When your words count: a discriminative model to predict approval of referrals.

Inform Prim Care

Houston VA Health Services Research and Development Center of Excellence, Michael E De Bakey Veterans Affairs Medical Center and Baylor College of Medicine, 20002 Holcombe Blvd 152, Houston, TX 77030, USA.

Published: May 2010

Objective: To develop and test a statistical model which correctly predicts the approval of outpatient referrals when reviewed by a specialty service based on nine discriminating variables.

Design: Retrospective cross-sectional study.

Setting: Large public county hospital system in a southern US city.

Participants: Written documents and associated data from 500 random adult referrals made by primary care providers to various specialty services during the course of one month.

Main Outcome Measures: The resulting correct prediction rates obtained by the model.

Results: The model correctly predicted 78.6% of approved referrals using all nine discriminating variables, 75.3% of approved referrals using all variables in a stepwise manner and 74.7% of approved referrals using only the referral total word count as a single discriminating variable.

Conclusions: Three iterations of the model correctly predicted at least 75% of the approved referrals in the validation set. A correct prediction of whether or not a referral will be approved can be made in three out of four cases.

Download full-text PDF

Source
http://dx.doi.org/10.14236/jhi.v17i4.738DOI Listing

Publication Analysis

Top Keywords

approved referrals
16
model correctly
12
correct prediction
8
correctly predicted
8
referrals
7
approved
5
count discriminative
4
model
4
discriminative model
4
model predict
4

Similar Publications

Background: An idiopathic macular hole (IMH) is a foveal opening in the neurosensory retina caused by perifoveal vitreomacular traction and detachment. IMH prevalence varies considerably across populations, highlighting a need for further investigation, especially in underrepresented groups such as Hispanics.

Methods: This retrospective, descriptive, cross-sectional study analyzed IMH prevalence in a Hispanic population over four years.

View Article and Find Full Text PDF

Background: Neurobrucellosis, a serious central nervous system infection caused by Brucella species, presents significant challenges due to its diverse clinical manifestations and the risk of long-term complications and poor outcomes. Identifying predictors of adverse outcomes is critical for improving patient management and overall prognosis.

Objectives: This study aimed to evaluate the long-term morbidity and mortality associated with neurobrucellosis and to identify key predictors of adverse outcomes.

View Article and Find Full Text PDF

Background: The global burden of HIV and AIDS continues to significantly impact public health, particularly in Sub-Saharan Africa. This study investigates the spatial distribution and associated risk factors of HIV prevalence in Botswana using data from the 2021 Botswana AIDS Impact Survey (BAIS V).

Methods: The analysis included 12,653 adults aged 15-64 years and employed chi-square tests, multilevel mixed-effects regression, and spatial analysis techniques.

View Article and Find Full Text PDF

Background: Cholangiocarcinoma (CCA) is a type of cancer that develops in the biliary tract. CCA accounts for 10% of primary hepatic cancers and is characterized by its aggressive nature and poor prognosis. This systematic review and meta-analysis aims to assess the prognostic value of the novel hepatic function assessment measure known as albumin-bilirubin (ALBI) grade in patients with CCA.

View Article and Find Full Text PDF

Background: Nephrology referral has been recognized as a modifiable factor influencing patient outcomes. The study aimed to compare clinical outcomes among patients referred early versus late to nephrologists.

Methods: We searched online database from inception to June 1, 2022, to obtain all eligible literature reporting outcomes of patients referred early versus late to nephrologists.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!