Development and validation of a preliminary multivariable diagnostic model for identifying unusual infections in hospitalized patients

Aysun Tekin; Mohammad Joghataee; Lucrezia Rovati; Hong Truong; Claudia Castillo-Zambrano; Kushagra Kushagra; Nasrin Nikravangolsefid; Mahmut Ozkan; Ashish Gupta; Vitaly Herasevich; Juan Domecq; John O’Horo; Ognjen Gajic

doi:10.17305/bb.2024.10447

Authors

Aysun Tekin Division of Nephrology and Hypertension, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA https://orcid.org/0000-0002-1891-2118
Mohammad Joghataee Department of Business Analytics and Information Systems, Auburn University, Auburn, AL, USA. https://orcid.org/0000-0002-8849-4695
Lucrezia Rovati Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy
Hong Truong Division of Nephrology and Hypertension, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA
Claudia Castillo-Zambrano Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA https://orcid.org/0000-0002-9469-6656
Kushagra Kushagra Department of Business Analytics and Information Systems, Auburn University, Auburn, AL, USA.
Nasrin Nikravangolsefid Division of Nephrology and Hypertension, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA https://orcid.org/0000-0003-1362-6769
Mahmut Ozkan Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA. https://orcid.org/0000-0001-5905-3498
Ashish Gupta Department of Business Analytics and Information Systems, Auburn University, Auburn, AL, USA.
Vitaly Herasevich Department of Anesthesiology and Critical Care Medicine, Mayo Clinic, Rochester, MN, USA https://orcid.org/0000-0002-0214-0651
Juan Domecq Division of Nephrology and Hypertension, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA
John O’Horo Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA; Division of Infectious Diseases, Mayo Clinic, Rochester, MN, USA https://orcid.org/0000-0002-0880-4498
Ognjen Gajic Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Mayo Clinic, Rochester, MN, USA. https://orcid.org/0000-0003-4218-0890

DOI:

https://doi.org/10.17305/bb.2024.10447

Keywords:

Atypical infections, diagnostic delay, diagnostic model, multivariable model, rare infections

Abstract

Diagnostic delay leads to poor outcomes in infections, and it occurs more often when the causative agent is unusual. Delays are attributable to failing to consider such diagnoses in a timely fashion. Using routinely collected electronic health record (EHR) data, we built a preliminary multivariable diagnostic model for early identification of unusual fungal infections and tuberculosis in hospitalized patients. We conducted a two-gate case-control study. Cases encompassed adult patients admitted to 19 Mayo Clinic enterprise hospitals between January 2010 and March 2023 diagnosed with blastomycosis, cryptococcosis, histoplasmosis, mucormycosis, pneumocystosis, or tuberculosis. Control groups were drawn from all admitted patients (random controls) and those with community-acquired infections (ID-controls). Development and validation datasets were created using randomization for dividing cases and controls (7:3), with a secondary validation using ID-controls. A logistic regression model was constructed using baseline and laboratory variables, with the unusual infections of interest outcome. The derivation dataset comprised 1043 cases and 7000 random controls, while the 451 cases were compared to 3000 random controls and 1990 ID-controls for validation. Within the derivation dataset, the model achieved an area under the curve (AUC) of 0.88 (95% confidence interval [CI]: 0.87-0.89) with a good calibration accuracy (Hosmer-Lemeshow P = 0.623). Comparable performance was observed in the primary (AUC = 0.88; 95% CI: 0.86-0.9) and secondary validation datasets (AUC = 0.84; 95% CI: 0.82-0.86). In this multicenter study, an EHR-based preliminary diagnostic model accurately identified five unusual fungal infections and tuberculosis in hospitalized patients. With further validation, this model could help decrease time to diagnosis.