AI and Rare Diseases ── 2026-11-09
New papers on rare diseases (other than neurological and cancer) and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 8 disease groups, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.
Read by disease: Platforms（0） · Inborn errors of metabolism（1） · Genetic syndromes（0） · Rare blood disorders（0） · Immune and connective tissue（0） · Heart and lung（1） · Kidney, liver and gut（0） · Skin and bone（0）
Rare-disease diagnosis and drug discovery platforms and AI
No new qualifying paper for this issue.
Inborn errors of metabolism: treatment, trials and AI
- Abstract
Inborn errors of metabolism (IEMs) are a heterogeneous group of rare genetic diseases characterized by enzymatic, transporter, or cofactor deficiencies that disrupt metabolic homeostasis. Biomarker identification is central to their diagnosis, prognosis, and therapeutic monitoring, but phenotypic heterogeneity and limited patient cohorts pose persistent challenges. Computational tools, including genome-scale metabolic modeling, systems biology, and quantitative systems pharmacology, are emerging and aiming to address these limitations. This work aimed to identify, characterize, and synthesize the available evidence on computational tools for predicting or identifying metabolic biomarkers in individuals diagnosed with IEMs. A rapid systematic review was conducted following PRISMA 2020 guidelines, searching PubMed and EMBASE for studies published within the last ten years in English or Spanish. Eligible studies applied computational methodologies, such as in silico modeling, constraint-based modeling, machine learning, or metabolic network analysis, for biomarker discovery, prediction, or validation in IEMs. Three reviewers performed selection independently, resolving discrepancies by consensus. Of 955 records identified, 13 studies met the eligibility criteria. They were classified into four categories: machine learning and artificial intelligence approaches for predictive modeling and risk stratification; genome-scale and constraint-based modeling to simulate enzymatic deficiencies and identify candidate biomarkers; systems biology and network-based modeling for pathway-level signatures and diagnostic visualization; and quantitative systems pharmacology frameworks to model therapeutic response and biomarker trajectories. When combined with conventional methods, computational tools may improve the mechanistic interpretability, scalability, and multi-omics integration during biomarker identification for EIMs. However, most approaches remain exploratory, and prospective clinical validation is limited. Future efforts should prioritize hybrid modeling, standardized reporting, and clinical integration.
Journal IF-equivalent: 0.9 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Saldaña DA, Echeverri-Peña OY, Alméciga-Díaz CJ. Computational tools for biomarker identification in inborn errors of metabolism: A rapid systematic review. Molecular Genetics and Metabolism. 2026 Dec;149(4):110316. doi:10.1016/j.ymgme.2026.110316.Checked: Abstract only
See all 1 Inborn errors of metabolism papers →
Genetic syndromes and paediatric rare diseases: treatment, trials and AI
No new qualifying paper for this issue.
Rare blood disorders: treatment, trials and AI
No new qualifying paper for this issue.
Autoinflammatory, immunodeficiency and rare connective-tissue diseases: treatment, trials and AI
No new qualifying paper for this issue.
Rare cardiovascular and respiratory diseases: treatment, trials and AI
- Abstract
Technetium-99 m pyrophosphate (Tc-99 m PYP) planar scintigraphy is widely used for evaluating transthyretin cardiac amyloidosis (ATTR-CM). However, interpreting equivocal Perugini Grade 1 cardiac uptake remains a significant clinical challenge due to overlapping blood-pool activity and low signal-to-noise ratio. We aimed to develop and validate a multimodal deep learning framework to predict expert SPECT/CT adjudicated Perugini categories from planar imaging and pre-procedural clinical variables, with particular attention to Grade 1 examinations. In this multicenter study utilizing data from the Taiwan Multicenter TTCA-PYP Registry ( N = 438), we developed a multimodal neural network. The framework processes physician-verified cardiac planar ROIs (32 × 128 pixels) with a truncated Wide-ResNet50-2 encoder and 23 routine clinical variables with a frozen TabPFN embedding, aligned by a CLIP-style contrastive loss and fused by cross-attention, to predict SPECT/CT-adjudicated Perugini categories (Grade 0, Grade 1, Grades 2–3). Genetic testing status and study design were not inputs. Evaluation used 10 repetitions of a hospital- and grade-stratified assessment set with 10-fold cross-validation, decision curve analysis, and leave-one-center-out testing of the two centers with all grades (FEMH, NTUH). Overall accuracy was higher with the multimodal model than with imaging only (0.826 vs. 0.751; paired difference + 0.075, 95% CI 0.034 to 0.117), whereas macro-AUC was similar (0.925 vs. 0.917). In Grade 1, precision increased from 0.536 to 0.694 (difference + 0.159, 95% CI 0.056 to 0.261) and recall decreased from 0.704 to 0.683 (difference − 0.022, 95% CI − 0.120 to 0.077); F1-score and PR-AUC differences were less certain. Intervals used a Nadeau-Bengio correction for repeated resampling. With FEMH or NTUH held out, accuracy was 0.704 and 0.889, but Grade 1 recall was 0.312 in FEMH and Grade 0 recall 0.071 in NTUH. The multimodal framework may serve as an adjunct for standardizing expert imaging-based Perugini classification from planar Tc-99 m PYP examinations. It does not establish an etiologic diagnosis of ATTR-CM, and Grade 1 predictions remain indeterminate findings requiring monoclonal protein assessment and, where appropriate, tomographic or further clinical evaluation. Performance did not transfer uniformly to held-out centers, and independent validation is required.
Journal IF-equivalent: 3.8 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)Reference: Ou DX, Huang CH, Wang SY, Lin YH, Chang WT, Yu WC, et al. Integration of clinical parameters and deep learning based ROI enhancement in Tc-99m PYP scintigraphy for predicting SPECT/CT-adjudicated Perugini categories in suspected transthyretin cardiac amyloidosis. BMC Med Imaging. 2026 Nov 6 [Epub ahead of print]. doi:10.1186/s12880-026-03036-1.Checked: Abstract only
See all 1 Heart and lung papers →
Rare kidney, liver and gastrointestinal diseases: treatment, trials and AI
No new qualifying paper for this issue.
Rare skin and bone diseases: treatment, trials and AI
No new qualifying paper for this issue.