Impact of diagnosis code grouping method on clinical prediction model performance: A multi-site retrospective observational study.

OBJECTIVE: The primary purpose of this work is to systematically assess the performance trade-offs on clinical prediction tasks of four diagnosis code groupings: AHRQ-Elixhauser, Single-level CCS, truncated ICD-9-CM codes, and raw ICD-9-CM codes. MATERIALS AND METHODS: We used two distinct datasets from different geographic regions and patient populations and train models for three prediction tasks: 1-year mortality following an ICU stay, 30-day mortality following surgery, and 30-day complication following surgery. We run multiple commonly-used binary classification models including penalized logistic regression, random forest, and gradient boosted trees. Model performance is evaluated using the Area Under the Receiver Operating Characteristic (AUROC) and the Area Under the Precision-Recall Curve (AUCPR). RESULTS: Single-level CCS, truncated codes, and raw codes significantly outperformed AHRQ-Elixhauser ICD grouping when predicting 30-day postoperative complication and one-year mortality after ICU admission. The performance across groupings was more similar in the 30-day postoperative mortality prediction task. DISCUSSION: Single-level CCS groupings represent aggregations of raw codes into meaningful clinical concepts and consistently balance interoperability between ICD-9-CM and ICD-10-CM while maintaining strong model performance as measured by AUROC and AUCPR. Key limitations include experimentation across two datasets and three prediction tasks, which although were well labeled and sufficiently prevalent, do not encompass all modeling tasks and outcomes. CONCLUSION: Single-level CCS groupings may serve as a good baseline for future models that incorporate diagnosis codes as features in clinical prediction tasks. Code and a compute environment summary are provided along with the analyses to enable reproducibility and to support future research.

Model-Based Algorithms for Detecting Peripheral Artery Disease Using Administrative Data From an Electronic Health Record Data System: Algorithm Development Study.

BACKGROUND: Peripheral artery disease (PAD) affects 8 to 10 million Americans, who face significantly elevated risks of both mortality and major limb events such as amputation. Unfortunately, PAD is relatively underdiagnosed, undertreated, and underresearched, leading to wide variations in treatment patterns and outcomes. Efforts to improve PAD care and outcomes have been hampered by persistent difficulties identifying patients with PAD for clinical and investigatory purposes. OBJECTIVE: The aim of this study is to develop and validate a model-based algorithm to detect patients with peripheral artery disease (PAD) using data from an electronic health record (EHR) system. METHODS: An initial query of the EHR in a large health system identified all patients with PAD-related diagnosis codes for any encounter during the study period. Clinical adjudication of PAD diagnosis was performed by chart review on a random subgroup. A binary logistic regression to predict PAD was built and validated using a least absolute shrinkage and selection operator (LASSO) approach in the adjudicated patients. The algorithm was then applied to the nonsampled records to further evaluate its performance. RESULTS: The initial EHR data query using 406 diagnostic codes yielded 15,406 patients. Overall, 2500 patients were randomly selected for ground truth PAD status adjudication. In the end, 108 code flags remained after removing rarely- and never-used codes. We entered these code flags plus administrative encounter, imaging, procedure, and specialist flags into a LASSO model. The area under the curve for this model was 0.862. CONCLUSIONS: The algorithm we constructed has two main advantages over other approaches to the identification of patients with PAD. First, it was derived from a broad population of patients with many different PAD manifestations and treatment pathways across a large health system. Second, our model does not rely on clinical notes and can be applied in situations in which only administrative billing data (eg, large administrative data sets) are available. A combination of diagnosis codes and administrative flags can accurately identify patients with PAD in large cohorts.

Publisher Correction: High-performance virtual screening by targeting a high-resolution RNA dynamic ensemble.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Impact of Procedural Bleeding in Peripheral Artery Disease: An Analysis From EUCLID Trial.

BACKGROUND: The relationship between invasive vascular procedures and bleeding in patients with peripheral artery disease has not been well described in the literature. This post hoc analysis from the EUCLID trial (Examining Use of Ticagrelor in Peripheral Artery Disease) aimed to describe the incidence of major and minor postprocedural bleeding and characterize the timing and severity of bleeding events relative to the procedure. METHODS: EUCLID was a multicenter, randomized controlled trial of 13 885 patients with symptomatic peripheral artery disease that tested the efficacy and safety of ticagrelor compared with clopidogrel for the prevention of major adverse cardiovascular events. A total of 2661 patients underwent 3062 coronary revascularization, peripheral revascularization, and amputation during the study. The primary safety end point was Thrombolysis in Myocardial Infarction major or minor bleeding. All bleeding events were formally adjudicated by a clinical end point classification group. RESULTS: Major bleeding events most often occurred ≤7 days following the procedure. The incidence of Thrombolysis in Myocardial Infarction major or minor bleeding ≤7 days following peripheral revascularization (3.3%; 95% CI, 2.5%-4.1%) was similar to rates after coronary revascularization (4.0%; 95% CI, 2.6%-5.4%) and lower extremity amputation (2.3%; 95% CI, 0.8%-3.8%). The severity of bleeding events (as graded by drop in hemoglobin, need for transfusion, bleeding in a critical location, and fatal bleeding) was also similar following peripheral, coronary revascularization, and lower extremity amputation. CONCLUSIONS: The incidence of Thrombolysis in Myocardial Infarction major/minor bleeding following peripheral revascularization is comparable to rates after coronary revascularization and lower extremity amputation, and the majority of bleeding events occur within 7 days following the procedure. The severity of periprocedural bleeding is also similar after procedures, with the most frequently adjudicated reason being a drop in hemoglobin ≥2 g/dL. Future studies should be performed to enhance our understanding of bleeding risk related to revascularization and amputation procedures in peripheral artery disease patients.

Endovascular treatment of femoro-popliteal lesions.

Peripheral artery disease (PAD) is a major health concern affecting more than 200 million people worldwide and studies have shown PAD to be a strong predictor of mortality, morbidity, and disability. The management of PAD is multi-tiered and advancements in technology have given physicians more options for endovascular revascularization if medical therapy does not result in substantial improvement. Many randomized controlled trials have reported efficacy of various therapies including laser atherectomy, stent technology, and drug-coated balloons over standard percutaneous transluminal angioplasty; however, uncertainty regarding the best standard of care remains unclear because of a lack of head to head comparisons between novel therapies. Furthermore, variability in the reported clinical outcomes exists and makes it difficult to evaluate the superiority of any specific treatment modality, especially for functional capacity and quality of life. Recently established consensus definitions for clinical outcomes coupled with investigators incorporating direct comparisons within clinical trials will be crucial to establish consistent care and meaningful gain in treatment for these patients. This review will highlight the treatment modalities, literature supporting each treatment modality, and insight into why they are being used and why variation exists around the United States.

High-performance virtual screening by targeting a high-resolution RNA dynamic ensemble.

Dynamic ensembles hold great promise in advancing RNA-targeted drug discovery. Here we subjected the transactivation response element (TAR) RNA from human immunodeficiency virus type-1 to experimental high-throughput screening against ~100,000 drug-like small molecules. Results were augmented with 170 known TAR-binding molecules and used to generate sublibraries optimized for evaluating enrichment when virtually screening a dynamic ensemble of TAR determined by combining NMR spectroscopy data and molecular dynamics simulations. Ensemble-based virtual screening scores molecules with an area under the receiver operator characteristic curve of ~0.85-0.94 and with ~40-75% of all hits falling within the top 2% of scored molecules. The enrichment decreased significantly for ensembles generated from the same molecular dynamics simulations without input NMR data and for other control ensembles. The results demonstrate that experimentally determined RNA ensembles can significantly enrich libraries with true hits and that the degree of enrichment is dependent on the accuracy of the ensemble.