Machine Learning Modeling to Predict Atrial Fibrillation Detection in Embolic Stroke of Undetermined Source Patients.

BACKGROUND: In patients with embolic stroke of undetermined source (ESUS), occult atrial fibrillation (AF) has been implicated as a key source of cardioembolism. However, only a minority acquire implantable cardiac loop recorders (ILRs) to detect occult paroxysmal AF, partly due to financial cost and procedural inconvenience. Without the initiation of appropriate anticoagulation, these patients are at risk of increased ischemic stroke recurrence. Hence, cost-effective and accurate methods of predicting AF in ESUS patients are highly sought after. OBJECTIVE: We aimed to incorporate clinical and echocardiography data into machine learning (ML) algorithms for AF prediction on ILRs in ESUS. METHODS: This was a single-center cohort study that included 157 consecutive patients diagnosed with ESUS from October 2014 to October 2017 who had ILR evaluation. We developed four ML models, with hyperparameters tuned, to predict AF detection on an ILR. RESULTS: The median age of the cohort was 67 (IQR 59-74) years old and the median monitoring duration was 1051 (IQR 478-1287) days. Of the 157 patients, 32 (20.4%) had occult AF detected on the ILR. Support vector machine predicted for AF with a 95% confidence interval area under the receiver operating characteristic curve (AUC) of 0.736-0.737, multilayer perceptron with an AUC of 0.697-0.708, XGBoost with an AUC of 0.697-0.697, and random forest with an AUC of 0.663-0.674. ML feature importance found that age, HDL-C, and admitting heart rate were important non-echocardiography variables, while peak mitral A-wave velocity and left atrial volume were important echocardiography parameters aiding this prediction. CONCLUSION: Machine learning modeling incorporating clinical and echocardiographic variables predicted AF in ESUS patients with moderate accuracy.

Prognostication of Outcomes in Spontaneous Intracerebral Hemorrhage: A Propensity Score-Matched Analysis with Support Vector Machine.

OBJECTIVE: The role of surgery in spontaneous intracerebral hemorrhage (SICH) remains controversial. We aimed to use explainable machine learning (ML) combined with propensity-score matching to investigate the effects of surgery and identify subgroups of patients with SICH who may benefit from surgery in an interpretable fashion. METHODS: We conducted a retrospective study of a cohort of 282 patients aged ≥21 years with SICH. ML models were developed to separately predict for surgery and surgical evacuation. SHapley Additive exPlanations (SHAP) values were calculated to interpret the predictions made by ML models. Propensity-score matching was performed to estimate the effect of surgery and surgical evacuation on 90-day poor functional outcomes (PFO). RESULTS: Ninety-two patients (32.6%) underwent surgery, and 57 patients (20.2%) underwent surgical evacuation. A total of 177 patients (62.8%) had 90-day PFO. The support vector machine achieved a c-statistic of 0.915 when predicting 90-day PFO for patients who underwent surgery and a c-statistic of 0.981 for patients who underwent surgical evacuation. The SHAP scores for the top 5 features were Glasgow Coma Scale score (0.367), age (0.214), volume of hematoma (0.258), location of hematoma (0.195), and ventricular extension (0.164). Surgery, but not surgical evacuation of the hematoma, was significantly associated with improved mortality at 90-day follow-up (odds ratio, 0.26; 95% confidence interval, 0.10-0.67; P = 0.006). CONCLUSIONS: Explainable ML approaches could elucidate how ML models predict outcomes in SICH and identify subgroups of patients who respond to surgery. Future research in SICH should focus on an explainable ML-based approach that can identify subgroups of patients who may benefit functionally from surgical intervention.

Developing an Artificial Intelligence-Driven Nudge Intervention to Improve Medication Adherence: A Human-Centred Design Approach.

To improve medication adherence, we co-developed a digital, artificial intelligence (AI)-driven nudge intervention with stakeholders (patients, providers, and technologists). We used a human-centred design approach to incorporate user needs in creating an AI-driven nudge tool. We report the findings of the first stage of a multi-phase project: understanding user needs and ideating solutions. We interviewed healthcare providers (n = 10) and patients (n = 10). Providers also rated example nudge interventions in a survey. Stakeholders felt the intervention could address existing deficits in medication adherence tracking and were optimistic about the solution. Participants identified flexibility of the intervention, including mode of delivery, intervention intensity, and the ability to stratify to user ability and needs, as critical success factors. Reminder nudges and provision of healthcare worker contact were rated highly by all. Conversely, patients perceived incentive-based nudges poorly. Finally, participants suggested that user burden could be minimised by leveraging existing software (rather than creating a new App) and simplifying or automating the data entry requirements where feasible. Stakeholder interviews generated in-depth data on the perspectives and requirements for the proposed solution. The participatory approach will enable us to incorporate user needs into the design and improve the utility of the intervention. Our findings show that an AI-driven nudge tool is an acceptable and appropriate solution, assuming it is flexible to user requirements.

The role of intracranial pressure variability as a predictor of intracranial hypertension and mortality in critically ill patients.

OBJECTIVE: Intracranial pressure (ICP) monitoring is a widely utilized and essential tool for tracking neurosurgical patients, but there are limitations to the use of a solely ICP-based paradigm for guiding management. It has been suggested that ICP variability (ICPV), in addition to mean ICP, may be a useful predictor of neurological outcomes, as it represents an indirect measure of intact cerebral pressure autoregulation. However, the current literature regarding the applicability of ICPV shows conflicting associations between ICPV and mortality. Thus, the authors aimed to investigate the effect of ICPV on intracranial hypertensive episodes and mortality using the eICU Collaborative Research Database version 2.0. METHODS: The authors extracted from the eICU database 1,815,676 ICP readings from 868 patients with neurosurgical conditions. ICPV was computed using two methods: the rolling standard deviation (RSD) and the absolute deviation from the rolling mean (DRM). An episode of intracranial hypertension was defined as at least 25 minutes of ICP > 22 mm Hg in any 30-minute window. The effects of mean ICPV on intracranial hypertension and mortality were computed using multivariate logistic regression. A recurrent neural network with long short-term memory was used for time-series predictions of ICP and ICPV to prognosticate future episodes of intracranial hypertension. RESULTS: A higher mean ICPV was significantly associated with intracranial hypertension using both ICPV definitions (RSD: aOR 2.82, 95% CI 2.07-3.90, p < 0.001; DRM: aOR 3.93, 95% CI 2.77-5.69, p < 0.001). ICPV was significantly associated with mortality in patients with intracranial hypertension (RSD: aOR 1.28, 95% CI 1.04-1.61, p = 0.026, DRM: aOR 1.39, 95% CI 1.10-1.79, p = 0.007). In the machine learning models, both definitions of ICPV achieved similarly good results, with the best F1 score of 0.685 ± 0.026 and an area under the curve of 0.980 ± 0.003 achieved with the DRM definition over 20 minutes. CONCLUSIONS: ICPV may be useful as an adjunct for the prognostication of intracranial hypertensive episodes and mortality in neurosurgical critical care as part of neuromonitoring. Further research on predicting future intracranial hypertensive episodes with ICPV may help clinicians react expediently to ICP changes in patients.

Personalised Dosing Using the CURATE.AI Algorithm: Protocol for a Feasibility Study in Patients with Hypertension and Type II Diabetes Mellitus.

Chronic diseases typically require long-term management through healthy lifestyle practices and pharmacological intervention. Although efficacious treatments exist, disease control is often sub-optimal leading to chronic disease-related sequela. Poor disease control can partially be explained by the 'one size fits all' pharmacological approach. Precision medicine aims to tailor treatments to the individual. CURATE.AI is a dosing optimisation platform that considers individual factors to improve the precision of drug therapies. CURATE.AI has been validated in other therapeutic areas, such as cancer, but has yet to be applied in chronic disease care. We will evaluate the CURATE.AI system through a single-arm feasibility study (n = 20 hypertensives and n = 20 type II diabetics). Dosing decisions will be based on CURATE.AI recommendations. We will prospectively collect clinical and qualitative data and report on the clinical effect, implementation challenges, and acceptability of using CURATE.AI. In addition, we will explore how to enhance the algorithm further using retrospective patient data. For example, the inclusion of other variables, the simultaneous optimisation of multiple drugs, and the incorporation of other artificial intelligence algorithms. Overall, this project aims to understand the feasibility of using CURATE.AI in clinical practice. Barriers and enablers to CURATE.AI will be identified to inform the system's future development.

Machine Learning Models Prognosticate Functional Outcomes Better than Clinical Scores in Spontaneous Intracerebral Haemorrhage.

OBJECTIVE: This study aims to develop and compare the use of deep neural networks (DNN) and support vector machines (SVM) to clinical prognostic scores for prognosticating 30-day mortality and 90-day poor functional outcome (PFO) in spontaneous intracerebral haemorrhage (SICH). MATERIALS AND METHODS: We conducted a retrospective cohort study of 297 SICH patients between December 2014 and May 2016. Clinical data was collected from electronic medical records using standardized data collection forms. The machine learning workflow included imputation of missing data, dimensionality reduction, imbalanced-class correction, and evaluation using cross-validation and comparison of accuracy against clinical prognostic scores. RESULTS: 32 (11%) patients had 30-day mortality while 177 (63%) patients had 90-day PFO. For prognosticating 30-day mortality, the class-balanced accuracies for DNN (0.875; 95% CI 0.800-0.950; McNemar's p-value 1.000) and SVM (0.848; 95% CI 0.767-0.930; McNemar's p-value 0.791) were comparable to that of the original ICH score (0.833; 95% CI 0.748-0.918). The c-statistics for DNN (0.895; DeLong's p-value 0.715), and SVM (0.900; DeLong's p-value 0.619), though greater than that of the original ICH score (0.862), were not significantly different. For prognosticating 90-day PFO, the class-balanced accuracies for DNN (0.853; 95% CI 0.772-0.934; McNemar's p-value 0.003) and SVM (0.860; 95% CI 0.781-0.939; McNemar's p-value 0.004) were better than that of the ICH-Grading Scale (0.706; 95% CI 0.600-0.812). The c-statistic for SVM (0.883; DeLong's p-value 0.022) was significantly greater than that of the ICH-Grading Scale (0.778), while the c-statistic for DNN was 0.864 (DeLong's p-value 0.055). CONCLUSION: We showed that the SVM model performs significantly better than clinical prognostic scores in predicting 90-day PFO in SICH.

Optimizing Autoencoders for Learning Deep Representations From Health Data.

Analyzing patients' health data using machine learning techniques can improve both patient outcomes and hospital operations. However, heterogeneous patient data (e.g., vital signs) and inefficient feature learning methods affect the implementation of machine learning-based patient data analysis. In this paper, we present a novel unsupervised deep learning-based feature learning (DFL) framework to automatically learn compact representations from patient health data for efficient clinical decision making. Real-world pneumonia patient data from the National University Hospital in Singapore are collected and analyzed to evaluate the performance of DFL. Furthermore, publicly available electroencephalogram data are extracted from the UCI Machine Learning Repository to test and support our findings. Using both data sets, we compare the performance of DFL to that of several popular feature learning methods and demonstrate its advantages.