Clinician-Driven AI: Code-Free Self-Training on Public Data for Diabetic Retinopathy Referral.

Importance: Democratizing artificial intelligence (AI) enables model development by clinicians with a lack of coding expertise, powerful computing resources, and large, well-labeled data sets. Objective: To determine whether resource-constrained clinicians can use self-training via automated machine learning (ML) and public data sets to design high-performing diabetic retinopathy classification models. Design, Setting, and Participants: This diagnostic quality improvement study was conducted from January 1, 2021, to December 31, 2021. A self-training method without coding was used on 2 public data sets with retinal images from patients in France (Messidor-2 [n = 1748]) and the UK and US (EyePACS [n = 58 689]) and externally validated on 1 data set with retinal images from patients of a private Egyptian medical retina clinic (Egypt [n = 210]). An AI model was trained to classify referable diabetic retinopathy as an exemplar use case. Messidor-2 images were assigned adjudicated labels available on Kaggle; 4 images were deemed ungradable and excluded, leaving 1744 images. A total of 300 images randomly selected from the EyePACS data set were independently relabeled by 3 blinded retina specialists using the International Classification of Diabetic Retinopathy protocol for diabetic retinopathy grade and diabetic macular edema presence; 19 images were deemed ungradable, leaving 281 images. Data analysis was performed from February 1 to February 28, 2021. Exposures: Using public data sets, a teacher model was trained with labeled images using supervised learning. Next, the resulting predictions, termed pseudolabels, were used on an unlabeled public data set. Finally, a student model was trained with the existing labeled images and the additional pseudolabeled images. Main Outcomes and Measures: The analyzed metrics for the models included the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, and F1 score. The Fisher exact test was performed, and 2-tailed P values were calculated for failure case analysis. Results: For the internal validation data sets, AUROC values for performance ranged from 0.886 to 0.939 for the teacher model and from 0.916 to 0.951 for the student model. For external validation of automated ML model performance, AUROC values and accuracy were 0.964 and 93.3% for the teacher model, 0.950 and 96.7% for the student model, and 0.890 and 94.3% for the manually coded bespoke model, respectively. Conclusions and Relevance: These findings suggest that self-training using automated ML is an effective method to increase both model performance and generalizability while decreasing the need for costly expert labeling. This approach advances the democratization of AI by enabling clinicians without coding expertise or access to large, well-labeled private data sets to develop their own AI models.

May-Thurner Syndrome and Lymphedema Reconstruction.

May-Thurner syndrome (MTS) is an anatomical variant that results in compression of the left common iliac vein by the right common iliac artery. Although often asymptomatic, lower extremity swelling/edema, deep venous thrombosis, post-thrombotic syndrome, and eventual lymphedema (due to long-standing venous obstruction) can develop. The clinical management of patients presenting for lymphedema surgery with concomitant or undiagnosed MTS is not well described. Methods: This review investigates two patients who were evaluated for unilateral lower extremity lymphedema, both of whom were subsequently diagnosed with MTS. Standard imaging (including lymphoscintigraphy, indocyanine green lymphangiography, and magnetic resonance venography) were performed to identify proximal venous obstruction. Treatment was accomplished using vascular surgical management, including stenting of the iliac vein before lymphedema reconstruction with vascularized lymph node transfer and multiple lymphovenous bypass. Results: Both patients we examined in this review had improvement of lymphedema with vascular surgical management. Literature review reveals that MTS has an incidence as high as 20% in the population, although commonly unidentified due to lack of symptomatology. Conclusions: There are no studies documenting the incidence of MTS in patients referred for lymphedema surgical management. Routine studies should be obtained to screen for proximal venous obstruction in patients presenting for surgical management of lower extremity lymphedema. Additional research is needed regarding the approach to managing patients with both MTS and lymphedema. Careful observational and prospective studies may elucidate the appropriate time interval between venous stenting and lymphedema microsurgical reconstruction.