RESUMO
BACKGROUND: Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality. OBJECTIVE: This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data. METHODS: In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips. RESULTS: Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance. CONCLUSIONS: Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.
Assuntos
Crowdsourcing , Pulmão , Ultrassonografia , Crowdsourcing/métodos , Humanos , Ultrassonografia/métodos , Ultrassonografia/normas , Pulmão/diagnóstico por imagem , Estudos Prospectivos , Feminino , Masculino , Aprendizado de Máquina , Adulto , Pessoa de Meia-Idade , Estudos RetrospectivosRESUMO
OBJECTIVE: This proof-of-concept study assessed how confidently an artificial intelligence (AI) model can determine the sex of a fetus from an ultrasound image. STUDY DESIGN: Analysis was performed using 19,212 ultrasound image slices from a high-volume fetal sex determination practice. This dataset was split into a training set (11,769) and test set (7,443). A computer vision model was trained using a transfer learning approach with EfficientNetB4 architecture as base. The performance of the computer vision model was evaluated on the hold out test set. Accuracy, Cohen's Kappa and Multiclass Receiver Operating Characteristic area under the curve (AUC) were used to evaluate the performance of the model. RESULTS: The AI model achieved an Accuracy of 88.27% on the holdout test set and a Cohen's Kappa score 0.843. The ROC AUC score for Male was calculated to be 0.896, for Female a score of 0.897, for Unable to Assess a score of 0.916, and for Text Added a score of 0.981 was achieved. CONCLUSION: This novel AI model proved to have a high rate of fetal sex capture that could be of significant use in areas where ultrasound expertise is not readily available. KEY POINTS: · This is the first proof-of-concept AI model to determine fetal sex.. · This study adds to the growing research in ultrasound AI.. · Our findings demonstrate AI integration into obstetric care..
RESUMO
BACKGROUND: The purpose of this study is to assess the viability of a knee arthroplasty prediction model using 3-view X-rays that helps determine if patients with knee pain are candidates for total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA), or are not arthroplasty candidates. METHODS: Analysis was performed using radiographic and surgical data from a high-volume joint replacement practice. The dataset included 3 different X-ray views (anterior-posterior, lateral, and sunrise) for 2,767 patients along with information of whether that patient underwent an arthroplasty surgery (UKA or TKA) or not. This resulted in a dataset including 8,301 images from 2,707 patients. This dataset was then split into a training set (70%) and holdout test set (30%). A computer vision model was trained using a transfer learning approach. The performance of the computer vision model was evaluated on the holdout test set. Accuracy and multiclass receiver operating characteristic area under curve was used to evaluate the performance of the model. RESULTS: The artificial intelligence model achieved an accuracy of 87.8% on the holdout test set and a quadratic Cohen's kappa score of 0.811. The multiclass receiver operating characteristic area under curve score for TKA was calculated to be 0.97; for UKA a score of 0.96 and for No Surgery a score of 0.98 was achieved. An accuracy of 93.8% was achieved for predicting Surgery versus No Surgery and 88% for TKA versus not TKA was achieved. CONCLUSION: The artificial intelligence/machine learning model demonstrated viability for predicting which patients are candidates for a UKA, TKA, or no surgical intervention.
Assuntos
Artroplastia do Joelho , Osteoartrite do Joelho , Humanos , Artroplastia do Joelho/métodos , Osteoartrite do Joelho/cirurgia , Inteligência Artificial , Resultado do Tratamento , Articulação do Joelho/diagnóstico por imagem , Articulação do Joelho/cirurgia , Aprendizado de MáquinaRESUMO
Patient-performed point-of-care ultrasound (POCUS) may be feasible for use in home-based healthcare. We investigated whether novice users can obtain lung ultrasound (LUS) images via self-scanning with similar interpretability and quality as experts. Adult participants with no prior medical or POCUS training, who were capable of viewing PowerPoint slides in their home and who could hold a probe to their chest were recruited. After training, volunteers self-performed 8-zone LUS and saved images using a hand-held POCUS device in their own home. Each 8-zone LUS scan was repeated by POCUS experts. Clips were independently viewed and scored by POCUS experts blinded to performing sonographers. Quality and interpretability scores of novice- and expert-obtained LUS images were compared. Thirty volunteers with average age of 42.8 years (Standard Deviation (SD) 15.8), and average body mass index of 23.7 (SD 3.1) were recruited. Quality of novice and expert scans did not differ (median score 2.6, interquartile range (IQR) 2.3-2.9 vs. 2.8, IQR 2.3-3.0, respectively p = 0.09). Individual zone quality also did not differ (P > 0.05). Interpretability of LUS was similar between expert and novice scanners (median 7 zones interpretable, IQR 6-8, for both groups, p = 0.42). Interpretability of novice-obtained scans did not differ from expert scans (median 7 out of 8 zones, IQR 6-8, p = 0.42). Novice-users can self-obtain interpretable, expert-quality LUS clips with minimal training. Patient-performed LUS may be feasible for outpatient home monitoring.
Assuntos
Diagnóstico por Imagem , Sistemas Automatizados de Assistência Junto ao Leito , Adulto , Humanos , Ultrassonografia , Testes Imediatos , TóraxRESUMO
Artificial intelligence (AI) has made considerable progress within the last decade and is the subject of contemporary literature. This trend is driven by improved computational abilities and increasing amounts of complex data that allow for new approaches in analysis and interpretation. Renal cell carcinoma (RCC) has a rising incidence since most tumors are now detected at an earlier stage due to improved imaging. This creates considerable challenges as approximately 10%-17% of kidney tumors are designated as benign in histopathological evaluation; however, certain co-morbid populations (the obese and elderly) have an increased peri-interventional risk. AI offers an alternative solution by helping to optimize precision and guidance for diagnostic and therapeutic decisions. The narrative review introduced basic principles and provide a comprehensive overview of current AI techniques for RCC. Currently, AI applications can be found in any aspect of RCC management including diagnostics, perioperative care, pathology, and follow-up. Most commonly applied models include neural networks, random forest, support vector machines, and regression. However, for implementation in daily practice, health care providers need to develop a basic understanding and establish interdisciplinary collaborations in order to standardize datasets, define meaningful endpoints, and unify interpretation.
RESUMO
INTRODUCTION: Sudden cardiac death is a rare cause of death in young athletes. Current screening techniques include history and physical exam (H and P), with or without an electrocardiogram (ECG). Adding point of care cardiac ultrasound has demonstrated benefits, but there is limited data about implementing this technology. We evaluated the feasibility of adding ultrasound to preparticipation screening for collegiate athletes. METHODS: We prospectively enrolled 42 collegiate athletes randomly selected from several sports. All athletes were screened using a 14-point H and P based on 2014 American College of Cardiology (ACC) and American Heart Association (AHA) guidelines, ECG, and cardiac ultrasound. RESULTS: We screened 11 female and 31 male athletes. On ultrasound, male athletes demonstrated significantly larger interventricular septal wall thickness (p = 0.002), posterior wall thickness (p <0.001) and aortic root breadth (p = 0.002) compared to females. Based on H and P and ECGs alone and a combination of H and P with ECG, no athletes demonstrated a positive screening for cardiac abnormalities. However, with combined H and P, ECG, and cardiac ultrasound, one athlete demonstrated positive findings. CONCLUSIONS: We believe that adding point of care ultrasound to the preparticipation exam of college athletes is feasible. This workflow may provide a model for athletic departments' screening.
Assuntos
Atletas , Morte Súbita Cardíaca/prevenção & controle , Cardiopatias/diagnóstico , Programas de Rastreamento/métodos , Sociedades , Estudantes , Universidades , Adolescente , Morte Súbita Cardíaca/epidemiologia , Ecocardiografia , Eletrocardiografia , Feminino , Cardiopatias/epidemiologia , Humanos , Incidência , Masculino , Esportes , Estados Unidos/epidemiologia , Adulto JovemRESUMO
A patient presented after ingesting the contents of a lava lamp that he believed to contain alcohol. It was later discovered that this product was comprised of 76% calcium nitrate, leading to his subsequent development of methemoglobinemia. This disease is a medical emergency secondary to poor transportation of oxygen and resultant tissue hypoxic effects. Therefore, having high suspicion for this disease process in patients with toxic ingestions, understanding the proper diagnosis, and promptly starting treatment are all critical actions for emergency physicians.