Symptoms and signs of lung cancer prior to diagnosis: Comparative study using electronic health records

Abstract

Background: Lung cancer is the most common cause of cancer-related death in the United States (US), with most patients diagnosed at later stages (3 or 4). While most patients are diagnosed following symptomatic presentation, no studies have compared symptoms and physical examination signs at or prior to diagnosis from electronic health records (EHR) in the United States (US). Objective: To identify symptoms and signs in patients prior to lung cancer diagnosis in EHR data. Study Design: Case-control study. Methods: We studied 698 primary lung cancer cases in adults diagnosed between January 1, 2012 and December 31, 2019, and 6,841 controls matched by age, sex, smoking status, and type of clinic. Coded and free-text data from the EHR were extracted from 2 years prior to diagnosis date for cases and index date for controls. Univariate and multivariate conditional logistic regression were used to identify symptoms and signs associated with lung cancer. Analyses were repeated excluding symptom data from 1, 3, 6, and 12 months before the diagnosis/index dates. Results: Eleven symptoms and signs recorded during the study period were associated with a significantly higher chance of being a lung cancer case in multivariate analyses. Of these, seven were significantly associated with lung cancer six months prior to diagnosis: hemoptysis (OR 3.2, 95%CI 1.9-5.3), cough (OR 3.1, 95%CI 2.4-4.0), chest crackles or wheeze (OR 3.1, 95%CI 2.3-4.1), bone pain (OR 2.7, 95%CI 2.1-3.6), back pain (OR 2.5, 95%CI 1.9-3.2), weight loss (OR 2.1, 95%CI 1.5-2.8) and fatigue (OR 1.6, 95%CI 1.3-2.1). Conclusions: Patients diagnosed with lung cancer appear to have symptoms and signs recorded in the EHR that distinguish them from similar matched patients in ambulatory care, often six months or more before their diagnosis. These findings suggest opportunities to improve the diagnostic process for lung cancer in the US.

How Timely Is Diagnosis of Lung Cancer? Cohort Study of Individuals with Lung Cancer Presenting in Ambulatory Care in the United States

“…Furthermore, NLP extraction is limited by performance of the annotation tool used and what the provider documents, which could vary widely from provider to provider. Third, our definition of onset of clinical presentation based on the documentation of a certain number of symptoms/signs associated with lung cancer may be too non-specific and merely reflect other concomitant illness, however these clinical features are consistent with multiple other studies that have examined clinical presentation of lung cancer in ambulatory care [ 6 , 17 , 51 ].…”

“…NLP identified a richer set of symptoms/signs from free text clinical fields compared to coded data [ 17 ]. This may explain why we identified earlier documentation of symptoms/signs potentially associated lung cancer than previous studies that did not use NLP methods.…”

“…In addition, the rates of lung cancer detected with LDCT screening we observed are consistent with contemporaneous data of screening rates of 3.9% among eligible adults [ 46 ]. Using NLP to extract details of symptoms and clinical features provided more detailed descriptions of clinical presentations than would have been possible using either coded or claims data alone as used in previous research [ 17 ]. Linkage to SEER cancer registry that has been used in multiple previous studies and provided diagnosis dates, staging, as well as key variables at time of diagnosis [ 9 , 47 , 48 ].…”

“…A retrospective cohort of patients who received ambulatory care at UW Medicine (UWM), a health system affiliated with the University of Washington (Seattle, Washington) with a diagnosis of a first, primary lung cancer [ 17 ]. This study was approved by the University of Washington Human Subjects Division (STUDY00008248 and STUDY00013191).…”

“…Definitions of key pre-diagnosis time points were adapted from international cancer reporting standards [ 22 , 23 , 24 ]; (A) First symptomatic presentation, (B) Referral for or receipt of initial chest imaging (chest X-ray or chest CT), (C) Referral to or encounter with a specialist (i.e., Ambulatory Surgery, General Surgery, Hematology, Interventional Radiology, Medical Oncology, Neuro Oncology, Oncology, Palliative Care, Pulmonary Diagnostic Testing, Pulmonary Medicine, Radiation Oncology, Radiation Therapy, Respiratory Disease, Sarcoma, Special Procedures, Surgery, Thoracic, Thoracic Medicine, Thoracic Surgery), (D) Date of diagnosis, and (E) Date of first treatment ( Appendix A ). Date of first symptomatic presentation was based on the presence of symptoms or signs that have previously been identified as significantly associated with the presence of lung cancer compared to matched controls from the same population [ 17 ]. These were: finger clubbing, lymphadenopathy, cough, hemoptysis, chest crackles or wheeze, weight loss, back pain, bone pain, shortness of breath, fatigue or chest pain.…”