The Probability of Lung Cancer in Patients With Incidentally Detected Pulmonary Nodules: Clinical Characteristics and Accuracy of Prediction Models.

BACKGROUND: The frequency of cancer and accuracy of prediction models have not been studied in large, population-based samples of patients with incidental pulmonary nodules measuring > 8 mm in diameter. RESEARCH QUESTIONS: How does the frequency of cancer vary by size and smoking history among patients with incidental nodules? How accurate are two widely used models for identifying cancer in these patients? STUDY DESIGN AND METHODS: We assembled a retrospective cohort of individuals with incidental nodules measuring > 8 mm in diameter identified by chest CT imaging between 2006 and 2016. We used a validated natural language processing algorithm to identify nodules and their characteristics by scanning the text of dictated radiology reports. We reported patient and nodule characteristics stratified by the presence or absence of a lung cancer diagnosis within 27 months of nodule identification and estimated the area under the receiver operating characteristic curve (AUC) to compare the accuracy of the Mayo Clinic and Brock models for identifying cancer. RESULTS: The sample included 23,780 individuals with a nodule measuring > 8 mm, including 2,356 patients (9.9%) with a lung cancer diagnosis within 27 months of nodule identification. Cancer was diagnosed in 5.4% of never smokers, 12.2% of former smokers, and 17.7% of current smokers. Cancer was diagnosed in 5.7% of patients with nodules measuring 9 to 15 mm, 12.1% of patients with nodules > 15 to 20 mm, and 18.4% of patients with nodules > 20 to 30 mm. In the full sample, the Mayo Clinic model (AUC, 0.747; 95% CI, 0.737-0.757) was more accurate than the Brock model (AUC, 0.713; 95% CI, 0.702-0.724; P < .0001). When restricted to ever smokers, the Mayo Clinic model was still more accurate. Both models overestimated the probability of cancer. INTERPRETATION: Almost 10% of patients with an incidental pulmonary nodule measuring > 8 mm in diameter will receive a lung cancer diagnosis. Existing prediction models have only fair accuracy and overestimate the probability of cancer.

Natural Language Processing to Identify Pulmonary Nodules and Extract Nodule Characteristics From Radiology Reports.

BACKGROUND: There is an urgent need for population-based studies on managing patients with pulmonary nodules. RESEARCH QUESTION: Is it possible to identify pulmonary nodules and associated characteristics using an automated method? STUDY DESIGN AND METHODS: We revised and refined an existing natural language processing (NLP) algorithm to identify radiology transcripts with pulmonary nodules and greatly expanded its functionality to identify the characteristics of the largest nodule, when present, including size, lobe, laterality, attenuation, calcification, and edge. We compared NLP results with a reference standard of manual transcript review in a random test sample of 200 radiology transcripts. We applied the final automated method to a larger cohort of patients who underwent chest CT scan in an integrated health care system from 2006 to 2016, and described their demographic and clinical characteristics. RESULTS: In the test sample, the NLP algorithm had very high sensitivity (98.6%; 95% CI, 95.0%-99.8%) and specificity (100%; 95% CI, 93.9%-100%) for identifying pulmonary nodules. For attenuation, edge, and calcification, the NLP algorithm achieved similar accuracies, and it correctly identified the diameter of the largest nodule in 135 of 141 cases (95.7%; 95% CI, 91.0%-98.4%). In the larger cohort, the NLP found 217,771 reports with nodules among 717,304 chest CT reports (30.4%). From 2006 to 2016, the number of reports with nodules increased by 150%, and the mean size of the largest nodule gradually decreased from 11 to 8.9 mm. Radiologists documented the laterality and lobe (90%-95%) more often than the attenuation, calcification, and edge characteristics (11%-14%). INTERPRETATION: The NLP algorithm identified pulmonary nodules and associated characteristics with high accuracy. In our community practice settings, the documentation of nodule characteristics is incomplete. Our results call for better documentation of nodule findings. The NLP algorithm can be used in population-based studies to identify pulmonary nodules, avoiding labor-intensive chart review.

Radiotherapy for brain metastases near the end of life in an integrated health care system.

BACKGROUND: To examine radiotherapy (RT) patterns-of-care and utilization at the end of life (EOL) among non-small cell lung cancer (NSCLC) patients with brain metastasis (BrM) in an integrated health care system. METHODS: Central tumor registry identified 5,133 patients diagnosed with NSCLC from 2007-2011. BrM were determined by imaging. Patient and clinical characteristics were obtained by chart abstraction. In addition to abstracted variables, graded prognostic assessment (GPA) score of 0-1 was derived by collected data and tested as a predictor of death within 14 or 30 days of RT. RESULTS: On NSCLC presentation, 10% harbored BrM while 7% developed BrM thereafter. Of 900 BrM patients, 15% were not referred for RT, with median time to death of 21 days. Median time to death for 5% not recommended RT was 48 days. Among those receiving brain RT, 11.9% died within 14 days and 23.3% (cumulatively) died within 30 days of treatment. Over 50% with GPA score 0-1 received RT, 11% within 14 days and 21% within 30 days of death; median survival of GPA score 0-1 patients was 49 days. GPA score 0-1 independently predicted for death within 30 days of RT receipt. CONCLUSIONS: BrM are common in NSCLC, and most patients are referred for brain RT. A surprising proportion of patients received treatment near the EOL, as 23% died within 30 days of RT. GPA score of 0-1 predicted for death within 30 days of treatment. RT referral, recommendation, and timing should be better tailored to life expectancy, and additional benchmarks for quality of care are needed.

Health-related quality of life outcomes from a contemporary prostate cancer registry in a large diverse population.

OBJECTIVE: To assess the health-related quality of life (HRQoL) of patients with prostate cancer up to 24 months after treatment in a contemporary large diverse population. PATIENTS AND METHODS: Patients with newly diagnosed prostate cancer from March 2011 to January 2014 in our healthcare system were included. The Expanded Prostate Cancer Index Composite (EPIC-26) questionnaire was administered before treatment, and at 1, 3, 6, 12, 18, and 24 months after treatment up to November 2014 for all methods of treatment. The Kruskall-Wallis test was used to compare the distribution of each EPIC-26 domain score at each time point, and mixed models were used to assess the overall scores over the period after treatment. RESULTS: In all, 5 727 patients were included. There were data for 3 422, 2 329, 2 017, 1 922, 1 772, 1 260, and 837 patients before treatment, and at 1, 3, 6, 12, 18, and 24 months after treatment, respectively. At 1 month, bowel scores were the lowest for patients that had had radiation therapy, and urinary irritative symptoms were the lowest for those who had had brachytherapy. There were sexual function declines for all the treatment methods, with surgery having the steepest decline; open radical prostatectomy (ORP) had a greater decline than robot-assisted laparoscopic prostatectomy (RALP). Patients who underwent RALP had a better return of sexual function, approaching that of brachytherapy and radiation therapy at 24 months. Urinary incontinence (UI) also declined the most in surgical patients, with RALP patients improving slightly more than ORP patients at 12-24 months. CONCLUSIONS: Patients' HRQoL after prostate cancer treatment varies by treatment method. Notably, sexual function recovers most for RALP patients. UI remains worse at 24 months after surgery, compared to other methods of prostate cancer treatment.

Recent Trends in the Identification of Incidental Pulmonary Nodules.

RATIONALE: Pulmonary nodules are common incidental findings, but information about their incidence in the era of computed tomography (CT) is lacking. OBJECTIVES: To examine recent trends in pulmonary nodule identification. METHODS: We used electronic health records and natural language processing to identify members of an integrated health system who had nodules measuring 4 to 30 mm. We calculated rates of chest CT imaging, nodule identification, and receipt of a new lung cancer diagnosis within 2 years of nodule identification, and standardized rates by age and sex to estimate the frequency of nodule identification in the U.S. population in 2010. MEASUREMENTS AND MAIN RESULTS: Between 2006 and 2012, more than 200,000 adult members underwent 415,581 chest CT examinations. The annual frequency of chest CT imaging increased from 1.3 to 1.9% for all adult members, whereas the frequency of nodule identification increased from 24 to 31% for all scans performed. The annual rate of chest CT increased from 15.4 to 20.7 per 1,000 person-years, and the rate of nodule identification increased from 3.9 to 6.6 per 1,000 person-years, whereas the rate of a new lung cancer diagnosis remained stable. By extrapolation, more than 4.8 million Americans underwent at least one chest CT scan and 1.57 million had a nodule identified, including 63,000 who received a new lung cancer diagnosis within 2 years. CONCLUSIONS: Incidental pulmonary nodules are an increasingly common consequence of routine medical care, with an incidence that is much greater than recognized previously. More frequent nodule identification has not been accompanied by increases in the diagnosis of cancerous nodules.

A natural language processing program effectively extracts key pathologic findings from radical prostatectomy reports.

INTRODUCTION AND OBJECTIVE: Natural language processing (NLP) software programs have been widely developed to transform complex free text into simplified organized data. Potential applications in the field of medicine include automated report summaries, physician alerts, patient repositories, electronic medical record (EMR) billing, and quality metric reports. Despite these prospects and the recent widespread adoption of EMR, NLP has been relatively underutilized. The objective of this study was to evaluate the performance of an internally developed NLP program in extracting select pathologic findings from radical prostatectomy specimen reports in the EMR. METHODS: An NLP program was generated by a software engineer to extract key variables from prostatectomy reports in the EMR within our healthcare system, which included the TNM stage, Gleason grade, presence of a tertiary Gleason pattern, histologic subtype, size of dominant tumor nodule, seminal vesicle invasion (SVI), perineural invasion (PNI), angiolymphatic invasion (ALI), extracapsular extension (ECE), and surgical margin status (SMS). The program was validated by comparing NLP results to a gold standard compiled by two blinded manual reviewers for 100 random pathology reports. RESULTS: NLP demonstrated 100% accuracy for identifying the Gleason grade, presence of a tertiary Gleason pattern, SVI, ALI, and ECE. It also demonstrated near-perfect accuracy for extracting histologic subtype (99.0%), PNI (98.9%), TNM stage (98.0%), SMS (97.0%), and dominant tumor size (95.7%). The overall accuracy of NLP was 98.7%. NLP generated a result in <1 second, whereas the manual reviewers averaged 3.2 minutes per report. CONCLUSIONS: This novel program demonstrated high accuracy and efficiency identifying key pathologic details from the prostatectomy report within an EMR system. NLP has the potential to assist urologists by summarizing and highlighting relevant information from verbose pathology reports. It may also facilitate future urologic research through the rapid and automated creation of large databases.

Extracting data from electronic medical records: validation of a natural language processing program to assess prostate biopsy results.

OBJECTIVE: The extraction of specific data from electronic medical records (EMR) remains tedious and is often performed manually. Natural language processing (NLP) programs have been developed to identify and extract information within clinical narrative text. We performed a study to assess the validity of an NLP program to accurately identify patients with prostate cancer and to retrieve pertinent pathologic information from their EMR. MATERIALS AND METHODS: A retrospective review was performed of a prospectively collected database including patients from the Southern California Kaiser Permanente Medical Region that underwent prostate biopsies during a 2-week period. A NLP program was used to identify patients with prostate biopsies that were positive for prostatic adenocarcinoma from all pathology reports within this period. The application then processed 100 consecutive patients with prostate adenocarcinoma to extract 10 variables from their pathology reports. The extraction and retrieval of information by NLP was then compared to a blinded manual review. RESULTS: A consecutive series of 18,453 pathology reports were evaluated. NLP correctly detected 117 out of 118 patients (99.1%) with prostatic adenocarcinoma after TRUS-guided prostate biopsy. NLP had a positive predictive value of 99.1% with a 99.1% sensitivity and a 99.9% specificity to correctly identify patients with prostatic adenocarcinoma after biopsy. The overall ability of the NLP application to accurately extract variables from the pathology reports was 97.6%. CONCLUSIONS: Natural language processing is a reliable and accurate method to identify select patients and to extract relevant data from an existing EMR in order to establish a prospective clinical database.

Automated identification of patients with pulmonary nodules in an integrated health system using administrative health plan data, radiology reports, and natural language processing.

INTRODUCTION: Lung nodules are commonly encountered in clinical practice, yet little is known about their management in community settings. An automated method for identifying patients with lung nodules would greatly facilitate research in this area. METHODS: Using members of a large, community-based health plan from 2006 to 2010, we developed a method to identify patients with lung nodules, by combining five diagnostic codes, four procedural codes, and a natural language processing algorithm that performed free text searches of radiology transcripts. An experienced pulmonologist reviewed a random sample of 116 radiology transcripts, providing a reference standard for the natural language processing algorithm. RESULTS: With the use of an automated method, we identified 7112 unique members as having one or more incident lung nodules. The mean age of the patients was 65 years (standard deviation 14 years). There were slightly more women (54%) than men, and Hispanics and non-whites comprised 45% of the lung nodule cohort. Thirty-six percent were never smokers whereas 11% were current smokers. Fourteen percent of the patients were subsequently diagnosed with lung cancer. The sensitivity and specificity of the natural language processing algorithm for identifying the presence of lung nodules were 96% and 86%, respectively, compared with clinician review. Among the true positive transcripts in the validation sample, only 35% were solitary and unaccompanied by one or more associated findings, and 56% measured 8 to 30 mm in diameter. CONCLUSIONS: A combination of diagnostic codes, procedural codes, and a natural language processing algorithm for free text searching of radiology reports can accurately and efficiently identify patients with incident lung nodules, many of whom are subsequently diagnosed with lung cancer.