Deep Learning vs Traditional Models for Predicting Hospital Readmission among Patients with Diabetes.

A hospital readmission risk prediction tool for patients with diabetes based on electronic health record (EHR) data is needed. The optimal modeling approach, however, is unclear. In 2,836,569 encounters of 36,641 diabetes patients, deep learning (DL) long short-term memory (LSTM) models predicting unplanned, all-cause, 30-day readmission were developed and compared to several traditional models. Models used EHR data defined by a Common Data Model. The LSTM model Area Under the Receiver Operating Characteristic Curve (AUROC) was significantly greater than that of the next best traditional model [LSTM 0.79 vs Random Forest (RF) 0.72, p<0.0001]. Experiments showed that performance of the LSTM models increased as prior encounter number increased up to 30 encounters. An LSTM model with 16 selected laboratory tests yielded equivalent performance to a model with all 981 laboratory tests. This new DL model may provide the basis for a more useful readmission risk prediction tool for diabetes patients.

Sciatic Nerve Variants in Patients Diagnosed With Sciatica: Is There a Correlation?

PURPOSE: Compression of the sciatic nerve in its path along the piriformis muscle can produce sciatica-like symptoms. There are 6 predominant types of sciatic nerve variations with type 1 being the most common (84.2%), followed by type 2 (13.9%). However, there is scarce literature on the prevalence of sciatic nerve variation in those diagnosed with sciatica. MATERIALS AND METHODS: The charts of 95 patients clinically diagnosed with sciatica who had a magnetic resonance imaging of the pelvis/hip were retrospectively studied. All patients had T1-weighted axial, coronal, and sagittal images. Magnetic resonance imagings were interpreted separately by 2 board-certified fellowship-trained musculoskeletal radiologists to identify the sciatic nerve variant. RESULTS: Seven cases were excluded because of inadequate imaging. Of the remaining 88 patients, 5 had bilateral sciatica resulting in a sample size of 93 limbs. Fifty-two (55.9%) had type 1 sciatic nerve anatomy, 39 (41.9%) had type 2, and 2 (2.2%) had type 3. The proportions of type 1 and 2 variations were significantly different from the normal distribution (P < 0.001), whereas type 3, 4, 5, and 6 variants were not (P = 1.00). CONCLUSIONS: There is strong statistical significance regarding the relationship between sciatic nerve variation and the clinical diagnosis of sciatica. Preoperative magnetic resonance imaging can be considered in sciatica patients to prevent iatrogenic injury in pelvic surgery.

Interactive Cost-benefit Analysis: Providing Real-World Financial Context to Predictive Analytics.

Objective: Clinical implementation of predictive analytics that assess risk of high-cost outcomes are presumed to save money because they help focus interventions designed to avert those outcomes on a subset patients who are most likely to benefit from the intervention. This premise may not always be true. A cost-benefit analysis is necessary to show if a strategy of applying the predictive algorithm is truly favorable to alternative strategies. Methods: We designed and implemented an interactive web-based cost-benefit calculator, enabling specification of accuracy parameters for the predictive model and other clinical and financial factors related to the occurrence of an undesirable outcome. We use the web tool, populated with real-world data to illustrate a cost-benefit analysis of a strategy of applying predictive analytics to select a cohort of high-risk patients to receive interventions to avert readmissions for Congestive Heart Failure (CHF). Results: Application of predictive analytics in clinical care may not always be a cost-saving strategy compared with intervening on all patients. Improving the accuracy of a predictive model may lower costs, but other factors such as the prevalence and cost of the outcome, and the cost and effectiveness of the intervention designed to avert the outcome may be more influential in determining the favored strategy. Conclusion: An interactive cost-benefit analyses provides insights regarding the financial implications of a clinical strategy that implements predictive analytics.