Consensus Between Radiologists, Specialists in Internal Medicine, and AI Software on Chest X-Rays in a Hospital-at-Home Service: Prospective Observational Study
Bibliographic record
Abstract
Background: Home hospitalization is a care modality growing in popularity worldwide. Telemedicine-driven hospital-at-home (HAH) services could replace traditional hospital departments for selected patients. Chest x-rays typically serve as a key diagnostic tool in such cases. Objective: The implementation, analysis, and clinical assimilation of chest x-rays into an HAH service has not been described yet. Our objective is to introduce this essential information to the realm of HAH services for the first time worldwide. Methods: The study involved a prospective follow-up, description, and analysis of the HAH patient population who underwent chest x-rays at home. A comparative analysis was performed to evaluate the level of agreement among three interpretation modalities: a radiologist, a specialist in internal medicine, and a designated artificial intelligence (AI) algorithm. Results: Between February 2021 and May 2023, 300 chest radiographs were performed at the homes of 260 patients, with the median age being 78 (IQR 65-87) years. The most frequent underlying morbidity was cardiovascular disease (n=185, 71.2%). Of the x-rays, 286 (95.3%) were interpreted by a specialist in internal medicine, 29 (9.7%) by a specialized radiologist, and 95 (31.7%) by the AI software. The overall raw agreement level among these three modalities exceeded 90%. The consensus level evaluated using the Cohen κ coefficient showed substantial agreement (κ=0.65) and moderate agreement (κ=0.49) between the specialist in internal medicine and the radiologist, and between the specialist in internal medicine and the AI software, respectively. Conclusions: Chest x-rays play a crucial role in the HAH setting. Rapid and reliable interpretation of these x-rays is essential for determining whether a patient requires transfer back to in-hospital surveillance. Our comparative results showed that interpretation by an experienced specialist in internal medicine demonstrates a significant level of consensus with that of the radiologists. However, AI algorithm-based interpretation needs to be further developed and revalidated prior to clinical applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.037 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".