting the outcomes among adult patients with isolated moderate and severe TBI.

Machine learning determination of applied behavioral analysis treatment plan type

BACKGROUND

Applied behavioral analysis (ABA) is regarded as the gold standard treatment for autism spectrum disorder (ASD) and has the potential to improve outcomes for patients with ASD. It can be delivered at different intensities, which are classified as comprehensive or focused treatment approaches. Comprehensive ABA targets multiple developmental domains and involves 20-40 h/week of treatment. Focused ABA targets individual behaviors and typically involves 10-20 h/week of treatment. Determining the appropriate treatment intensity involves patient assessment by trained therapists, however, the final determination is highly subjective and lacks a standardized approach. In our study, we examined the ability of a machine learning (ML) prediction model to classify which treatment intensity would be most suited individually for patients with ASD who are undergoing ABA treatment.

METHODS

Retrospective data from 359 patients diagnosed with ASD were analyzed and included in the training and testing of an ML model for predicting comprehensive or focused treatment for individuals undergoing ABA treatment. Data inputs included demographics, schooling, behavior, skills, and patient goals. A gradient-boosted tree ensemble method, XGBoost, was used to develop the prediction model, which was then compared against a standard of care comparator encompassing features specified by the Behavior Analyst Certification Board treatment guidelines. Prediction model performance was assessed via area under the receiver-operating characteristic curve (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

The prediction model achieved excellent performance for classifying patients in the comprehensive versus focused treatment groups (AUROC: 0.895; 95% CI 0.811-0.962) and outperformed the standard of care comparator (AUROC 0.767; 95% CI 0.629-0.891). The prediction model also achieved sensitivity of 0.789, specificity of 0.808, PPV of 0.6, and NPV of 0.913. Out of 71 patients whose data were employed to test the prediction model, only 14 misclassifications occurred. A majority of misclassifications (n = 10) indicated comprehensive ABA treatment for patients that had focused ABA treatment as the ground truth, therefore still providing a therapeutic benefit. The three most important features contributing to the model's predictions were bathing ability, age, and hours per week of past ABA treatment.

CONCLUSION

This research demonstrates that the ML prediction model performs well to classify appropriate ABA treatment plan intensity using readily available patient data. This may aid with standardizing the process for determining appropriate ABA treatments, which can facilitate initiation of the most appropriate treatment intensity for patients with ASD and improve resource allocation.

An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data

Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients' class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.

Machine learning approaches for biomolecular, biophysical, and biomaterials research

A fluent conversation with a virtual assistant, person-tailored news feeds, and deep-fake images created within seconds-all those things that have been unthinkable for a long time are now a part of our everyday lives. What these examples have in common is that they are realized by different means of machine learning (ML), a technology that has fundamentally changed many aspects of the modern world. The possibility to process enormous amount of data in multi-hierarchical, digital constructs has paved the way not only for creating intelligent systems but also for obtaining surprising new insight into many scientific problems. However, in the different areas of biosciences, which typically rely heavily on the collection of time-consuming experimental data, applying ML methods is a bit more challenging: Here, difficulties can arise from small datasets and the inherent, broad variability, and complexity associated with studying biological objects and phenomena. In this Review, we give an overview of commonly used ML algorithms (which are often referred to as "machines") and learning strategies as well as their applications in different bio-disciplines such as molecular biology, drug development, biophysics, and biomaterials science. We highlight how selected research questions from those fields were successfully translated into machine readable formats, discuss typical problems that can arise in this context, and provide an overview of how to resolve those encountered difficulties.

Machine learning in the detection and management of atrial fibrillation

Machine learning has immense novel but also disruptive potential for medicine. Numerous applications have already been suggested and evaluated concerning cardiovascular diseases. One important aspect is the detection and management of potentially thrombogenic arrhythmias such as atrial fibrillation. While atrial fibrillation is the most common arrhythmia with a lifetime risk of one in three persons and an increased risk of thromboembolic complications such as stroke, many atrial fibrillation episodes are asymptomatic and a first diagnosis is oftentimes only reached after an embolic event. Therefore, screening for atrial fibrillation represents an important part of clinical practice. Novel technologies such as machine learning have the potential to substantially improve patient care and clinical outcomes. Additionally, machine learning applications may aid cardiologists in the management of patients with already diagnosed atrial fibrillation, for example, by identifying patients at a high risk of recurrence after catheter ablation. We summarize the current state of evidence concerning machine learning and, in particular, artificial neural networks in the detection and management of atrial fibrillation and describe possible future areas of development as well as pitfalls.

Prediction of hearing recovery in unilateral sudden sensorineural hearing loss using artificial intelligence

Despite the significance of predicting the prognosis of idiopathic sudden sensorineural hearing loss (ISSNHL), no predictive models have been established. This study used artificial intelligence to develop prognosis models to predict recovery from ISSNHL. We retrospectively reviewed the medical data of 453 patients with ISSNHL (men, 220; women, 233; mean age, 50.3 years) who underwent treatment at a tertiary hospital between January 2021 and December 2019 and were followed up after 1 month. According to Siegel's criteria, 203 patients recovered in 1 month. Demographic characteristics, clinical and laboratory data, and pure-tone audiometry were analyzed. Logistic regression (baseline), a support vector machine, extreme gradient boosting, a light gradient boosting machine, and multilayer perceptron were used. The outcomes were the area under the receiver operating characteristic curve (AUROC) primarily, area under the precision-recall curve, Brier score, balanced accuracy, and F1 score. The light gradient boosting machine model had the best AUROC and balanced accuracy. Together with multilayer perceptron, it was also significantly superior to logistic regression in terms of AUROC. Using the SHapley Additive exPlanation method, we found that the initial audiogram shape is the most important prognostic factor. Machine/deep learning methods were successfully established to predict the prognosis of ISSNHL.