clinicians

2026-10-05

RESEARCH · 1 SOURCE · arXiv cs.AI

FD-SCoPE: verifiable, feedback-driven LLM framework for clinician queries over trial evidence tables

The paper (arXiv:2610.02576v1) introduces FD-SCoPE, a language-model framework that answers clinician-style questions over systematic-review evidence tables by exposing the query, selected trials, and derivation rule for each answer and learning from expert corrections. On an oncology table of 159 immune checkpoint inhibitor trial records it completed 140 clinician-style tasks (alternatives 90.7–97.9%), retrieved 99.3% of relevant records for derived attributes with 89.8% PPV, achieved derived-value F1 77.7% (vs. 64.8–73.4% for four baselines), and raised F1 on 1,201 unseen questions from 77.9% to 84.9% after simulated corrections.

6.0

2026-09-30

RESEARCH · 1 SOURCE · arXiv cs.AI

Study of 19,930 ChatGPT conversations finds dramatic, premature action suggestions for distressed young adults; clinicians propose de‑escalation guidelines

ArXiv preprint (arXiv:2609.35953v1) analyzes 19,930 ChatGPT conversations and survey data from 158 users aged 18–25; clinicians reviewed five exemplar chats. Distressed participants reported stronger emotional engagement and more behavioral change; ChatGPT tended to respond with overly dramatic and action‑oriented suggestions, while clinicians identified seven process failures and distilled clinician‑grounded design guidelines: 1) ask about safety, 2) de‑escalate intensity, and 3) explore concerns without validating harmful conclusions.

7.0

2026-09-21

RESEARCH · 1 SOURCE · arXiv cs.AI

InterviewPlayground paper (arXiv:2609.21149v1) pilots clinician-grounded QA for AI psychiatric intake

The authors introduce InterviewPlayground, a clinician-grounded evaluation platform built around a memory-augmented patient simulator for open-ended AI interviewing, and report a pilot 25-minute assessment with 6 clinicians comparing the platform to a GPT-based LLM interviewer. In the pilot the LLM recovered more embedded clinically relevant items (88.0% vs 38.9%) but made more unsupported clinical inferences (56.8% vs 27.8%) and identified fewer safety concerns (33.3% vs 66.7%).

6.0

2026-08-04

RESEARCH · 1 SOURCE · MIT News AI

Benefits of medical AI assistance depend on user expertise

A study found that non-experts deferred to LLM-based diagnostic assistance even when the AI was incorrect, while clinicians were more likely to identify and correct AI errors. The results indicate that the effectiveness and safety of medical AI support vary with user expertise.

7.0