Development and validation of a case definition to estimate the prevalence and incidence of cirrhosis in pan-Canadian primary care databases.

Aims: To develop and validate case definitions to identify patients with cirrhosis and alcohol-related cirrhosis using primary care electronic medical records (EMRs) and to estimate cirrhosis prevalence and incidence in pan-Canadian primary care databases, between 2011 and 2019. Methods: A total of 689,301 adult patients were included with ≥1 visit to a primary care provider within the Canadian Primary Care Sentinel Study Network between January 1, 2017, and December 31, 2018. A subsample of 17,440 patients was used to validate the case definitions. Sensitivity, specificity, predictive values were calculated with their 95% CIs and then determined the population-level prevalence and incidence trends with the most accurate case definition. Results: The most accurate case definition included: ≥1 health condition, billing, or encounter diagnosis for International Classification of Diseases, Ninth Revision codes 571.2, 571.5, 789.59, or 571. Sensitivity (84.6; 95% CI 83.1%-86.%), specificity (99.3; 95% CI 99.1%-99.4%), positive predictive values (94.8; 95% CI 93.9%-95.7%), and negative predictive values (97.5; 95% CI 97.3%-97.7%). Application of this definition to the overall population resulted in a crude prevalence estimate of (0.46%; 95% CI 0.45%-0.48%). Annual incidence of patients with a clinical diagnosis of cirrhosis nearly doubled between 2011 (0.05%; 95% CI 0.04%-0.06%) and 2019 to (0.09%; 95% CI 0.08%-0.09%). Conclusions: The EMR-based case definition accurately captured patients diagnosed with cirrhosis in primary care. Future work to characterize patients with cirrhosis and their primary care experiences can support improvements in identification and management in primary care settings.

Pan-Canadian Electronic Medical Record Diagnostic and Unstructured Text Data for Capturing PTSD: Retrospective Observational Study.

BACKGROUND: The availability of electronic medical record (EMR) free-text data for research varies. However, access to short diagnostic text fields is more widely available. OBJECTIVE: This study assesses agreement between free-text and short diagnostic text data from primary care EMR for identification of posttraumatic stress disorder (PTSD). METHODS: This retrospective cross-sectional study used EMR data from a pan-Canadian repository representing 1574 primary care providers at 265 clinics using 11 EMR vendors. Medical record review using free text and short diagnostic text fields of the EMR produced reference standards for PTSD. Agreement was assessed with sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. RESULTS: Our reference set contained 327 patients with free text and short diagnostic text. Among these patients, agreement between free text and short diagnostic text had an accuracy of 93.6% (CI 90.4%-96.0%). In a single Canadian province, case definitions 1 and 4 had a sensitivity of 82.6% (CI 74.4%-89.0%) and specificity of 99.5% (CI 97.4%-100%). However, when the reference set was expanded to a pan-Canada reference (n=12,104 patients), case definition 4 had the strongest agreement (sensitivity: 91.1%, CI 90.1%-91.9%; specificity: 99.1%, CI 98.9%-99.3%). CONCLUSIONS: Inclusion of free-text encounter notes during medical record review did not lead to improved capture of PTSD cases, nor did it lead to significant changes in case definition agreement. Within this pan-Canadian database, jurisdictional differences in diagnostic codes and EMR structure suggested the need to supplement diagnostic codes with natural language processing to capture PTSD. When unavailable, short diagnostic text can supplement free-text data for reference set creation and case validation. Application of the PTSD case definition can inform PTSD prevalence and characteristics.

Characterizing primary care patients with posttraumatic stress disorder using electronic medical records: a retrospective cross-sectional study.

BACKGROUND: Posttraumatic stress disorder (PTSD) has significant morbidity and economic costs. This study describes the prevalence and characteristics of patients with PTSD using primary care electronic medical record (EMR) data. METHODS: This retrospective cross-sectional study used EMR data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). This study included 1,574 primary care providers located in 7 Canadian provinces. There were 689,301 patients that visited a CPCSSN provider between 1 January 2017 and 31 December 2019. We describe associations between PTSD and patient characteristics using descriptive statistics, chi-square, and multiple logistic regression models. RESULTS: Among the 689,301 patients included, 8,817 (1.3%, 95% CI 1.2-1.3) had a diagnosis of PTSD. On multiple logistic regression analysis, patients with depression (OR 4.4, 95% CI 4.2-4.7, P < 0.001), alcohol abuse/dependence (OR 1.7, 95% CI 1.6-1.9, P < 0.001), and/or drug abuse/dependence (OR 2.6, 95% CI 2.5-2.8, P < 0.001) had significantly higher odds of PTSD compared with patients without those conditions. Patients residing in community areas considered the most material deprived (OR 2.1, 95% CI 1.5-2.1, P < 0.001) or the most socially deprived (OR 2.8, 95% CI 2.7-5.3, P < 0.001) had higher odds of being diagnosed with PTSD compared with patients in the least deprived areas. CONCLUSIONS: The prevalence of PTSD in Canadian primary care is 1.3% (95% CI 1.25-1.31). Using EMR records we confirmed the co-occurrence of PTSD with other mental health conditions within primary care settings suggesting benefit for improved screening and evidence-based resources to manage PTSD.

Posttraumatic stress disorder (PTSD) is a mental health disorder with symptoms presenting after having experienced or witnessed a traumatic event. PTSD symptoms continue for more than 1 month after the event and negatively impact the health and social wellbeing of an individual. Primary care, including family doctors, nurse practitioners, and community paediatricians, are often the first point of healthcare for an individual. This study found that PTSD is diagnosed and managed in primary care. Patients with PTSD had comorbidities, substance use, and visited their primary care provider more frequently. Additionally, patients with PTSD often live in a community area that is experiencing high material and social deprivation. The presence of PTSD in primary care suggests the need for new and additional evidence-based resources to assist in managing this complex condition.

Natural Language Processing of Computed Tomography Reports to Label Metastatic Phenotypes With Prognostic Significance in Patients With Colorectal Cancer.

PURPOSE: Natural language processing (NLP) applied to radiology reports can help identify clinically relevant M1 subcategories of patients with colorectal cancer (CRC). The primary purpose was to compare the overall survival (OS) of CRC according to American Joint Committee on Cancer TNM staging and explore an alternative classification. The secondary objective was to estimate the frequency of metastasis for each organ. METHODS: Retrospective study of CRC who underwent computed tomography (CT) chest, abdomen, and pelvis between July 1, 2009, and March 26, 2019, at a tertiary cancer center, previously labeled for the presence or absence of metastasis by an NLP prediction model. Patients were classified in M0, M1a, M1b, and M1c (American Joint Committee on Cancer), or an alternative classification on the basis of the metastasis organ number: M1, single; M2, two; M3, three or more organs. Cox regression models were used to estimate hazard ratios; Kaplan-Meier curves were used to visualize survival curves using the two M1 subclassifications. RESULTS: Nine thousand nine hundred twenty-eight patients with a total of 48,408 CT chest, abdomen, and pelvis reports were included. On the basis of NLP prediction, the median OS of M1a, M1b, and M1c was 4.47, 1.72, and 1.52 years, respectively. The median OS of M1, M2, and M3 was 4.24, 2.05, and 1.04 years, respectively. Metastases occurred most often in liver (35.8%), abdominopelvic lymph nodes (32.9%), lungs (29.3%), peritoneum (22.0%), thoracic nodes (19.9%), bones (9.2%), and pelvic organs (7.5%). Spleen and adrenal metastases occurred in < 5%. CONCLUSION: NLP applied to a large radiology report database can identify clinically relevant metastatic phenotypes and be used to investigate new M1 substaging for CRC. Patients with three or more metastatic disease organs have the worst prognosis, with an OS of 1 year.

Characterizing posttraumatic stress disorder in primary care using electronic medical records: a retrospective cohort study.

Context: Posttraumatic stress disorder (PTSD) is a chronic mental health disorder associated with significant morbidity and economic cost. Primary care providers are frequently involved in the ongoing management of patients experiencing PTSD, as well as related comorbid conditions. Despite recognized need to enhance PTSD management in primary care settings, knowledge regarding its prevalence in these settings is limited. Objective: To apply a validated case definition of PTSD to electronic medical records (EMRs) of family physicians and nurse practitioners participating in the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Study Design: Retrospective cross-sectional study. Dataset: This study accessed de-identified EMR from 1,574 primary care providers participating in the CPCSSN. Population Studied: The study population included all patients with at least one visit to a primary care provider participating in the CPCSSN between January 1, 2017 and December 31, 2019 (N = 689,301). Outcome Measures: We identified patients with PTSD and described associations between PTSD and patient characteristics (including sex, age, geography, depression, anxiety, medical comorbidities, substance use and social and material deprivation) using multivariable logistic regression models. Results: Among the 689,301 patients meeting inclusion criteria, 8,213 (1.2%) had a diagnosis of PTSD. Patients with PTSD were significantly more likely to reside in an urban location (84.9% vs. 80.4%; p-value <.0001) and have one or more comorbid conditions (90.8% vs. 70.2%; p-value <.0001). On multivariable logistic regression analysis, patients with depression (OR 4.8; 95%CI 4.6-5.1) and anxiety (OR 2.2; 95%CI 2.1-2.3) had increased odds of having PTSD compared to patients without depression or anxiety. Patients with alcohol (OR 1.8; 95%CI 1.6-1.9) and drug (OR 3.1; 95%CI 2.9-3.3) use disorders had significantly higher odds of PTSD compared to patients without these disorders. Patients in the most deprived neighborhoods based on census data had 4.2 times higher odds of have PTSD (95%CI 3.2-5.43) compared to patients in the least deprived areas. Conclusions: This is the first study to describe PTSD prevalence in a large Canadian sample of primary care patients using an EMR-based case definition. Characterizing patients with PTSD in primary care may improve disease surveillance and inform the interdisciplinary care required to manage PTSD symptoms.

Developing a Cancer Digital Twin: Supervised Metastases Detection From Consecutive Structured Radiology Reports.

The development of digital cancer twins relies on the capture of high-resolution representations of individual cancer patients throughout the course of their treatment. Our research aims to improve the detection of metastatic disease over time from structured radiology reports by exposing prediction models to historical information. We demonstrate that Natural language processing (NLP) can generate better weak labels for semi-supervised classification of computed tomography (CT) reports when it is exposed to consecutive reports through a patient's treatment history. Around 714,454 structured radiology reports from Memorial Sloan Kettering Cancer Center adhering to a standardized departmental structured template were used for model development with a subset of the reports included for validation. To develop the models, a subset of the reports was curated for ground-truth: 7,732 total reports in the lung metastases dataset from 867 individual patients; 2,777 reports in the liver metastases dataset from 315 patients; and 4,107 reports in the adrenal metastases dataset from 404 patients. We use NLP to extract and encode important features from the structured text reports, which are then used to develop, train, and validate models. Three models-a simple convolutional neural network (CNN), a CNN augmented with an attention layer, and a recurrent neural network (RNN)-were developed to classify the type of metastatic disease and validated against the ground truth labels. The models use features from consecutive structured text radiology reports of a patient to predict the presence of metastatic disease in the reports. A single-report model, previously developed to analyze one report instead of multiple past reports, is included and the results from all four models are compared based on accuracy, precision, recall, and F1-score. The best model is used to label all 714,454 reports to generate metastases maps. Our results suggest that NLP models can extract cancer progression patterns from multiple consecutive reports and predict the presence of metastatic disease in multiple organs with higher performance when compared with a single-report-based prediction. It demonstrates a promising automated approach to label large numbers of radiology reports without involving human experts in a time- and cost-effective manner and enables tracking of cancer progression over time.

Natural Language Processing of Large-Scale Structured Radiology Reports to Identify Oncologic Patients With or Without Splenomegaly Over a 10-Year Period.

PURPOSE: To assess the accuracy of a natural language processing (NLP) model in extracting splenomegaly described in patients with cancer in structured computed tomography radiology reports. METHODS: In this retrospective study between July 2009 and April 2019, 3,87,359 consecutive structured radiology reports for computed tomography scans of the chest, abdomen, and pelvis from 91,665 patients spanning 30 types of cancer were included. A randomized sample of 2,022 reports from patients with colorectal cancer, hepatobiliary cancer (HB), leukemia, Hodgkin lymphoma (HL), and non-HL patients was manually annotated as positive or negative for splenomegaly. NLP model training/testing was performed on 1,617/405 reports, and a new validation set of 400 reports from all cancer subtypes was used to test NLP model accuracy, precision, and recall. Overall survival was compared between the patient groups (with and without splenomegaly) using Kaplan-Meier curves. RESULTS: The final cohort included 3,87,359 reports from 91,665 patients (mean age 60.8 years; 51.2% women). In the testing set, the model achieved accuracy of 92.1%, precision of 92.2%, and recall of 92.1% for splenomegaly. In the validation set, accuracy, precision, and recall were 93.8%, 92.9%, and 86.7%, respectively. In the entire cohort, splenomegaly was most frequent in patients with leukemia (32.5%), HB (17.4%), non-HL (9.1%), colorectal cancer (8.5%), and HL (5.6%). A splenomegaly label was associated with an increased risk of mortality in the entire cohort (hazard ratio 2.10; 95% CI, 1.98 to 2.22; P < .001). CONCLUSION: Automated splenomegaly labeling by NLP of radiology report demonstrates good accuracy, precision, and recall. Splenomegaly is most frequently reported in patients with leukemia, followed by patients with HB.

AI in predicting COPD in the Canadian population.

Chronic obstructive pulmonary disease (COPD) is a progressive lung disease that produces non-reversible airflow limitations. Approximately 10% of Canadians aged 35 years or older are living with COPD. Primary care is often the first contact an individual will have with the healthcare system providing acute care, chronic disease management, and services aimed at health maintenance. This study used Electronic Medical Record (EMR) data from primary care clinics in seven provinces across Canada to develop predictive models to identify COPD in the Canadian population. The comprehensive nature of this primary care EMR data containing structured numeric, categorical, hybrid, and unstructured text data, enables the predictive models to capture symptoms of COPD and discriminate it from diseases with similar symptoms. We applied two supervised machine learning models, a Multilayer Neural Networks (MLNN) model and an Extreme Gradient Boosting (XGB) to identify COPD patients. The XGB model achieved an accuracy of 86% in the test dataset compared to 83% achieved by the MLNN. Utilizing feature importance, we identified a set of key symptoms from the EMR for diagnosing COPD, which included medications, health conditions, risk factors, and patient age. Application of this XGB model to primary care structured EMR data can identify patients with COPD from others having similar chronic conditions for disease surveillance, and improve evidence-based care delivery.

Diagnosing post-traumatic stress disorder using electronic medical record data.

This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model's ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations.

Patterns of Metastatic Disease in Patients with Cancer Derived from Natural Language Processing of Structured CT Radiology Reports over a 10-year Period.

Background Patterns of metastasis in cancer are increasingly relevant to prognostication and treatment planning but have historically been documented by means of autopsy series. Purpose To show the feasibility of using natural language processing (NLP) to gather accurate data from radiology reports for assessing spatial and temporal patterns of metastatic spread in a large patient cohort. Materials and Methods In this retrospective longitudinal study, consecutive patients who underwent CT from July 2009 to April 2019 and whose CT reports followed a departmental structured template were included. Three radiologists manually curated a sample of 2219 reports for the presence or absence of metastases across 13 organs; these manually curated reports were used to develop three NLP models with an 80%-20% split for training and test sets. A separate random sample of 448 manually curated reports was used for validation. Model performance was measured by accuracy, precision, and recall for each organ. The best-performing NLP model was used to generate a final database of metastatic disease across all patients. For each cancer type, statistical descriptive reports were provided by analyzing the frequencies of metastatic disease at the report and patient levels. Results In 91 665 patients (mean age ± standard deviation, 61 years ± 15; 46 939 women), 387 359 reports were labeled. The best-performing NLP model achieved accuracies from 90% to 99% across all organs. Metastases were most frequently reported in abdominopelvic (23.6% of all reports) and thoracic (17.6%) nodes, followed by lungs (14.7%), liver (13.7%), and bones (9.9%). Metastatic disease tropism is distinct among common cancers, with the most common first site being bones in prostate and breast cancers and liver among pancreatic and colorectal cancers. Conclusion Natural language processing may be applied to cancer patients' CT reports to generate a large database of metastatic phenotypes. Such a database could be combined with genomic studies and used to explore prognostic imaging phenotypes with relevance to treatment planning. © RSNA, 2021 Online supplemental material is available for this article.

Impact of Fucosylation on Self-Assembly of Prostate and Breast Tumor Spheroids by Using Cyclo-RGDfK(TPP) Peptide and Image Object Detection.

INTRODUCTION: Core fucosylation of N-glycans on the integrin ß1 subunit is essential for the functional activity of the integrin. The binding of α5ß1 integrin with the tripeptide Arg-Gly-Asp (RGD) motif within the extracellular matrix protein fibronectin may be influenced by the α-1,6-fucose core or α-1,2-fucose and α-1,3/4-fucose peripheral N-glycan profiles. Here, we investigated whether fucosylation impacts the formation of matrix-free 3D multicellular tumor spheroids (MCTS) from human triple negative breast MDA-MB231 cell line, prostate PC3 and DU145 cell lines and DU145 gemcitabine resistant (GemR) variant by using the cyclic Arg-Gly-Asp-D-Phe-Lys peptide modified with 4-carboxybutyl-triphenylphosphonium bromide (cyclo-RGDfK(TPP)) peptide method. METHODS: Microscopic imaging, lectin histochemistry, flow cytometry, WST-1 cell viability assay and You Only Look Once version 2 (YOLOv2) training object detection using cyclic learning rates were used to evaluate the formation of MCTS, morphologic changes, and the expression levels of α-1,6-fucose and α-1,2-fucose linkages on the cell surface. RESULTS: DU145 prostate cancer cells expressed higher α-1,6-fucose than α-1,2-fucose linkages on their cell surface, as determined by lectin cytochemistry and flow cytometry. Blockage of the α-1,6- and α-1,2-fucose linkages with Aspergillus oryzae lectin (AOL) and Ulex Europaeus agglutinin I (UEA I) one hour before the addition of cyclic-RGDfK(TPP) peptide to the monolayer of the cancer cells resulted in a statistically significant dose-dependent reduction in spheroid volumes using threshold diameters of 40 and 60 µm. Application of a 40 µm threshold diameter measurements of spheroids resulted in fewer false-positive ones compared to the 60 µm diameter threshold previously used in our studies. A state-of-the-art, image object detection system YOLOv2 was used to automate the analysis of spheroid measurements and volumes. The results showed that YOLOv2 corroborated manual spheroid detection and volume measurements with high precision and accuracy. CONCLUSION: For the first time, the findings demonstrate that α-1,6- and α-1,2-fucose linkages of N-glycans on the cell surface receptors facilitate cyclo-RGDfK(TPP)-mediated self-assembly of cancer cells to form 3D multicellular tumor spheroids.