AI aided workflow for hip dysplasia screening using ultrasound in primary care clinics
Bibliographic record
Abstract
Developmental dysplasia of the hip (DDH) is a common cause of premature osteoarthritis. This osteoarthritis can be prevented if DDH is detected by ultrasound and treated in infancy, but universal DDH screening is generally not cost-effective due to the need for experts to perform the scans. The purpose of our study was to evaluate the feasibility of having non-expert primary care clinic staff perform DDH ultrasound using handheld ultrasound with artificial intelligence (AI) decision support. We performed an implementation study evaluating the FDA-cleared MEDO-Hip AI app interpreting cine-sweep images obtained from handheld Philips Lumify probe to detect DDH. Initial scans were done by nurses or family physicians in 3 primary care clinics, trained by video, powerpoint slides and brief in-person. When the AI app recommended follow-up (FU), we first performed internal FU by a sonographer using the AI app; cases still considered abnormal by AI were referred to pediatric orthopedic clinic for assessment. We performed 369 scans in 306 infants. Internal FU rates were initially 40% for nurses and 20% for physicians, declining steeply to 14% after ~ 60 cases/site: 4% technical failure, 8% normal at sonographer FU using AI, and 2% confirmed DDH. Of 6 infants referred to pediatric orthopedic clinic, all were treated for DDH (100% specificity); 4 had no risk factors and may not have otherwise been identified. Real-time AI decision support and a simplified portable ultrasound protocol enabled lightly trained primary care clinic staff to perform hip dysplasia screening with FU and case detection rates similar to costly formal ultrasound screening, where the US scan is performed by a sonographer and interpreted by a radiologist/orthopedic surgeon. This highlights the potential utility of AI-supported portable ultrasound in primary care.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".