Toolkit to Compute Time-Based Elixhauser Comorbidity Indices and Extension to Common Data Models

Simple Excel and ICD-10 based dataset calculator for the Charlson and Elixhauser comorbidity indices

Background

The Charlson and Elixhauser Comorbidity Indices are the most widely used comorbidity assessment methods in medical research. Both methods are adapted for use with the International Classification of Diseases, which 10th revision (ICD-10) is used by over a hundred countries in the world. Available Charlson and Elixhauser Comorbidity Index calculating methods are limited to a few applications with command-line user interfaces, all requiring specific programming language skills. This study aims to use Microsoft Excel to develop a non-programming and ICD-10 based dataset calculator for Charlson and Elixhauser Comorbidity Index and to validate its results with R- and SAS-based methods.

Methods

The Excel-based dataset calculator was developed using the program’s formulae, ICD-10 coding algorithms, and different weights of the Charlson and Elixhauser Comorbidity Index. Real, population-wide, nine-year spanning, index hip fracture data from the Estonian Health Insurance Fund was used for validating the calculator. The Excel-based calculator’s output values and processing speed were compared to R- and SAS-based methods.

Results

A total of 11,491 hip fracture patients’ comorbidities were used for validating the Excel-based calculator. The Excel-based calculator’s results were consistent, revealing no discrepancies, with R- and SAS-based methods while comparing 192,690 and 353,265 output values of Charlson and Elixhauser Comorbidity Index, respectively. The Excel-based calculator’s processing speed was slower but differing only from a few seconds up to four minutes with datasets including 6250–200,000 patients.

Conclusions

This study proposes a novel, validated, and non-programming-based method for calculating Charlson and Elixhauser Comorbidity Index scores. As the comorbidity calculations can be conducted in Microsoft Excel’s simple graphical point-and-click interface, the new method lowers the threshold for calculating these two widely used indices.

Trial registration

retrospectively registered.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01492-7.

Patient characteristics and procedural outcomes of moderate sedation for endoscopic procedures in patients with obesity: A retrospective, propensity score-matched study

Background  Endoscopic procedures are performed commonly with moderate sedation. Obesity can pose a challenge in its safe administration. This study was aimed at assessing outcomes of endoscopy procedures performed with moderate sedation in obese patients. Patients and methods  This was a retrospective study of patients undergoing esophagogastroduodenoscopy (EGD) and/or colonoscopy with moderate sedation from July 17, 2017 to December 31, 2019. Demographics, comorbidities, outpatient medications and procedure-related outcomes (procedure time, recovery time, cardiopulmonary adverse events, 7-day post-procedure hospitalization, cecal intubation time, withdrawal time, tolerance of moderate sedation and sedation medications administered) were compared for patient with and without obesity after propensity score matching. Standard statistical methods were used for analysis. Results  A total of 7601 procedures were performed with moderate sedation for 5746 patients. Propensity score matching identified 1360 and 1740 pairs of EGDs and colonoscopies with moderate sedation for patients with and without obesity. Recovery time was found to be shorter for obese patients undergoing EGD (OR: 0.989, 95 % CI: 0.981-.998; P  = 0.01). Obese patients did not differ from non-obese patients in any other procedure-related outcomes for EGDs or colonoscopies. Conclusions  Outcomes for endoscopy procedures performed with moderate sedation were noted to be similar between obese and non-obese patients. These findings suggest that moderate sedation can be used safely for endoscopic procedures in patients with obesity.

Machine Learning Approach to Optimize Sedation Use in Endoscopic Procedures

Endoscopy procedures are often performed with either moderate or deep sedation. While deep sedation is costly, procedures with moderate sedation are not always well tolerated resulting in patient discomfort, and are often aborted. Due to lack of clear guidelines, the decision to utilize moderate sedation or anesthesia for a procedure is made by the providers, leading to high variability in clinical practice. The objective of this study was to build a Machine Learning (ML) model that predicts if a colonoscopy can be successfully completed with moderate sedation based on patients' demographics, comorbidities, and prescribed medications. XGBoost model was trained and tested on 10,025 colonoscopies (70% - 30%) performed at University of Arkansas for Medical Sciences (UAMS). XGBoost achieved average area under receiver operating characteristic curve (AUC) of 0.762, F1-score to predict procedures that need moderate sedation was 0.85, and precision and recall were 0.81 and 0.89 respectively. The proposed model can be employed as a decision support tool for physicians to bolster their confidence while choosing between moderate sedation and anesthesia for a colonoscopy procedure.

Role of Machine Learning Techniques to Tackle the COVID-19 Crisis: Systematic Review

BACKGROUND

SARS-CoV-2, the novel coronavirus responsible for COVID-19, has caused havoc worldwide, with patients presenting a spectrum of complications that have pushed health care experts to explore new technological solutions and treatment plans. Artificial Intelligence (AI)-based technologies have played a substantial role in solving complex problems, and several organizations have been swift to adopt and customize these technologies in response to the challenges posed by the COVID-19 pandemic.

OBJECTIVE

The objective of this study was to conduct a systematic review of the literature on the role of AI as a comprehensive and decisive technology to fight the COVID-19 crisis in the fields of epidemiology, diagnosis, and disease progression.

METHODS

A systematic search of PubMed, Web of Science, and CINAHL databases was performed according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify all potentially relevant studies published and made available online between December 1, 2019, and June 27, 2020. The search syntax was built using keywords specific to COVID-19 and AI.

RESULTS

The search strategy resulted in 419 articles published and made available online during the aforementioned period. Of these, 130 publications were selected for further analyses. These publications were classified into 3 themes based on AI applications employed to combat the COVID-19 crisis: Computational Epidemiology, Early Detection and Diagnosis, and Disease Progression. Of the 130 studies, 71 (54.6%) focused on predicting the COVID-19 outbreak, the impact of containment policies, and potential drug discoveries, which were classified under the Computational Epidemiology theme. Next, 40 of 130 (30.8%) studies that applied AI techniques to detect COVID-19 by using patients' radiological images or laboratory test results were classified under the Early Detection and Diagnosis theme. Finally, 19 of the 130 studies (14.6%) that focused on predicting disease progression, outcomes (ie, recovery and mortality), length of hospital stay, and number of days spent in the intensive care unit for patients with COVID-19 were classified under the Disease Progression theme.

CONCLUSIONS

In this systematic review, we assembled studies in the current COVID-19 literature that utilized AI-based methods to provide insights into different COVID-19 themes. Our findings highlight important variables, data types, and available COVID-19 resources that can assist in facilitating clinical and translational research.