Predicting clinical events characterizing the progression of amyotrophic lateral sclerosis via machine learning approaches using routine visits data: a feasibility study.

BACKGROUND: Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease that results in death within a short time span (3-5 years). One of the major challenges in treating ALS is its highly heterogeneous disease progression and the lack of effective prognostic tools to forecast it. The main aim of this study was, then, to test the feasibility of predicting relevant clinical outcomes that characterize the progression of ALS with a two-year prediction horizon via artificial intelligence techniques using routine visits data. METHODS: Three classification problems were considered: predicting death (binary problem), predicting death or percutaneous endoscopic gastrostomy (PEG) (multiclass problem), and predicting death or non-invasive ventilation (NIV) (multiclass problem). Two supervised learning models, a logistic regression (LR) and a deep learning multilayer perceptron (MLP), were trained ensuring technical robustness and reproducibility. Moreover, to provide insights into model explainability and result interpretability, model coefficients for LR and Shapley values for both LR and MLP were considered to characterize the relationship between each variable and the outcome. RESULTS: On the one hand, predicting death was successful as both models yielded F1 scores and accuracy well above 0.7. The model explainability analysis performed for this outcome allowed for the understanding of how different methodological approaches consider the input variables when performing the prediction. On the other hand, predicting death alongside PEG or NIV proved to be much more challenging (F1 scores and accuracy in the 0.4-0.6 interval). CONCLUSIONS: In conclusion, predicting death due to ALS proved to be feasible. However, predicting PEG or NIV in a multiclass fashion proved to be unfeasible with these data, regardless of the complexity of the methodological approach. The observed results suggest a potential ceiling on the amount of information extractable from the database, e.g., due to the intrinsic difficulty of the prediction tasks at hand, or to the absence of crucial predictors that are, however, not currently collected during routine practice.

Supervised and Unsupervised Approaches for the Real-Time Detection of Undesired Insulin Suspension Caused by Malfunctions.

BACKGROUND: Automated insulin delivery (AID) systems, permit improved treatment of type 1 diabetes (T1D). Unfortunately, malfunctioning in the insulin pump or in the infusion set can prevent insulin from being administered, reducing the AID efficacy and posing the patient at risk. Different data-driven methods available in the literature can be used to deal with the problem of automatically detecting complete insulin suspension in real-time. This article investigates both supervised and unsupervised strategies and proposes a fair comparison under either population or personalized settings. METHODS: Several algorithms are compared using data generated through the UVA/Padova T1D simulator, a computer simulator widely used to test control strategies in silico and accepted by the Food and Drugs Administration (FDA) as a substitute to animal pre-clinical trials. Two synthetic data sets, each consisting of 100 virtual subjects monitored for 1 month, were generated. Occasional faults of the insulin pump are simulated as complete occlusions by suspending the therapy administration. Personalized algorithms are investigated with unsupervised approaches only, since personalized labels are hardly available. RESULTS: In the population scenario, the supervised approach outperforms the unsupervised strategy. In particular, logistic regression and random forest achieves a recall of 72% and 82%, with 0.12 and 0.21 false positives (FP) per day, respectively. In the personalized setting scenario, the unsupervised algorithms are tailored on each patient and outperform the population ones, in particular isolation forest achieves a recall 80% and 0.06 FPs per day. CONCLUSIONS: This article suggests that unsupervised personalized approach, by addressing the large variability in glucose response among individuals with T1D, is superior to other one-fits-all approaches in detecting insulin suspensions caused by malfunctioning. Population methodologies can be effectively used while waiting to collect sufficient patient data, when the system is installed on a new patient.

Unsupervised Retrospective Detection of Pressure Induced Failures in Continuous Glucose Monitoring Sensors for T1D Management.

Continuous Glucose Monitoring sensors (CGMs) have revolutionized type 1 diabetes (T1D) management. In particular, in several cases, the retrospective analysis of CGM recordings allows clinicians to review and adjust patients' therapy. However, in this set-up, the artifacts that are often present in CGM data could lead to incorrect therapeutic actions. To mitigate this risk, we investigate how to detect one of the most common of these artifacts, the so-called pressure induced sensor attenuations, by means of anomaly detection algorithms. Specifically, these methods belong to the class of unsupervised techniques, which is particularly appealing since it does not require a labeled dataset, hardly available in practice. After having designed five features to highlight the anomalous state of the sensor, 8 different methods (e.g. Isolation Forest and Histogram-based Outlier Score) are assessed both in silico using the UVa/Padova Type 1 Diabetes Simulator and on real data of 36 subjects monitored for about 10 days. In the in silico scenario, the best results are achieved with Isolation Forest, which recognized the 74% of the failures generating on average only 2 false alerts during the whole monitoring time. In real data, Isolation Forest is confirmed to be effective in the detection of failures, achieving a recall of 55% and generating 3 false alarms in 10 days. By allowing to detect more than 50% of the artifacts while discarding only a few portions of correct data in several days of monitoring, the proposed approach could effectively improve the quality of CGM data used by clinicians to retrospectively evaluate and adjust T1D therapy.

Data-Driven Supervised Compression Artifacts Detection on Continuous Glucose Sensors.

Continuous Glucose Monitoring (CGM) sensors micro-invasively provide frequent glucose readings, improving the management of Type 1 diabetic patients' life and making available reach data-sets for retrospective analysis. Unlikely, CGM sensors are subject to failures, such as compression artifacts, that might impact on both real-time and respective CGM use. In this work is focused on retrospective detection of compression artifacts. An in-silico dataset is generated using the T1D UVa/Padova simulator and compression artifacts are subsequently added in known position, thus creating a dataset with perfectly accurate faulty/not-faulty labels. The problem of compression artifact detection is then faced with supervised data-driven techniques, in particular using Random Forest algorithm. The detection performance guaranteed by the method on in-silico data is satisfactory, opening the way for further analysis on real-data.