1) MacKenzie, J., Coric, C., Kim, Y.W., Lee, C., Grant-Kels, J.M.
Current applications of artificial intelligence in dermatology offices and potential ethical landmines
(2025) Clinics in Dermatology, .
Abstract
We review the ethical issues surrounding the use of artificial intelligence (AI) in medical offices, focusing on dermatology. Although previously reviewed, there have been significant advances in the employment of AI in various office tasks over the last year, accompanied by increased acceptance among dermatologists. There is now a plethora of applications for AI in our practices to enhance efficiency, streamline administrative tasks, and reduce physician burnout. Physicians should consider several ethical issues before employing AI, including informed consent, accuracy, privacy, trust/truthfulness, beneficence, nonmaleficence, staff displacement with the associated loss of human contact, bias, and justice or equity. In scenarios where AI proves to be inaccurate, we also need to resolve liability or accountability. We review the various applications of AI in our clinical practice and outline its benefits, including the ethical considerations necessary to use this technology to enhance our practices. © 2025 Elsevier Inc.
2) Areias, A.C., Janela, D., Moulder, R.G., Molinos, M., Bento, V., Moreira, C., Yanamadala, V., Correia, F.D., Costa, F.
Applying AI to Safely and Effectively Scale Care to Address Chronic MSK Conditions
(2024) Journal of Clinical Medicine, 13 (15), art. no. 4366, .
Abstract
Background/Objectives: The rising prevalence of musculoskeletal (MSK) conditions has not been balanced by a sufficient increase in healthcare providers. Scalability challenges are being addressed through the use of artificial intelligence (AI) in some healthcare sectors, with this showing potential to also improve MSK care. Digital care programs (DCP) generate automatically collected data, thus making them ideal candidates for AI implementation into workflows, with the potential to unlock care scalability. In this study, we aimed to assess the impact of scaling care through AI in patient outcomes, engagement, satisfaction, and adverse events. Methods: Post hoc analysis of a prospective, pre-post cohort study assessing the impact on outcomes after a 2.3-fold increase in PT-to-patient ratio, supported by the implementation of a machine learning-based tool to assist physical therapists (PTs) in patient care management. The intervention group (IG) consisted of a DCP supported by an AI tool, while the comparison group (CG) consisted of the DCP alone. The primary outcome concerned the pain response rate (reaching a minimal clinically important change of 30%). Other outcomes included mental health, program engagement, satisfaction, and the adverse event rate. Results: Similar improvements in pain response were observed, regardless of the group (response rate: 64% vs. 63%; p = 0.399). Equivalent recoveries were also reported in mental health outcomes, specifically in anxiety (p = 0.928) and depression (p = 0.187). Higher completion rates were observed in the IG (79.9% (N = 19,252) vs. CG 70.1% (N = 8489); p < 0.001). Patient engagement remained consistent in both groups, as well as high satisfaction (IG: 8.76/10, SD 1.75 vs. CG: 8.60/10, SD 1.76; p = 0.021). Intervention-related adverse events were rare and even across groups (IG: 0.58% and CG 0.69%; p = 0.231). Conclusions: The study underscores the potential of scaling MSK care that is supported by AI without compromising patient outcomes, despite the increase in PT-to-patient ratios. © 2024 by the authors.
3) Obuchi, S.P., Kojima, M., Suzuki, H., Garbalosa, J.C., Imamura, K., Ihara, K., Hirano, H., Sasai, H., Fujiwara, Y., Kawai, H.
Artificial intelligence detection of cognitive impairment in older adults during walking
(2024) Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring, 16 (3), art. no. e70012, .
Abstract
INTRODUCTION: To detect early cognitive impairment in community-dwelling older adults, this study explored the viability of artificial intelligence (AI)-assisted linear acceleration and angular velocity analysis during walking. METHODS: This cross-sectional study included 879 participants without dementia (female, 60.6%; mean age, 73.5 years) from the 2011 Comprehensive Gerontology Survey. Sensors attached to the pelvis and left ankle recorded the triaxial linear acceleration and angular velocity while the participants walked at a comfortable speed. Cognitive impairment was determined using Mini-Mental State Examination scores. Deep learning models were used to discern the linear acceleration and angular velocity data of 12,302 walking strides. RESULTS: The models’ average sensitivity, specificity, and area under the curve were 0.961, 0.643, and 0.833, respectively, across 30 testing datasets. DISCUSSION: AI-enabled gait analysis can be used to detect signs of cognitive impairment. Integrating this AI model into smartphones may help detect dementia early, facilitating better prevention. Highlights: Artificial intelligence (AI)-enabled gait analysis can be used to detect the early signs of cognitive decline. This AI model was constructed using data from a community-dwelling cohort. AI-assisted linear acceleration and angular velocity analysis during gait was used. The model may help in early detection of dementia. © 2024 The Author(s). Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring published by Wiley Periodicals LLC on behalf of Alzheimer's Association.
4) Areias, A.C., Moulder, R.G., Molinos, M., Janela, D., Bento, V., Moreira, C., Yanamadala, V., Cohen, S.P., Correia, F.D., Costa, F.
Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
(2024) JMIR Medical Informatics, 12, art. no. e64806, .
Abstract
Background: Low back pain (LBP) presents with diverse manifestations, necessitating personalized treatment approaches that recognize various phenotypes within the same diagnosis, which could be achieved through precision medicine. Although prediction strategies have been explored, including those employing artificial intelligence (AI), they still lack scalability and real-time capabilities. Digital care programs (DCPs) facilitate seamless data collection through the Internet of Things and cloud storage, creating an ideal environment for developing and implementing an AI predictive tool to assist clinicians in dynamically optimizing treatment. Objective: This study aims to develop an AI tool that continuously assists physical therapists in predicting an individual’s potential for achieving clinically significant pain relief by the end of the program. A secondary aim was to identify predictors of pain nonresponse to guide treatment adjustments. Methods: Data collected actively (eg, demographic and clinical information) and passively in real-time (eg, range of motion, exercise performance, and socioeconomic data from public data sources) from 6125 patients enrolled in a remote digital musculoskeletal intervention program were stored in the cloud. Two machine learning techniques, recurrent neural networks (RNNs) and light gradient boosting machine (LightGBM), continuously analyzed session updates up to session 7 to predict the likelihood of achieving significant pain relief at the program end. Model performance was assessed using the area under the receiver operating characteristic curve (ROC-AUC), precision-recall curves, specificity, and sensitivity. Model explainability was assessed using SHapley Additive exPlanations values. Results: At each session, the model provided a prediction about the potential of being a pain responder, with performance improving over time (P<.001). By session 7, the RNN achieved an ROC-AUC of 0.70 (95% CI 0.65-0.71), and the LightGBM achieved an ROC-AUC of 0.71 (95% CI 0.67-0.72). Both models demonstrated high specificity in scenarios prioritizing high precision. The key predictive features were pain-associated domains, exercise performance, motivation, and compliance, informing continuous treatment adjustments to maximize response rates. Conclusions: This study underscores the potential of an AI predictive tool within a DCP to enhance the management of LBP, supporting physical therapists in redirecting care pathways early and throughout the treatment course. This approach is particularly important for addressing the heterogeneous phenotypes observed in LBP. ©Anabela C Areias, Robert G Moulder, Maria Molinos, Dora Janela, Virgílio Bento, Carolina Moreira, Vijay Yanamadala, Steven P Cohen, Fernando Dias Correia, Fabíola Costa.
