− HEALTH We are the last generation that will influence what wellbeing means before AI systems optimize that definitio…− HEALTH Abstract There is much discussion of the false outputs that generative AI systems such as ChatGPT, Claude, Ge…± SCIENCE This article presents a Delphi consensus developed by a panel of editors-in-chief of anaesthesiology and pain…+ EDUCATION The study investigated how innovative, AI-supported teaching methods relate to the mathematics problem-solvin…+ EDUCATION As generative AI becomes increasingly integrated into higher education, understanding how students engage wit…+ HEALTH In the complex and multidimensional field of medicine, multimodal data are prevalent and crucial for informed…± SCIENCE This paper explores the evolution of geoscientific inquiry, tracing the progression from traditional physics-…− POLICY This paper conducts a systematic review and interdisciplinary analysis of the ethical challenges of generativ…
TruaceTracing the truth around AIMonday, July 20, 2026
Subscribe
Health·The Trace·Model-prefilled trace·Published 2026-07-20

GPT-4o-assisted evidence synthesis for osteogenesis imperfecta biologics

Source article: Artificial Intelligence for Evidence Synthesis of Emerging Biologics to Improve Skeletal Health in Osteogenesis Imperfecta: Systematic Review and Meta-Analysis

Background: Osteogenesis imperfecta (OI) is a rare genetic disorder characterized by bone fragility and recurrent fractures. Emerging biologics demonstrate promise by targeting bone-remodeling pathways, yet evidence for their efficacy and safety remains fragmented and heterogeneous, and no prior systematic review in OI has incorporated artificial intelligence (AI) to synthesize it. Objective: This study aims to systematically evaluate the efficacy and safety of novel biologics in patients with OI using an AI-ass…

TRV-2026-0321Peer-reviewedPermanent record — cite & verify
Trace impact reading

Negative state: both sides are scored from claims and sources, not community votes.

P 71The P score combines the specificity and measured human impact of the grounded problem claim with the strength of this Trace’s cited sources.G 63The G score combines the specificity and measured human impact of the grounded gain claim with the strength of this Trace’s cited sources.
Artificial Intelligence for Evidence Synthesis of Emerging Biologics to Improve Skeletal Health in Osteogenesis Imperfecta: Systematic Review and Meta-Analysis

"BC Cancer Research Centre #2" by SqueakyMarmot is licensed under CC BY-SA 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/2.0/.

The quick read

By December 2025, researchers conducted a systematic review and meta-analysis of 13 trials (n=684) of five emerging biologics for osteogenesis imperfecta, using GPT-4o to perform parallel title/abstract and full-text screening and to assist risk-of-bias assessment. The AI workflow achieved 97.4% sensitivity at abstract level and 88.9% at full-text, reducing total screening time by over 95% with substantial agreement to humans (kappa 0.778).

The acceleration matters for rare-disease research where evidence is fragmented, but clinical impact remains limited: denosumab and setrusumab improved lumbar spine aBMD without demonstrating superior fracture reduction versus bisphosphonates, and safety signals like 30.95% hypercalcemia with denosumab in children persist. The observed optimism and positional biases indicate that scaling this workflow will still require explicit human oversight for contextual clinical reasoning.

Main points
  • Systematic review included 13 trials (n=684) of denosumab, setrusumab, teriparatide, romosozumab, and fresolimumab up to December 1, 2025, with 10 trials (n=333) in meta-analysis.
  • In children denosumab produced 25.49% increase in lumbar spine aBMD at 12 months; in adults setrusumab yielded 9.38% improvement.
  • No biologic significantly reduced fracture incidence compared to bisphosphonates across trials.
  • Safety varied: denosumab associated with 30.95% hypercalcemia risk in children, while setrusumab had no treatment-related serious adverse events.
Gain

GPT-4o integrated into systematic review screening substantially accelerated evidence synthesis for osteogenesis imperfecta biologics while maintaining high sensitivity.

Problem

GPT-4o showed optimism and positional biases in risk-of-bias assessment because it relied on probabilistic language patterns rather than structured clinical reasoning.

The rundown

The review searched PubMed, Web of Science, Embase, ScienceDirect, Cochrane Library and ClinicalTrials.gov to December 1, 2025, including randomized, nonrandomized and single-arm trials reporting aBMD and/or fractures, excluding case series.

GPT-4o performed parallel 2-stage screening and assisted risk of bias assessment using an adapted Cochrane RoB 2 tool, benchmarked against humans with sensitivity, specificity and weighted Cohen kappa of 0.778.

Primary outcome was percentage change in aBMD synthesized via random-effects meta-analysis, showing age-specific gains but no superior fracture reduction over bisphosphonates.

What this doesn’t fix

Findings are constrained by a small and heterogeneous trial base, limiting generalizability of both efficacy estimates and AI performance.

Sources

Reader signal

How should this claim be treated?

The debate