A convolutional neural network model predicted pharmacological remission of type 2 diabetes 2 years after gastric bypass surgery with an AUC of 0.85 during validation, outperforming traditional predictive indices by 9% to 12%.
Observational (n=8,057)
Yes
Does a convolutional neural network (CNN) model improve the prediction of diabetes remission 2 years after Roux-en-Y gastric bypass surgery in patients with type 2 diabetes compared to traditional predictive indices?
A deep learning convolutional neural network model outperformed traditional clinical indices in predicting type 2 diabetes remission 2 years after Roux-en-Y gastric bypass surgery.
Effect estimate: AUC 0.85 (95% CI 0.83-0.86)
Absolute Event Rate: 0.85% vs 0.76%
BACKGROUND: Prediction of diabetes remission is an important topic in the evaluation of patients with type 2 diabetes (T2D) before bariatric surgery. Several high-quality predictive indices are available, but artificial intelligence algorithms offer the potential for higher predictive capability. OBJECTIVE: This study aimed to construct and validate an artificial intelligence prediction model for diabetes remission after Roux-en-Y gastric bypass surgery. METHODS: Patients who underwent surgery from 2007 to 2017 were included in the study, with collection of individual data from the Scandinavian Obesity Surgery Registry (SOReg), the Swedish National Patients Register, the Swedish Prescribed Drugs Register, and Statistics Sweden. A 7-layer convolution neural network (CNN) model was developed using 80% (6446/8057) of patients randomly selected from SOReg and 20% (1611/8057) of patients for external testing. The predictive capability of the CNN model and currently used scores (DiaRem, Ad-DiaRem, DiaBetter, and individualized metabolic surgery) were compared. RESULTS: In total, 8057 patients with T2D were included in the study. At 2 years after surgery, 77.09% achieved pharmacological remission (n=6211), while 63.07% (4004/6348) achieved complete remission. The CNN model showed high accuracy for cessation of antidiabetic drugs and complete remission of T2D after gastric bypass surgery. The area under the receiver operating characteristic curve (AUC) for the CNN model for pharmacological remission was 0.85 (95% CI 0.83-0.86) during validation and 0.83 for the final test, which was 9%-12% better than the traditional predictive indices. The AUC for complete remission was 0.83 (95% CI 0.81-0.85) during validation and 0.82 for the final test, which was 9%-11% better than the traditional predictive indices. CONCLUSIONS: The CNN method had better predictive capability compared to traditional indices for diabetes remission. However, further validation is needed in other countries to evaluate its external generalizability.
Cao et al. (Sat,) conducted a observational in Type 2 diabetes and morbid obesity (n=8,057). Convolutional Neural Network (CNN) prediction model vs. Traditional predictive indices (DiaRem, Ad-DiaRem, DiaBetter, IMS) was evaluated on Pharmacological remission of type 2 diabetes at 2 years (AUC 0.85, 95% CI 0.83-0.86). A convolutional neural network model predicted pharmacological remission of type 2 diabetes 2 years after gastric bypass surgery with an AUC of 0.85 during validation, outperforming traditional predictive indices by 9% to 12%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: