Dataset Information

Predicting Non-Adherence with Outpatient Colonoscopy Using a Novel Electronic Tool that Measures Prior Non-Adherence.

ABSTRACT:

Background

Accurately predicting the risk of no-show for a scheduled colonoscopy can help target interventions to improve compliance with colonoscopy, and thereby reduce the disease burden of colorectal cancer and enhance the utilization of resources within endoscopy units.

Objectives

We aimed to utilize information available in an electronic medical record (EMR) and endoscopy scheduling system to create a predictive model for no-show risk, and to simultaneously evaluate the role for natural language processing (NLP) in developing such a model.

Design

This was a retrospective observational study using discovery and validation phases to design a colonoscopy non-adherence prediction model. An NLP-derived variable called the Non-Adherence Ratio ("NAR") was developed, validated, and included in the model.

Participants

Patients scheduled for outpatient colonoscopy at an Academic Medical Center (AMC) that is part of a multi-hospital health system, 2009 to 2011, were included in the study.

Main measures

Odds ratios for non-adherence were calculated for all variables in the discovery cohort, and an Area Under the Receiver Operating Curve (AUC) was calculated for the final non-adherence prediction model.

Key results

The non-adherence model included six variables: 1) gender; 2) history of psychiatric illness, 3) NAR; 4) wait time in months; 5) number of prior missed endoscopies; and 6) education level. The model achieved discrimination in the validation cohort (AUC= =70.2 %). At a threshold non-adherence score of 0.46, the model's sensitivity and specificity were 33 % and 92 %, respectively. Removing the NAR from the model significantly reduced its predictive power (AUC = 64.3 %, difference = 5.9 %, p < 0.001).

Conclusions

A six-variable model using readily available clinical and demographic information demonstrated accuracy for predicting colonoscopy non-adherence. The NAR, a novel variable developed using NLP technology, significantly strengthened this model's predictive power.

SUBMITTER: Blumenthal DM

PROVIDER: S-EPMC4441666 | biostudies-literature | 2015 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Non-Adherence with Outpatient Colonoscopy Using a Novel Electronic Tool that Measures Prior Non-Adherence.

Blumenthal Daniel M DM Singal Gaurav G Mangla Shikha S SS Macklin Eric A EA Chung Daniel C DC

Journal of general internal medicine 20150114 6

<h4>Background</h4>Accurately predicting the risk of no-show for a scheduled colonoscopy can help target interventions to improve compliance with colonoscopy, and thereby reduce the disease burden of colorectal cancer and enhance the utilization of resources within endoscopy units.<h4>Objectives</h4>We aimed to utilize information available in an electronic medical record (EMR) and endoscopy scheduling system to create a predictive model for no-show risk, and to simultaneously evaluate the role ...[more]

PMID: 25586869

Similar Datasets

Project description:OBJECTIVE:The authors sought to develop and validate models using electronic health records to predict suicide attempt and suicide death following an outpatient visit. METHOD:Across seven health systems, 2,960,929 patients age 13 or older (mean age, 46 years; 62% female) made 10,275,853 specialty mental health visits and 9,685,206 primary care visits with mental health diagnoses between Jan. 1, 2009, and June 30, 2015. Health system records and state death certificate data identified suicide attempts (N=24,133) and suicide deaths (N=1,240) over 90 days following each visit. Potential predictors included 313 demographic and clinical characteristics extracted from records for up to 5 years before each visit: prior suicide attempts, mental health and substance use diagnoses, medical diagnoses, psychiatric medications dispensed, inpatient or emergency department care, and routinely administered depression questionnaires. Logistic regression models predicting suicide attempt and death were developed using penalized LASSO (least absolute shrinkage and selection operator) variable selection in a random sample of 65% of the visits and validated in the remaining 35%. RESULTS:Mental health specialty visits with risk scores in the top 5% accounted for 43% of subsequent suicide attempts and 48% of suicide deaths. Of patients scoring in the top 5%, 5.4% attempted suicide and 0.26% died by suicide within 90 days. C-statistics (equivalent to area under the curve) for prediction of suicide attempt and suicide death were 0.851 (95% CI=0.848, 0.853) and 0.861 (95% CI=0.848, 0.875), respectively. Primary care visits with scores in the top 5% accounted for 48% of subsequent suicide attempts and 43% of suicide deaths. C-statistics for prediction of suicide attempt and suicide death were 0.853 (95% CI=0.849, 0.857) and 0.833 (95% CI=0.813, 0.853), respectively. CONCLUSIONS:Prediction models incorporating both health record data and responses to self-report questionnaires substantially outperform existing suicide risk prediction tools.

Project description:ImportanceThere are insufficient data describing the incidence and risk factors of postcolonoscopy complications in older individuals.ObjectiveTo assess the association between older age (?75 years) and the risk of postcolonoscopy complications.Design, setting, and participantsThis population-based retrospective cohort study included adults (?50 years) undergoing outpatient colonoscopy between April 2008 and September 2017, identified from Ontario administrative databases. Individuals with inflammatory bowel disease and hereditary colorectal cancer syndromes were excluded. The study population was subdivided into a colorectal cancer screening-eligible cohort (patients aged 50-74 years) and an older cohort (patients aged ?75 years). The statistical analysis was conducted from December 2018 to September 2019.ExposuresOlder age (?75 years).Main outcomes and measuresThe primary outcome was postcolonoscopy complications, defined as the composite of hospitalization or emergency department visits in the 30-day period after the outpatient colonoscopy. Secondary outcomes included incidence of surgically treated colorectal cancer and all-cause mortality at 30 days. Independent variables associated with postcolonoscopy complications were also assessed.ResultsThe study sample included 38?069 patients; the mean (SD) age was 65.2 (10.1) years, there were 19?037 women (50.0%), and 27?831 patients (73.1%) underwent a first colonoscopy. The cumulative incidence of complications was 3.4% (1310 patients) in the overall population, and it was higher in individuals aged 75 years or older (515 of 7627 patients [6.8%]) than in screening-eligible cohort (795 of 30?443 patients [2.6%]) (P?<?.001). Independent risk factors for postcolonoscopy complications were age 75 years or older (odds ratio [OR], 2.3; 95% CI, 2.0-2.6), anemia (OR, 1.4; 95% CI, 1.2-1.7), cardiac arrhythmia (OR, 1.7; 95% CI, 1.2-2.2), congestive heart failure (OR, 3.4; 95% CI, 2.5-4.6), hypertension (OR, 1.2; 95% CI, 1.0-1.5), chronic kidney disease (OR, 1.8; 95% CI, 1.1-3.0), liver disease (OR, 4.7; 95% CI, 3.5-6.5), smoking history (OR, 3.2; 95% CI, 2.4-4.3), and obesity (OR, 2.3; 95% CI, 1.2-4.2). The number of previous colonoscopies was associated with a lower risk of complications (OR, 0.9; 95% CI, 0.7-1.0). The incidence of surgically treated colorectal cancer was higher in the older cohort than the screening-eligible cohort (119 patients [1.6%] vs 144 patients [0.5%]; P?<?.001). All-cause mortality rates were 0.1% overall (39 patients) and 0.1% (19 patients) for individuals aged 50 to 74 years and 0.2% (20 patients) for those aged 75 years and older (P?<?.001).Conclusions and relevanceIn this population-based cohort study of individuals living in southern Ontario, age of 75 years and older was associated with a higher risk of 30-day postprocedure complications after outpatient colonoscopy. These findings suggest that the decision to perform a colonoscopy should be carefully considered in patients older than 75 years, especially in the presence of comorbidities. Further studies are needed to better understand the benefits of invasive procedures as opposed to less invasive approaches for colorectal cancer screening and surveillance among older patients.

Project description:BackgroundClinical-performance measurement has helped improve the quality of health-care; yet success in attaining high levels of quality across multiple domains simultaneously still varies considerably. Although many sources of variability in care quality have been studied, the difficulty required to complete the clinical work itself has received little attention.ObjectiveWe present a task-based methodology for evaluating the difficulty of clinical-performance measures (CPMs) by assessing the complexity of their component requisite tasks.DesignUsing Functional Job Analysis (FJA), subject-matter experts (SMEs) generated task lists for 17 CPMs; task lists were rated on ten dimensions of complexity, and then aggregated into difficulty composites.ParticipantsEleven outpatient work SMEs; 133 VA Medical Centers nationwide.Main measuresClinical Performance: 17 outpatient CPMs (2000-2008) at 133 VA Medical Centers nationwide. Measure Difficulty: for each CPM, the number of component requisite tasks and the average rating across ten FJA complexity scales for the set of tasks comprising the measure.Key resultsMeasures varied considerably in the number of component tasks (M?=?10.56, SD?=?6.25, min?=?5, max?=?25). Measures of chronic care following acute myocardial infarction exhibited significantly higher measure difficulty ratings compared to diabetes or screening measures, but not to immunization measures ([Formula: see text]?=?0.45, -0.04, -0.05, and -0.06 respectively; F (3, 186)?=?3.57, p?=?0.015). Measure difficulty ratings were not significantly correlated with the number of component tasks (r?=?-0.30, p?=?0.23).ConclusionsEvaluating the difficulty of achieving recommended CPM performance levels requires more than simply counting the tasks involved; using FJA to assess the complexity of CPMs' component tasks presents an alternate means of assessing the difficulty of primary-care CPMs and accounting for performance variation among measures and performers. This in turn could be used in designing performance reward programs, or to match workflow to clinician time and effort.

Dataset Information

Predicting Non-Adherence with Outpatient Colonoscopy Using a Novel Electronic Tool that Measures Prior Non-Adherence.

Background

Objectives

Design

Participants

Main measures

Key results

Conclusions

Publications

Predicting Non-Adherence with Outpatient Colonoscopy Using a Novel Electronic Tool that Measures Prior Non-Adherence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets