Delayed Venous Thromboembolism Diagnosis and Mortality Risk

Abstract

Importance: Nonspecific symptoms of venous thromboembolism (VTE) hinder timely recognition, and no automated tools exist to monitor diagnostic delay.

Objective: To evaluate rates of diagnostic delay of VTE (DOVE) at 2 health care systems using different electronic health record (EHR) systems, to categorize missed diagnoses, and to assess the association of diagnostic delays with 30-day all-cause mortality.

Design, setting, and participants: This diagnostic study used retrospective EHR data from Mass General Brigham (MGB) and Penn State Health (PSH). For MGB, data from 2016 to 2021 were extracted, whereas for PSH, data from 2019 to 2022 data were used. An electronic clinical quality measure (eCQM) was developed and used to quantify DOVE. The eCQM analyses were conducted from 2020 to 2022 at MGB and from 2022 to 2023 at PSH; mortality analyses were conducted from 2023 to 2024. Patients with VTE and documented VTE-related symptoms in primary care were included.

Exposure: Diagnosis of VTE.

Main outcomes and measures: The primary outcomes were DOVE rates and 30-day all-cause mortality by time to diagnosis. DOVE rates were calculated using thresholds of greater than 24 hours and greater than 72 hours, validated through EHR review. Missed opportunities were categorized into system, practitioner, patient, and other unclassified factors. Thirty-day all-cause mortality and risk ratios (RRs) were compared between timely (≤24 hours) and delayed (>24 hours) diagnosis.

Results: A total of 3525 patients were included; 3281 patients (mean [SD] age, 65.95 [15.14] years; 1692 [51.57%] female) were from MGB, and 244 patients (mean [SD] age, 65.34 [16.76] years; 128 [52.46%] female) were from PSH. DOVE eCQM rates using the greater than 24-hour definition were 79.43% (95% CI, 78.00%-81.00%) for MGB and 82.38% (95% CI, 77.00%-87.00%) for PSH. The DOVE rate using the greater than 72-hour definition was 69.89% (95% CI, 68.00%-71.00%) for MGB and 71.31% (95% CI, 65.00%-77.00%) for PSH. Practitioner-related delays were most common. At MGB, mortality increased from 17 deaths (2.52%) for timely diagnosis to 217 deaths (8.33%) for delayed diagnoses, with an RR of 3.31 (95% CI, 2.03-5.38). At PSH, mortality increased from 2 deaths (4.65%) to 12 deaths (5.97%) with an RR of 1.28 (95% CI, 0.30-5.53). Diagnosis at less than 24 hours was often associated with missed pulmonary embolism leading to death.

Conclusions and relevance: In this diagnostic study of delayed VTE diagnosis, consistently high DOVE rates and associated increases in all-cause mortality support the use of the DOVE eCQM tool to guide quality improvement efforts at institutional, regional, and national levels.

Figure.. Process for Identifying Eligible Patients and Incident Cases of Venous Thromboembolism (VTE)

Figure illustrates the steps for identifying eligible patients for the diagnostic delay of VTE (DOVE) electronic clinical quality measure (eCQM). Incident VTE cases were defined using a validated algorithm requiring diagnostic, imaging, and treatment criteria. Each case was linked to a primary care practitioner (PCP) visit within the prior 30 days containing VTE-related symptoms, identified via natural language processing (NLP). Patients aged 18 years or older with no prior VTE and not receiving end-of-life care were included. The DOVE rate reflects the proportion diagnosed more than 24 hours after the index visit. CPT indicates Current Procedural Terminology; ICD-10, International Statistical Classification of Diseases and Related Health Problems, Tenth Revision.