Dataset Information

Perceptual training to improve hip fracture identification in conventional radiographs.

ABSTRACT: Diagnosing certain fractures in conventional radiographs can be a difficult task, usually taking years to master. Typically, students are trained ad-hoc, in a primarily-rule based fashion. Our study investigated whether students can more rapidly learn to diagnose proximal neck of femur fractures via perceptual training, without having to learn an explicit set of rules. One hundred and thirty-nine students with no prior medical or radiology training were shown a sequence of plain film X-ray images of the right hip and for each image were asked to indicate whether a fracture was present. Students were told if they were correct and the location of any fracture, if present. No other feedback was given. The more able students achieved the same level of accuracy as board certified radiologists at identifying hip fractures in less than an hour of training. Surprisingly, perceptual learning was reduced when the training set was constructed to over-represent the types of images participants found more difficult to categorise. Conversely, repeating training images did not reduce post-training performance relative to showing an equivalent number of unique images. Perceptual training is an effective way of helping novices learn to identify hip fractures in X-ray images and should supplement the current education programme for students.

SUBMITTER: Chen W

PROVIDER: S-EPMC5739398 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Perceptual training to improve hip fracture identification in conventional radiographs.

Chen Weijia W HolcDorf David D McCusker Mark W MW Gaillard Frank F Howe Piers D L PDL

PloS one 20171221 12

Diagnosing certain fractures in conventional radiographs can be a difficult task, usually taking years to master. Typically, students are trained ad-hoc, in a primarily-rule based fashion. Our study investigated whether students can more rapidly learn to diagnose proximal neck of femur fractures via perceptual training, without having to learn an explicit set of rules. One hundred and thirty-nine students with no prior medical or radiology training were shown a sequence of plain film X-ray image ...[more]

PMID: 29267344

Similar Datasets

Project description:PurposeTo investigate the feasibility of automatic identification and classification of hip fractures using deep learning, which may improve outcomes by reducing diagnostic errors and decreasing time to operation.Materials and methodsHip and pelvic radiographs from 1118 studies were reviewed, and 3026 hips were labeled via bounding boxes and classified as normal, displaced femoral neck fracture, nondisplaced femoral neck fracture, intertrochanteric fracture, previous open reduction and internal fixation, or previous arthroplasty. A deep learning-based object detection model was trained to automate the placement of the bounding boxes. A Densely Connected Convolutional Neural Network (or DenseNet) was trained on a subset of the bounding box images, and its performance was evaluated on a held-out test set and by comparison on a 100-image subset with two groups of human observers: fellowship-trained radiologists and orthopedists; senior residents in emergency medicine, radiology, and orthopedics.ResultsThe binary accuracy for detecting a fracture of this model was 93.7% (95% confidence interval [CI]: 90.8%, 96.5%), with a sensitivity of 93.2% (95% CI: 88.9%, 97.1%) and a specificity of 94.2% (95% CI: 89.7%, 98.4%). Multiclass classification accuracy was 90.8% (95% CI: 87.5%, 94.2%). When compared with the accuracy of human observers, the accuracy of the model achieved an expert-level classification, at the very least, under all conditions. Additionally, when the model was used as an aid, human performance improved, with aided resident performance approximating unaided fellowship-trained expert performance in the multiclass classification.ConclusionA deep learning model identified and classified hip fractures with expert-level performance, at the very least, and when used as an aid, improved human performance, with aided resident performance approximating that of unaided fellowship-trained attending physicians.Supplemental material is available for this article.© RSNA, 2020.

Project description:ImportancePatients with a hip fracture lose more than 50% knee-extension strength in the fractured limb within one week of surgery. Hence, immediate progressive strength training following hip fracture surgery may be rational, but the feasibility unknown.ObjectiveTo examine the feasibility of in-hospital progressive strength training implemented in the acute ward following hip fracture surgery, based on pre-specified criteria for feasibility.Design, setting and patientsA prospective cohort study conducted in an acute orthopedic hip fracture unit at a university hospital. A consecutive sample of 36 patients, 18 with a cervical and 18 with a trochanteric hip fracture (27 women and 9 men, mean (SD) age of 79.4 (8.3) years) were included between June and December 2012.InterventionA daily (on weekdays) program of progressive knee-extension strength training for the fractured limb, using ankle weight cuffs in 3 sets of 10 repetition maximum loadings.Main outcomes and measuresThe primary outcome was the change in training load (kg) during the knee-extension strength training. The secondary outcomes were changes in hip fracture-related pain and maximal isometric knee-extension strength.ResultsThe strength training was commenced at a mean of 2.4 (0.7) days after surgery. The training loads (kilograms lifted) increased from 1.6 (0.8) to 4.3 (1.7) kg over 4.3 (2.2) training sessions (P<.001). The maximal isometric knee-extension strength of the fractured limb increased from 0.37 (0.2) to 0.61 (0.3) Nm/kg (P<.001), while the average strength deficit in the fractured limb decreased from 50% to 32% (% non-fractured, P<.001). Only 3 of 212 sessions were not performed because of severe hip fracture-related pain.Conclusion and relevanceProgressive knee-extension strength training of the fractured limb commenced in the acute ward seems feasible, and may reduce strength asymmetry between limbs without hip pain interfering. The clinical efficacy needs confirmation in a randomized controlled design.Trial registrationClinicalTrials.gov ID: NCT01616030.

Dataset Information

Perceptual training to improve hip fracture identification in conventional radiographs.

Publications

Perceptual training to improve hip fracture identification in conventional radiographs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets