Dataset Information

Development and validation of an algorithm for classifying colonoscopy indication.

ABSTRACT: Accurate determination of colonoscopy indication is required for managing clinical programs and performing research; however, existing algorithms that use available electronic databases (eg, diagnostic and procedure codes) have yielded limited accuracy.To develop and validate an algorithm for classifying colonoscopy indication that uses comprehensive electronic medical data sources.We developed an algorithm for classifying colonoscopy indication by using commonly available electronic diagnostic, pathology, cancer, and laboratory test databases and validated its performance characteristics in comparison with a comprehensive review of patient medical records. We also evaluated the influence of each data source on the algorithm's performance characteristics.Kaiser Permanente Northern California healthcare system.A total of 300 patients who underwent colonoscopy between 2007 and 2010.Colonoscopy.Algorithm's sensitivity, specificity, and positive predictive value (PPV) for classifying screening, surveillance, and diagnostic colonoscopies. The reference standard was the indication assigned after comprehensive medical record review.For screening indications, the algorithm's sensitivity was 88.5% (95% confidence interval [CI], 80.4%-91.7%), specificity was 91.7% (95% CI, 87.0%-95.1%), and PPV was 83.3% (95% CI, 74.7%-90.0%). For surveillance indications, the algorithm's sensitivity was 93.4% (95% CI, 86.2%-97.5%), specificity was 92.8% (95% CI, 88.4%-95.9%), and PPV was 85.0% (95% CI, 76.5%-91.4%). The algorithm's sensitivity, specificity, and PPV for diagnostic indications were 81.4% (95% CI, 73.0%-88.1%), 96.8% (95% CI, 93.2%-98.8%), and 93.9% (95% CI, 87.2%-97.7%), respectively.Validation was confined to a single healthcare system.An algorithm that uses commonly available modern electronic medical data sources yielded a high sensitivity, specificity, and PPV for classifying screening, surveillance, and diagnostic colonoscopy indications. This algorithm had greater accuracy than the indication listed on the colonoscopy report.

SUBMITTER: Lee JK

PROVIDER: S-EPMC4340717 | biostudies-literature | 2015 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of an algorithm for classifying colonoscopy indication.

Lee Jeffrey K JK Jensen Christopher D CD Lee Alexander A Doubeni Chyke A CA Zauber Ann G AG Levin Theodore R TR Zhao Wei K WK Corley Douglas A DA

Gastrointestinal endoscopy 20150108 3

<h4>Background</h4>Accurate determination of colonoscopy indication is required for managing clinical programs and performing research; however, existing algorithms that use available electronic databases (eg, diagnostic and procedure codes) have yielded limited accuracy.<h4>Objective</h4>To develop and validate an algorithm for classifying colonoscopy indication that uses comprehensive electronic medical data sources.<h4>Design</h4>We developed an algorithm for classifying colonoscopy indicatio ...[more]

PMID: 25577596

Similar Datasets

Project description:Accurate indication classification is critical for obtaining unbiased estimates of colonoscopy effectiveness and quality improvement efforts, but there is a dearth of published systematic classification approaches. The objective of this study was to evaluate the effects of data-source and adjudication on indication classification and on estimates of the effectiveness of screening colonoscopy on late-stage colorectal cancer diagnosis risk.This was an observational study in members of four U.S. health plans. Eligible persons (n = 1039) were age 55-85 and had been enrolled for 5 years or longer in their health plans during 2006-2008. Patients were selected based on late-stage colorectal cancer diagnosis in a case-control design; each case patient was matched to 1-2 controls by study site, age, sex, and health plan enrollment duration. Reasons for colonoscopies received in the 10-year period before the reference date were collected from three medical records sources (progress notes; referral notes; procedure reports) and categorized using an algorithm, with committee adjudication of some tests. We evaluated indication classification concordance before and after adjudication and used logistic regressions with the Wald Chi-square test to compare estimates of the effects of screening colonoscopy on late-stage colorectal cancer diagnosis risk for each of our data sources to the adjudicated indication.Classification agreement between each data-source and adjudication was 78.8-94.0% (weighted kappa = 0.53-0.72); the highest agreement (weighted kappa = 0.86-0.88) was when information from all data sources was considered together. The choice of data-source influenced the association between screening colonoscopy and late-stage colorectal cancer diagnosis; estimates based on progress notes were closest to those based on the adjudicated indication (% difference in regression coefficients = 2.4%, p-value = 0.98), as compared to estimates from only referral notes (% difference in coefficients = 34.9%, p-value = 0.12) or procedure reports (% difference in coefficients = 27.4%, p-value = 0.23).There was no single gold-standard source of information in medical records. The estimates of colonoscopy effectiveness from progress notes alone were the closest to estimates using adjudicated indications. Thus, the details in the medical records are necessary for accurate indication classification.

Project description:Accurate diagnostic discrimination of benign renal oncocytoma (OC) and malignant renal cell carcinomas (RCC) is not only useful for planning appropriate treatment strategies of patients with renal masses but also for estimating prognosis. Classification of renal neoplasms solely by histopathology can often be challenging for a variety of reasons. The aim of this study was to develop and validate a genomic algorithm for molecular classification of renal cortical neoplasms that could be implemented in a routine clinical diagnostic setting. Using TCGA (The Cancer Genome Atlas) copy number profiles of over 600 RCC specimens, prior FISH studies and published literature, a classification algorithm was developed consisting of 15 genomic markers: loss of VHL, 3p21, 8p, and chromosomes 1, 2, 6, 10 and 17, and gain of 5qter, 16p, 17q, 20q, and chromosomes 3, 7, and 12. Criteria for scoring specimens for the presence of each genomic marker were established. As validation, 191 surgically resected formalin-fixed paraffin-embedded renal neoplasms were blindly submitted to targeted array-CGH and were classified according to the algorithm. Upon histologic re-review leading to exclusion of three specimens and using histology as the gold standard, the algorithm correctly classified 58 of 62 (93%) clear cell renal cell carcinoma, 51 of 56 (91%) papillary RCC, and 33 of 34 (97%) chromophobe RCC. Of the 36 OC specimens, 17 were classified as OC, two as a malignant subtype, 14 as benign, and three exhibited alterations not associated with a specific subtype. In ten of the latter two groups, CCND1-rearrangement was detected by fluorescence in situ hybridization, affording a classification as OC. Together, 33 of 36 (92%) OC were classified as OC or benign. For the entire validation cohort, an overall diagnostic sensitivity of 93% and above 97% specificity was achieved, suggesting that the implementation of genome-based molecular classification in a clinical diagnostic setting could impact the overall management and outcome of patients with renal tumors. A total of 191 RCC FFPE samples are analyzed including 63 clear cell RCC (ccRCC), 57 papillary RCC (pRCC), 35 chromophobe RCC (chrRCC) and 36 oncocytoma (OC). Two-color array-comparative genomic hybdrization on custom designed using RCC DNA as test and normal sex-matched DNA as reference.

Project description:BackgroundThe use of routine hospital data for understanding patterns of adverse outcomes has been limited in the past by the fact that pre-existing and post-admission conditions have been indistinguishable. The use of a 'Present on Admission' (or POA) indicator to distinguish pre-existing or co-morbid conditions from those arising during the episode of care has been advocated in the US for many years as a tool to support quality assurance activities and improve the accuracy of risk adjustment methodologies. The USA, Australia and Canada now all assign a flag to indicate the timing of onset of diagnoses. For quality improvement purposes, it is the 'not-POA' diagnoses (that is, those acquired in hospital) that are of interest.MethodsOur objective was to develop an algorithm for assessing the validity of assignment of 'not-POA' flags. We undertook expert review of the International Classification of Diseases, 10th Revision, Australian Modification (ICD-10-AM) to identify conditions that could not be plausibly hospital-acquired. The resulting computer algorithm was tested against all diagnoses flagged as complications in the Victorian (Australia) Admitted Episodes Dataset, 2005/06. Measures reported include rates of appropriate assignment of the new Australian 'Condition Onset' flag by ICD chapter, and patterns of invalid flagging.ResultsOf 18,418 diagnosis codes reviewed, 93.4% (n = 17,195) reflected agreement on status for flagging by at least 2 of 3 reviewers (including 64.4% unanimous agreement; Fleiss' Kappa: 0.61). In tests of the new algorithm, 96.14% of all hospital-acquired diagnosis codes flagged were found to be valid in the Victorian records analysed. A lower proportion of individual codes was judged to be acceptably flagged (76.2%), but this reflected a high proportion of codes used <5 times in the data set (789/1035 invalid codes).ConclusionAn indicator variable about the timing of occurrence of diagnoses can greatly expand the use of routinely coded data for hospital quality improvement programmes. The data-cleaning instrument developed and tested here can help guide coding practice in those health systems considering this change in hospital coding. The algorithm embodies principles for development of coding standards and coder education that would result in improved data validity for routine use of non-POA information.

Project description:BackgroundSmartphone-based emergency response apps are increasingly being used to identify and dispatch volunteer first responders (VFRs) to medical emergencies to provide faster first aid, which is associated with better prognoses. Volunteers' availability and willingness to respond are uncertain, leading in recent studies to response rates of 17% to 47%. Dispatch algorithms that select volunteers based on their estimated time of arrival (ETA) without considering the likelihood of response may be suboptimal due to a large percentage of alerts wasted on VFRs with shorter ETA but a low likelihood of response, resulting in delays until a volunteer who will actually respond can be dispatched.ObjectiveThis study aims to improve the decision-making process of human emergency medical services dispatchers and autonomous dispatch algorithms by presenting a novel approach for predicting whether a VFR will respond to or ignore a given alert.MethodsWe developed and compared 4 analytical models to predict VFRs' response behaviors based on emergency event characteristics, volunteers' demographic data and previous experience, and condition-specific parameters. We tested these 4 models using 4 different algorithms applied on actual demographic and response data from a 12-month study of 112 VFRs who received 993 alerts to respond to 188 opioid overdose emergencies. Model 4 used an additional dynamically updated synthetic dichotomous variable, frequent responder, which reflects the responder's previous behavior.ResultsThe highest accuracy (260/329, 79.1%) of prediction that a VFR will ignore an alert was achieved by 2 models that used events data, VFRs' demographic data, and their previous response experience, with slightly better overall accuracy (248/329, 75.4%) for model 4, which used the frequent responder indicator. Another model that used events data and VFRs' previous experience but did not use demographic data provided a high-accuracy prediction (277/329, 84.2%) of ignored alerts but a low-accuracy prediction (153/329, 46.5%) of responded alerts. The accuracy of the model that used events data only was unacceptably low. The J48 decision tree algorithm provided the best accuracy.ConclusionsVFR dispatch has evolved in the last decades, thanks to technological advances and a better understanding of VFR management. The dispatch of substitute responders is a common approach in VFR systems. Predicting the response behavior of candidate responders in advance of dispatch can allow any VFR system to choose the best possible response candidates based not only on ETA but also on the probability of actual response. The integration of the probability to respond into the dispatch algorithm constitutes a new generation of individual dispatch, making this one of the first studies to harness the power of predictive analytics for VFR dispatch. Our findings can help VFR network administrators in their continual efforts to improve the response times of their networks and to save lives.

Dataset Information

Development and validation of an algorithm for classifying colonoscopy indication.

Publications

Development and validation of an algorithm for classifying colonoscopy indication.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets