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.

Deoxyguanosine kinase deficiency: natural history and liver transplant outcome.

Autosomal recessive pathogenetic variants in the DGUOK gene cause deficiency of deoxyguanosine kinase activity and mitochondrial deoxynucleotides pool imbalance, consequently, leading to quantitative and/or qualitative impairment of mitochondrial DNA synthesis. Typically, patients present early-onset liver failure with or without neurological involvement and a clinical course rapidly progressing to death. This is an international multicentre study aiming to provide a retrospective natural history of deoxyguanosine kinase deficient patients. A systematic literature review from January 2001 to June 2023 was conducted. Physicians of research centres or clinicians all around the world caring for previously reported patients were contacted to provide followup information or additional clinical, biochemical, histological/histochemical, and molecular genetics data for unreported cases with a confirmed molecular diagnosis of deoxyguanosine kinase deficiency. A cohort of 202 genetically confirmed patients, 36 unreported, and 166 from a systematic literature review, were analyzed. Patients had a neonatal onset (≤ 1 month) in 55.7% of cases, infantile (>1 month and ≤ 1 year) in 32.3%, pediatric (>1 year and ≤18 years) in 2.5% and adult (>18 years) in 9.5%. Kaplan-Meier analysis showed statistically different survival rates (P < 0.0001) among the four age groups with the highest mortality for neonatal onset. Based on the clinical phenotype, we defined four different clinical subtypes: hepatocerebral (58.8%), isolated hepatopathy (21.9%), hepatomyoencephalopathy (9.6%), and isolated myopathy (9.6%). Muscle involvement was predominant in adult-onset cases whereas liver dysfunction causes morbidity and mortality in early-onset patients with a median survival of less than 1 year. No genotype-phenotype correlation was identified. Liver transplant significantly modified the survival rate in 26 treated patients when compared with untreated. Only six patients had additional mild neurological signs after liver transplant. In conclusion, deoxyguanosine kinase deficiency is a disease spectrum with a prevalent liver and brain tissue specificity in neonatal and infantile-onset patients and muscle tissue specificity in adult-onset cases. Our study provides clinical, molecular genetics and biochemical data for early diagnosis, clinical trial planning and immediate intervention with liver transplant and/or nucleoside supplementation.

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.