Journal article
A clinically-guided unsupervised clustering approach to recommend symptoms of disease associated with diagnostic opportunities
Diagnosis (Berlin, Germany), Vol.10(1), pp.43-53
02/2023
DOI: 10.1515/dx-2022-0044
PMCID: PMC9934811
PMID: 36127310
Abstract
Objectives
A first step in studying diagnostic delays is to select the signs, symptoms and alternative diseases that represent missed diagnostic opportunities. Because this step is labor intensive requiring exhaustive literature reviews, we developed machine learning approaches to mine administrative data sources and recommend conditions for consideration. We propose a methodological approach to find diagnostic codes that exhibit known patterns of diagnostic delays and apply this to the diseases of tuberculosis and appendicitis.
Methods
We used the IBM MarketScan Research Databases, and consider the initial symptoms of cough before tuberculosis and abdominal pain before appendicitis. We analyze diagnosis codes during healthcare visits before the index diagnosis, and use k-means clustering to recommend conditions that exhibit similar trends to the initial symptoms provided. We evaluate the clinical plausibility of the recommended conditions and the corresponding number of possible diagnostic delays based on these diseases.
Results
For both diseases of interest, the clustering approach suggested a large number of clinically-plausible conditions to consider (e.g., fever, hemoptysis, and pneumonia before tuberculosis). The recommended conditions had a high degree of precision in terms of clinical plausibility: >70% for tuberculosis and >90% for appendicitis. Including these additional clinically-plausible conditions resulted in more than twice the number of possible diagnostic delays identified.
Conclusions
Our approach can mine administrative datasets to detect patterns of diagnostic delay and help investigators avoid under-identifying potential missed diagnostic opportunities. In addition, the methods we describe can be used to discover less-common presentations of diseases that are frequently misdiagnosed.
Details
- Title: Subtitle
- A clinically-guided unsupervised clustering approach to recommend symptoms of disease associated with diagnostic opportunities
- Creators
- Aaron C Miller - Roy J. and Lucille A. Carver College of MedicineAlan T Arakkal - University of IowaScott H Koeneman - University of IowaJoseph E Cavanaugh - University of IowaPhilip M Polgreen - Roy J. and Lucille A. Carver College of Medicine
- Resource Type
- Journal article
- Publication Details
- Diagnosis (Berlin, Germany), Vol.10(1), pp.43-53
- DOI
- 10.1515/dx-2022-0044
- PMID
- 36127310
- PMCID
- PMC9934811
- NLM abbreviation
- Diagnosis (Berl)
- ISSN
- 2194-802X
- eISSN
- 2194-802X
- Grant note
- DOI: 10.13039/100000133, name: Agency for Healthcare Research and Quality, award: 5R01HS027375
- Language
- English
- Electronic publication date
- 09/21/2022
- Date published
- 02/2023
- Academic Unit
- Statistics and Actuarial Science; Infectious Diseases; Epidemiology; Biostatistics; Injury Prevention Research Center; Internal Medicine
- Record Identifier
- 9984296161402771
Metrics
38 Record Views