AI and Rare Diseases ── Immune and connective tissue ── 2026-10-05

Diagram of a study on AI that distinguishes edematous-phase systemic sclerosis from similar edema. Short videos are collected from 22 SSc and 38 non-SSc patients. The pressing and rebound phases of skin under finger pressure are analyzed across 2,080 videos. Five models are tested at thresholds of 70% to 85%: at 70-80% all exceed 99% sensitivity and 98% specificity, and at 85% the extra-large model is highest. — Image abstract — the whole article on one page (click to enlarge)

1 Immune and connective tissue papers. Lead: Artificial Intelligence Distinguishing Edematous Phase of Systemic Sclerosis from Mimickers: A Video-Based Diagnostic Study

Journals covered and how papers are chosen: see the index

Autoinflammatory, immunodeficiency and rare connective-tissue diseases: treatment, trials and AI

Artificial Intelligence Distinguishing Edematous Phase of Systemic Sclerosis from Mimickers: A Video-Based Diagnostic Study
Engineering Technology & Applied Science Research · 2026-10-02 · Evidence: Diagnostic accuracy study (AI model development with internal split-sample testing)
Abstract
Early diagnosis of Systemic Sclerosis (SSc), especially in the edematous phase, is challenging. This study developed an Artificial Intelligence (AI) model capable of distinguishing the edematous phase of SSc from other clinically similar conditions and to evaluating its accuracy. Short video clips were collected from two groups: (a) SSc patients with puffy skin in the hands and/or feet during the edematous phase and (b) non-SSc conditions with edema requiring differentiation from SSc. AI development involved analyzing skin responses to finger pressure, recording the pressing and rebound phases. The collected videos were divided into three sets: 70% for AI training, 10% for validation, and 20% for accuracy testing. A total of 2,080 videos from 22 SSc and 38 non-SSc patients were analyzed. Among the 38 non-SSc cases, the most common underlying conditions were renal disease and nephrotic syndrome (15 cases, 39.5%), followed by deep venous thrombosis (6 cases, 15.8%) and left- or right-sided heart failure (5 cases, 13.2%). Five AI models were evaluated at accuracy thresholds of 70%, 75%, 80%, and 85%. At thresholds of 70–80%, all models achieved sensitivity above 99% and specificity exceeding 98%. The extra-large model demonstrated the highest sensitivity, specificity, Positive Predictive Value (PPV), and Negative Predictive Value (NPV) at the 85% threshold, outperforming the nano, small, medium, and large models. The developed AI model demonstrated high accuracy in distinguishing the edematous phase of SSc from other similar skin edema across multiple confidence thresholds, supporting its potential as an effective diagnostic tool.
Journal IF-equivalent: 2.6 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Foocharoen C, Sonsilphong S, Onchan T, Pongkulkiat P, Mahakkanukrauh A, Suwannaroj S, et al. Artificial Intelligence Distinguishing Edematous Phase of Systemic Sclerosis from Mimickers: A Video-Based Diagnostic Study. Eng Technol Appl Sci Res. 2026 Oct 2;16(5):40056-64. doi:10.48084/etasr.20438.
Checked: Abstract only

← Back to this issue