Body Sensor Networks and AI to Advance Personalized and Population Healthcare
Permanent URI for this collectionhttps://hdl.handle.net/10125/112474
Browse
Recent Submissions
Item type: Item , Detecting Ethanol Intoxication and Impairment Using Wearable Biosensors(2026-01-06) Kaczor, Eric; Golleru, Manohar; Carter, Daniel; Painter, Orian; Kelleran, Kyle; Lynch, Joshua; Clemency, Brian; Cavuoto, Lora; Chai, Peter R.Reliable objective measures of a person’s intoxication and impairment from alcohol consumption are not readily available to the public. Wearable biosensors have the potential to provide a ubiquitous on-demand tool to deliver this kind of objective assessment in real world settings. This study evaluated the feasibility of assessing ethanol intoxication in N=28 healthy participants in a police academy’s intoxication lab using wrist-worn biosensors to continuously measure heart rate, skin temperature, electrodermal activity, and accelerometry. Participants consumed ad hoc standard alcoholic drinks in a controlled setting and had regular breath alcohol content assessments and underwent standard field sobriety testing. The analysis showed statistically significant changes in each physiologic parameter between the sober and intoxicated periods. An XGBoost model was applied to this data producing machine learning algorithms to identify impairment with an accuracy as high as 0.80. These results demonstrate that it is feasible to assess ethanol intoxication using wrist-worn biosensors.Item type: Item , AI-Based Skin Disease Diagnosis with Non-Dermoscopic Images: Tackling Bias and Data Limitations(2026-01-06) Bellatreccia, Chiara; Zama, Daniele; Dondi, Arianna; Pierantoni, Luca; Andreozzi, Laura; Neri, Iria; Lanari, Marcello; Borghesi, Andrea; Calegari, RobertaAI-based skin disease diagnosis holds significant potential for improving healthcare equity but remains challenged by fairness concerns, particularly in underrepresented populations. This study addresses these issues using a real-world dataset from an Italian hospital, which suffers from limited diversity in skin tones and disease classes, as well as non-dermoscopic, low-quality images captured under inconsistent conditions. These factors contribute to classification bias and hinder existing fairness mitigation strategies. We propose a novel two-stage pipeline that combines (1) targeted data augmentation using DreamBooth fine-tuned Stable Diffusion to generate synthetic images for darker skin tones, and (2) disease classification using a Swin Transformer model. Our results show improved fairness metrics and balanced performance across skin tone groups, demonstrating the effectiveness of synthetic data in reducing dermatological AI bias.Item type: Item , Feasibility of a Wearable Remote Monitoring Device for Patients Treated for Opioid Use Disorder in a Telehealth Program(2026-01-06) Weiner, Scott; Brookins, Trace; Shaw, Jesse; Coleman, Natalie; Reeser, David; Clear, Brian; Donlin Washington, Wendy; Macqueen, DavidOpioid use disorder (OUD) is increasingly prevalent in the United States. Telehealth-only OUD treatment with buprenorphine, first permitted during the COVID-19 pandemic, has expanded access but the modality complicates monitoring medication adherence and withdrawal symptoms. Remote patient monitoring (RPM) using smartwatch biometric sensors may improve telehealth OUD care, but feasibility is unknown. Patients (N=15) newly treated in a telehealth OUD program receiving buprenorphine were enrolled. Subjects were instructed to wear a smartwatch continuously, except during charging, for ten days. Adherence, defined as the proportion of hours in which at least one biometric data capture occurred, was measured. The mean adherence was 38.9%. Six patients (40.0%) demonstrated high adherence (>50%), and nine (60.0%) had low adherence. Although adherence was suboptimal, smartwatch-based RPM may be feasible in a telehealth-only OUD treatment program for some patients.Item type: Item , Implementation Barriers to Digital Mental Health Screening: A Qualitative Study of CAT-MH Implementations(2026-01-06) Huang, Kaidi; Tulu, Bengisu; Johnson, Sharon; Davis-Martin, RachelThe implementation of digital mental health screening tools shows promise for better identifying mental health needs in primary care settings, but their adoption remains challenging. This study uses CAT-MH as an example to investigate implementation barriers that prevent these tools from being integrated into clinical workflows across various healthcare settings. Following an exploratory qualitative design, we conducted interviews with eight healthcare professionals who have practical experience in implementing CAT-MH in their institutions. We used the EPIS framework to develop interview protocols and data analysis procedures. Our analysis revealed three primary barriers to implementation of CAT-MH: (1) EHR integration, (2) ambiguous role definitions and (3) insufficient organizational support. Our findings indicate that institutional-level coordination between stakeholders that influence system-wide implementation and clinical workflows must improve to support both effective integration and sustained use of innovative digital screening tool.Item type: Item , Introduction to the Minitrack on Body Sensor Networks and AI to Advance Personalized and Population Healthcare(2026-01-06) Goldfine, Charlotte; Lee, Jasper; Davis-Martin, Rachel