Identifying Symptoms Prior to Pancreatic Ductal Adenocarcinoma Diagnosis in Real-World Care Settings: Natural Language Processing Approach.

BACKGROUND: Pancreatic cancer is the third leading cause of cancer deaths in the United States. Pancreatic ductal adenocarcinoma (PDAC) is the most common form of pancreatic cancer, accounting for up to 90% of all cases. Patient-reported symptoms are often the triggers of cancer diagnosis and therefore, understanding the PDAC-associated symptoms and the timing of symptom onset could facilitate early detection of PDAC. OBJECTIVE: This paper aims to develop a natural language processing (NLP) algorithm to capture symptoms associated with PDAC from clinical notes within a large integrated health care system. METHODS: We used unstructured data within 2 years prior to PDAC diagnosis between 2010 and 2019 and among matched patients without PDAC to identify 17 PDAC-related symptoms. Related terms and phrases were first compiled from publicly available resources and then recursively reviewed and enriched with input from clinicians and chart review. A computerized NLP algorithm was iteratively developed and fine-trained via multiple rounds of chart review followed by adjudication. Finally, the developed algorithm was applied to the validation data set to assess performance and to the study implementation notes. RESULTS: A total of 408,147 and 709,789 notes were retrieved from 2611 patients with PDAC and 10,085 matched patients without PDAC, respectively. In descending order, the symptom distribution of the study implementation notes ranged from 4.98% for abdominal or epigastric pain to 0.05% for upper extremity deep vein thrombosis in the PDAC group, and from 1.75% for back pain to 0.01% for pale stool in the non-PDAC group. Validation of the NLP algorithm against adjudicated chart review results of 1000 notes showed that precision ranged from 98.9% (jaundice) to 84% (upper extremity deep vein thrombosis), recall ranged from 98.1% (weight loss) to 82.8% (epigastric bloating), and F1-scores ranged from 0.97 (jaundice) to 0.86 (depression). CONCLUSIONS: The developed and validated NLP algorithm could be used for the early detection of PDAC.

Stomach Cancer Prediction Model (SCoPM): An approach to risk stratification in a diverse U.S. population.

BACKGROUND AND AIMS: Population-based screening for gastric cancer (GC) in low prevalence nations is not recommended. The objective of this study was to develop a risk-prediction model to identify high-risk patients who could potentially benefit from targeted screening in a racial/ethnically diverse regional US population. METHODS: We performed a retrospective cohort study from Kaiser Permanente Southern California from January 2008-June 2018 among individuals age ≥50 years. Patients with prior GC or follow-up <30 days were excluded. Censoring occurred at GC, death, age 85 years, disenrollment, end of 5-year follow-up, or study conclusion. Cross-validated LASSO regression models were developed to identify the strongest of 20 candidate predictors (clinical, demographic, and laboratory parameters). Records from 12 of the medical service areas were used for training/initial validation while records from a separate medical service area were used for testing. RESULTS: 1,844,643 individuals formed the study cohort (1,555,392 training and validation, 289,251 testing). Mean age was 61.9 years with 53.3% female. GC incidence was 2.1 (95% CI 2.0-2.2) cases per 10,000 person-years (pyr). Higher incidence was seen with family history: 4.8/10,000 pyr, history of gastric ulcer: 5.3/10,000 pyr, H. pylori: 3.6/10,000 pyr and anemia: 5.3/10,000 pyr. The final model included age, gender, race/ethnicity, smoking, proton-pump inhibitor, family history of gastric cancer, history of gastric ulcer, H. pylori infection, and baseline hemoglobin. The means and standard deviations (SD) of c-index in validation and testing datasets were 0.75 (SD 0.03) and 0.76 (SD 0.02), respectively. CONCLUSIONS: This prediction model may serve as an aid for pre-endoscopic assessment of GC risk for identification of a high-risk population that could benefit from targeted screening.

Risk Factors for Acute Asthma Exacerbations in Adults With Mild Asthma.

BACKGROUND: Although individuals with mild asthma account for 30% to 40% of acute asthma exacerbations (AAEs), relatively little attention has been paid to risk factors for AAEs in this population. OBJECTIVE: To identify risk factors associated with AAEs in patients with mild asthma. METHODS: This was a retrospective cohort study. We used administrative data from a large managed care organization to identify 199,010 adults aged 18 to 85 years who met study criteria for mild asthma between 2013 and 2018. An asthma-coded qualifying visit (index visit) was identified for each patient. We then used information at the index visit or from the year before the index visit to measure potential risk factors for AAEs in the subsequent year. An AAE was defined as either an asthma-coded hospitalization or emergency department visit, or an asthma-related systemic corticosteroid administration (intramuscular or intravenous) or oral corticosteroid dispensing. Poisson regression models with robust SEs were used to estimate the adjusted risk ratios for future AAEs. RESULTS: In the study cohort, mean age was 44 years and 64% were female; 6.5% had AAEs within 1 year after the index visit. In multivariate models, age, sex, race, ethnicity, smoking status, body mass index, prior acute asthma care, and a variety of comorbidities and other clinical characteristics were significant predictors for future AAE risk. CONCLUSION: Population-based disease management strategies for asthma should be expanded to include people with mild asthma in addition to those with moderate to severe disease.

Early features of pancreatic cancer on magnetic resonance imaging (MRI): a case-control study.

PURPOSE: Magnetic resonance imaging has been recommended as a primary imaging modality among high-risk individuals undergoing screening for pancreatic cancer. We aimed to delineate potential precursor lesions for pancreatic cancer on MR imaging. METHODS: We conducted a case-control study at Kaiser Permanente Southern California (2008-2018) among patients that developed pancreatic cancer who had pre-diagnostic MRI examinations obtained 2-36 months prior to cancer diagnosis (cases) matched 1:2 by age, gender, race/ethnicity, contrast status and year of scan (controls). Patients with history of acute/chronic pancreatitis or prior pancreatic surgery were excluded. Images underwent blind review with assessment of a priori defined series of parenchymal and ductal features. We performed logistic regression to assess the associations between individual factors and pancreatic cancer. We further assessed the interaction among features as well as performed a sensitivity analysis stratifying based on specific time-windows (2-3 months, 4-12 months, 13-36 months prior to cancer diagnosis). RESULTS: We identified 141 cases (37.9% stage I-II, 2.1% III, 31.4% IV, 28.6% unknown) and 292 matched controls. A solid mass was noted in 24 (17%) of the pre-diagnostic MRI scans. Compared to controls, pre-diagnostic images from cancer cases more frequently exhibited the following ductal findings: main duct dilatation (51.4% vs 14.3%, OR [95% CI]: 7.75 [4.19-15.44], focal pancreatic duct stricture with distal (upstream) dilatation (43.6% vs 5.6%, OR 12.71 [6.02-30.89], irregularity (42.1% vs 6.0%, OR 9.73 [4.91-21.43]), focal pancreatic side branch dilation (13.6% vs1.6%, OR 11.57 [3.38-61.32]) as well as parenchymal features: atrophy (57.9% vs 27.4%, OR 46.4 [2.71-8.28], focal area of signal abnormality (39.3% vs 4.8%, OR 15.69 [6.72-44,78]), all p < 0.001). CONCLUSION: In addition to potential missed lesions, we have identified a series of ductal and parenchymal features on MRI that are associated with increased odds of developing pancreatic cancer.

Mortality Outcomes in a Large Population with and without Covert Cerebrovascular Disease.

Covert cerebrovascular disease (CCD) is frequently reported on neuroimaging and associates with increased dementia and stroke risk. We aimed to determine how incidentally-discovered CCD during clinical neuroimaging in a large population associates with mortality. We screened CT and MRI reports of adults aged ≥50 in the Kaiser Permanente Southern California health system who underwent neuroimaging for a non-stroke clinical indication from 2009-2019. Natural language processing identified incidental covert brain infarcts (CBI) and/or white matter hyperintensities (WMH), grading WMH as mild/moderate/severe. Models adjusted for age, sex, ethnicity, multimorbidity, vascular risks, depression, exercise, and imaging modality. Of n=241,028, the mean age was 64.9 (SD=10.4); mean follow-up 4.46 years; 178,554 (74.1%) had CT; 62,474 (25.9%) had MRI; 11,328 (4.7%) had CBI; and 69,927 (29.0%) had WMH. The mortality rate per 1,000 person-years with CBI was 59.0 (95%CI 57.0-61.1); with WMH=46.5 (45.7-47.2); with neither=17.4 (17.1-17.7). In adjusted models, mortality risk associated with CBI was modified by age, e.g. HR 1.34 [1.21-1.48] at age 56.1 years vs HR 1.22 [1.17-1.28] at age 72 years. Mortality associated with WMH was modified by both age and imaging modality e.g., WMH on MRI at age 56.1 HR = 1.26 [1.18-1.35]; WMH on MRI at age 72 HR 1.15 [1.09-1.21]; WMH on CT at age 56.1 HR 1.41 [1.33-1.50]; WMH on CT at age 72 HR 1.28 [1.24-1.32], vs. patients without CBI or without WMH, respectively. Increasing WMH severity associated with higher mortality, e.g. mild WMH on MRI had adjusted HR=1.13 [1.06-1.20] while severe WMH on CT had HR=1.45 [1.33-1.59]. Incidentally-detected CBI and WMH on population-based clinical neuroimaging can predict higher mortality rates. We need treatments and healthcare planning for individuals with CCD.

Association of endoscopic biopsy sampling methods with detection of precursor lesions of gastric cancer.

BACKGROUND AND AIMS: The yield of various endoscopic biopsy sampling methods for detection of precursor lesions of noncardia gastric cancer in a real-world setting remains unclear. Our objective was to evaluate the association of endoscopic biopsy sampling methods with detection of gastric intestinal metaplasia (GIM) and gastric dysplasia (GD). METHODS: We conducted a case-control study of adult patients who underwent EGD with biopsy sampling between 2010 and 2021 in a racially and ethnically diverse U.S. healthcare system. Cases were patients with histopathologic findings of GIM and/or GD. Control subjects were matched 1:1 by age, procedure date, and medical center. We compared the detection of GIM and GD using 4 different biopsy sampling methods: unspecified, specified stomach location, 2+2, and the Sydney protocol. Additionally, we assessed trends in use of sampling methods (Cochrane-Armitage) and identified patient and endoscopist factors associated with their use (logistic regression). RESULTS: We identified 20,938 GIM and 455 GD matched pairs. A greater proportion of GIM cases were detected using 2+2 (31.3% vs 25.3%, P < .0001) and the Sydney protocol (9.1% vs 1.0%, P < .0001) compared with control subjects. Similarly, a greater proportion of GD cases were detected using the Sydney protocol (15.6% vs .4%, P < .0001). We observed an increasing trend in the use of the Sydney protocol during the study period (3.8%-16.1% in cases, P < .0001; 1%-1.1% in control subjects, P = .005). Male and Asian American patients were more likely to undergo 2+2 or the Sydney protocol, whereas female and Hispanic endoscopists were more likely to perform sampling using these protocols. CONCLUSIONS: The application of the Sydney protocol is associated with an increased detection of precursor lesions of gastric cancer in routine clinical practice.

Dexamethasone Suppression Testing in a Contemporary Cohort with Adrenal Incidentalomas in Two U.S. Integrated Healthcare Systems.

Autonomous cortisol secretion (ACS) from an adrenal adenoma can increase the risk for comorbidities and mortality. The dexamethasone suppression test (DST) is the standard method to diagnose ACS. A multi-site, retrospective cohort of adults with diagnosed adrenal tumors was used to understand patient characteristics associated with DST completion and ACS. Time to DST completion was defined using the lab value and result date; follow-up time was from the adrenal adenoma diagnosis to the time of completion or censoring. ACS was defined by a DST > 1.8 µg/dL (50 nmol/L). The Cox proportional hazards regression model assessed associations between DST completion and patient characteristics. In patients completing a DST, a logistic regression model evaluated relationships between elevated ACS and covariates. We included 24,259 adults, with a mean age of 63.1 years, 48.1% obese, and 28.7% with a Charlson comorbidity index ≥ 4. Approximately 7% (n = 1768) completed a DST with a completion rate of 2.36 (95% CI 2.35, 2.37) per 100 person-years. Fully adjusted models reported that male sex and an increased Charlson comorbidity index were associated with a lower likelihood of DST completion. Current or former smoking status and an increased Charlson comorbidity index had higher odds of a DST > 1.8 µg/dL. In conclusion, clinical policies are needed to improve DST completion and the management of adrenal adenomas.

Stratifying future stroke risk with incidentally-discovered white matter disease severity and covert brain infarct site.

BACKGROUND: Covert cerebrovascular disease (CCD) includes white matter disease (WMD) and covert brain infarction (CBI). Incidentally-discovered CCD is associated with increased risk of subsequent symptomatic stroke. However, it is unknown whether the severity of WMD or the location of CBI predicts risk. OBJECTIVES: To examine the association of incidentally-discovered WMD severity and CBI location with risk of subsequent symptomatic stroke. METHOD: This retrospective cohort study includes patients 50 years old in the Kaiser Permanente Southern California health system who received neuroimaging for a non-stroke indication between 2009-2019. Incidental CBI and WMD were identified via natural language processing of the neuroimage report, and WMD severity was classified into grades. RESULTS: 261,960 patients received neuroimaging; 78,555 (30.0%) were identified to have incidental WMD, and 12,857 (4.9%) to have incidental CBI. Increasing WMD severity is associated with increased incidence rate of future stroke. However, the stroke incidence rate in CT-identified WMD is higher at each level of severity compared to rates in MRI-identified WMD. Patients with mild WMD via CT have a stroke incidence rate of 24.9 per 1,000 person-years, similar to that of patients with severe WMD via MRI. Among incidentally-discovered CBI patients with a determined CBI location, 97.9% are subcortical rather than cortical infarcts. CBI confers a similar risk of future stroke, whether cortical or subcortical, or whether MRI- or CT-detected. CONCLUSIONS: Increasing severity of incidental WMD is associated with an increased risk of future symptomatic stroke, dependent on the imaging modality. Subcortical and cortical CBI conferred similar risks.

Research data warehouse: using electronic health records to conduct population-based observational studies.

Background: Electronic health records and many legacy systems contain rich longitudinal data that can be used for research; however, they typically are not readily available. Materials and methods: At Kaiser Permanente Southern California (KPSC), a research data warehouse (RDW) has been developed and maintained since the late 1990s and widely extended in 2006, aggregating and standardizing data collected from internal and a few external sources. This article provides a high-level overview of the RDW and discusses challenges common to data warehouses or repositories for research use. To demonstrate the application of the data, we report the volume, patient characteristics, and age-adjusted prevalence of selected medical conditions and utilization rates of selected medical procedures. Results: A total of 105 million person-years of health plan enrollment was recorded in the RDW between 1981 and 2018, with most healthcare utilization data available since early or middle 1990s. Among active enrollees on December 31, 2018, 15% were ≥65 years of age, 33.9% were non-Hispanic white, 43.3% Hispanic, 11.0% Asian, and 8.4% African American, and 34.4% of children (2-17 years old) and 72.1% of adults (≥18 years old) were overweight or obese. The age-adjusted prevalence of asthma, atrial fibrillation, diabetes mellitus, hypercholesteremia, and hypertension increased between 2001 and 2018. Hospitalization and Emergency Department (ED) visit rates appeared lower, and office visit rates seemed higher at KPSC compared to the reported US averages. Discussion and conclusion: Although the RDW is unique to KPSC, its methodologies and experience may provide useful insights for researchers of other healthcare systems worldwide in the era of big data analysis.

Machine learning versus regression for prediction of sporadic pancreatic cancer.

BACKGROUND/OBJECTIVES: There is currently no widely accepted approach to identify patients at increased risk for sporadic pancreatic cancer (PC). We aimed to compare the performance of two machine-learning models with a regression-based model in predicting pancreatic ductal adenocarcinoma (PDAC), the most common form of PC. METHODS: This retrospective cohort study consisted of patients 50-84 years of age enrolled in either Kaiser Permanente Southern California (KPSC, model training, internal validation) or the Veterans Affairs (VA, external testing) between 2008 and 2017. The performance of random survival forests (RSF) and eXtreme gradient boosting (XGB) models were compared to that of COX proportional hazards regression (COX). Heterogeneity of the three models were assessed. RESULTS: The KPSC and the VA cohorts consisted of 1.8 and 2.7 million patients with 1792 and 4582 incident PDAC cases within 18 months, respectively. Predictors selected into all three models included age, abdominal pain, weight change, and glycated hemoglobin (A1c). Additionally, RSF selected change in alanine transaminase (ALT), whereas the XGB and COX selected the rate of change in ALT. The COX model appeared to have lower AUC (KPSC: 0.737, 95% CI 0.710-0.764; VA: 0.706, 0.699-0.714), compared to those of RSF (KPSC: 0.767, 0.744-0.791; VA: 0.731, 0.724-0.739) and XGB (KPSC: 0.779, 0.755-0.802; VA: 0.742, 0.735-0.750). Among patients with top 5% predicted risk from all three models (N = 29,663), 117 developed PDAC, of which RSF, XGB and COX captured 84 (9 unique), 87 (4 unique), 87 (19 unique) cases, respectively. CONCLUSIONS: The three models complement each other, but each has unique contributions.

Prediction of persistent chronic cough in patients with chronic cough using machine learning.

Introduction: The aim of this study was to develop and validate prediction models for risk of persistent chronic cough (PCC) in patients with chronic cough (CC). This was a retrospective cohort study. Methods: Two retrospective cohorts of patients 18-85 years of age were identified for years 2011-2016: a specialist cohort which included CC patients diagnosed by specialists, and an event cohort which comprised CC patients identified by at least three cough events. A cough event could be a cough diagnosis, dispensing of cough medication or any indication of cough in clinical notes. Model training and validation were conducted using two machine-learning approaches and 400+ features. Sensitivity analyses were also conducted. PCC was defined as a CC diagnosis or any two (specialist cohort) or three (event cohort) cough events in year 2 and again in year 3 after the index date. Results: 8581 and 52 010 patients met the eligibility criteria for the specialist and event cohorts (mean age 60.0 and 55.5 years), respectively. 38.2% and 12.4% of patients in the specialist and event cohorts, respectively, developed PCC. The utilisation-based models were mainly based on baseline healthcare utilisations associated with CC or respiratory diseases, while the diagnosis-based models incorporated traditional parameters including age, asthma, pulmonary fibrosis, obstructive pulmonary disease, gastro-oesophageal reflux, hypertension and bronchiectasis. All final models were parsimonious (five to seven predictors) and moderately accurate (area under the curve: 0.74-0.76 for utilisation-based models and 0.71 for diagnosis-based models). Conclusions: The application of our risk prediction models may be used to identify high-risk PCC patients at any stage of the clinical testing/evaluation to facilitate decision making.

An Analysis of the Clinical Medication Rules of Traditional Chinese Medicine for Polycystic Ovary Syndrome Based on Data Mining.

Objective: The aim of the present study is to investigate the rules and characteristics of the clinical administration of traditional Chinese medicine (TCM) in the treatment of polycystic ovary syndrome (PCOS) using data mining methods. Method: Medical cases of well-known contemporary TCM doctors treating PCOS were collected from the China National Knowledge Infrastructure, Chinese Biomedical Literature Service System, Wanfang, Chinese Scientific Journals Database, and PubMed; the data were then characterized, and a standardized database of medical cases was built. This database was used to (1) count the frequency of syndrome types and the herbs used in medical cases by data mining methods and (2) analyze drug association rules and systematic clustering methods. Results: A total of 330 papers were included, involving 382 patients and a total of 1,427 consultations. The most common syndrome type was kidney deficiency; sputum stasis was the core pathological product and causative factor. A total of 364 herbs were used. Among them, 22 herbs were used >300 times, including Danggui (Angelicae Sinensis Radix), Tusizi (Semen Cuscutae), Fuling (Poria), Xiangfu (Nutgrass Galingale Rhizome), and Baizhu (Atractylodis Macrocephalae Rhizoma). Additionally, 22 binomial associations were obtained from the analysis of association rules; five clustering formulae were obtained via the analysis of high-frequency drug clusters; and 27 core combinations were obtained by k-means clustering of formula. Conclusion: In the treatment of PCOS, TCM is primarily employed as a combination approach involving tonifying the kidneys, strengthening the spleen, eliminating damp and dissolving phlegm, activating blood circulation, and resolving blood stasis. The core prescription is primarily a compound intervention based on the Cangfu Daotan pill, Liuwei Dihuang pill, and Taohong Siwu decoction.

Stratifying Future Stroke Risk with Incidentally Discovered White Matter Disease Severity and Covert Brain Infarct Site.

BACKGROUND: Covert cerebrovascular disease (CCD) includes white matter disease (WMD) and covert brain infarction (CBI). Incidentally discovered CCD is associated with increased risk of subsequent symptomatic stroke. However, it is unknown whether the severity of WMD or the location of CBI predicts risk. OBJECTIVES: The aim of this study was to examine the association of incidentally discovered WMD severity and CBI location with risk of subsequent symptomatic stroke. METHOD: This retrospective cohort study includes patients aged ≥50 years old in the Kaiser Permanente Southern California health system who received neuroimaging for a nonstroke indication between 2009 and 2019. Incidental CBI and WMD were identified via natural language processing of the neuroimage report, and WMD severity was classified into grades. RESULTS: A total of 261,960 patients received neuroimaging; 78,555 patients (30.0%) were identified to have incidental WMD and 12,857 patients (4.9%) to have incidental CBI. Increasing WMD severity is associated with an increased incidence rate of future stroke. However, the stroke incidence rate in CT-identified WMD is higher at each level of severity compared to rates in MRI-identified WMD. Patients with mild WMD via CT have a stroke incidence rate of 24.9 per 1,000 person-years, similar to that of patients with severe WMD via MRI. Among incidentally discovered CBI patients with a determined CBI location, 97.9% are subcortical rather than cortical infarcts. CBI confers a similar risk of future stroke, whether cortical or subcortical or whether MRI- or CT-detected. CONCLUSIONS: Increasing severity of incidental WMD is associated with an increased risk of future symptomatic stroke, dependent on the imaging modality. Subcortical and cortical CBI conferred similar risks.

Risk Prediction of Pancreatic Cancer in Patients With Recent-onset Hyperglycemia: A Machine-learning Approach.

BACKGROUND: New-onset diabetes (NOD) has been suggested as an early indicator of pancreatic cancer. However, the definition of NOD by the American Diabetes Association requires 2 simultaneous or consecutive elevated glycemic measures. We aimed to apply a machine-learning approach using electronic health records to predict the risk in patients with recent-onset hyperglycemia. MATERIALS AND METHODS: In this retrospective cohort study, health plan enrollees 50 to 84 years of age who had an elevated (6.5%+) glycated hemoglobin (HbA1c) tested in January 2010 to September 2018 with recent-onset hyperglycemia were identified. A total of 102 potential predictors were extracted. Ten imputation datasets were generated to handle missing data. The random survival forests approach was used to develop and validate risk models. Performance was evaluated by c -index, calibration plot, sensitivity, specificity, and positive predictive value. RESULTS: The cohort consisted of 109,266 patients (mean age: 63.6 y). The 3-year incidence rate was 1.4 (95% confidence interval: 1.3-1.6)/1000 person-years of follow-up. The 3 models containing age, weight change in 1 year, HbA1c, and 1 of the 3 variables (HbA1c change in 1 y, HbA1c in the prior 6 mo, or HbA1c in the prior 18 mo) appeared most often out of the 50 training samples. The c -indexes were in the range of 0.81 to 0.82. The sensitivity, specificity, and positive predictive value in patients who had the top 20% of the predicted risks were 56% to 60%, 80%, and 2.5% to 2.6%, respectively. CONCLUSION: Targeting evaluation at the point of recent hyperglycemia based on elevated HbA1c could offer an opportunity to identify pancreatic cancer early and possibly impact survival in cancer patients.

Association of Incidentally Discovered Covert Cerebrovascular Disease Identified Using Natural Language Processing and Future Dementia.

Background Covert cerebrovascular disease (CCD) has been shown to be associated with dementia in population-based studies with magnetic resonance imaging (MRI) screening, but dementia risk associated with incidentally discovered CCD is not known. Methods and Results Individuals aged ≥50 years enrolled in the Kaiser Permanente Southern California health system receiving head computed tomography (CT) or MRI for nonstroke indications from 2009 to 2019, without prior ischemic stroke/transient ischemic attack, dementia/Alzheimer disease, or visit reason/scan indication suggestive of cognitive decline or stroke were included. Natural language processing identified incidentally discovered covert brain infarction (id-CBI) and white matter disease (id-WMD) on the neuroimage report; white matter disease was characterized as mild, moderate, severe, or undetermined. We estimated risk of dementia associated with id-CBI and id-WMD. Among 241 050 qualified individuals, natural language processing identified 69 931 (29.0%) with id-WMD and 11 328 (4.7%) with id-CBI. Dementia incidence rates (per 1000 person-years) were 23.5 (95% CI, 22.9-24.0) for patients with id-WMD, 29.4 (95% CI, 27.9-31.0) with id-CBI, and 6.0 (95% CI, 5.8-6.2) without id-CCD. The association of id-WMD with future dementia was stronger in younger (aged <70 years) versus older (aged ≥70 years) patients and for CT- versus MRI-discovered lesions. For patients with versus without id-WMD on CT, the adjusted HR was 2.87 (95% CI, 2.58-3.19) for older and 1.87 (95% CI, 1.79-1.95) for younger patients. For patients with versus without id-WMD on MRI, the adjusted HR for dementia risk was 2.28 (95% CI, 1.99-2.62) for older and 1.48 (95% CI, 1.32-1.66) for younger patients. The adjusted HR for id-CBI was 2.02 (95% CI, 1.70-2.41) for older and 1.22 (95% CI, 1.15-1.30) for younger patients for either modality. Dementia risk was strongly correlated with id-WMD severity; adjusted HRs compared with patients who were negative for id-WMD by MRI ranged from 1.41 (95% CI, 1.25-1.60) for those with mild disease on MRI to 4.11 (95% CI, 3.58-4.72) for those with severe disease on CT. Conclusions Incidentally discovered CCD is common and associated with a high risk of dementia, representing an opportunity for prevention. The association is strengthened when discovered at younger age, by increasing id-WMD severity, and when id-WMD is detected by CT scan rather than MRI.

Quantitative Radiomic Features From Computed Tomography Can Predict Pancreatic Cancer up to 36 Months Before Diagnosis.

INTRODUCTION: Pancreatic cancer is the third leading cause of cancer deaths among men and women in the United States. We aimed to detect early changes on computed tomography (CT) images associated with pancreatic ductal adenocarcinoma (PDAC) based on quantitative imaging features (QIFs) for patients with and without chronic pancreatitis (CP). METHODS: Adults 18 years and older diagnosed with PDAC in 2008-2018 were identified. Their CT scans 3 months-3 years before the diagnosis date were matched to up to 2 scans of controls. The pancreas was automatically segmented using a previously developed algorithm. One hundred eleven QIFs were extracted. The data set was randomly split for training/validation. Neighborhood and principal component analyses were applied to select the most important features. A conditional support vector machine was used to develop prediction algorithms separately for patients with and without CP. The computer labels were compared with manually reviewed CT images 2-3 years before the index date in 19 cases and 19 controls. RESULTS: Two hundred twenty-seven of 554 scans of non-CP cancer cases/controls and 70 of 140 scans of CP cancer cases/controls were included (average age 71 and 68 years, 51% and 44% females for non-CP patients and patients with CP, respectively). The QIF-based algorithms varied based on CP status. For non-CP patients, accuracy measures were 94%-95% and area under the curve (AUC) measures were 0.98-0.99. Sensitivity, specificity, positive predictive value, and negative predictive value were in the ranges of 88%-91%, 96%-98%, 91%-95%, and 94%-96%, respectively. QIFs on CT examinations within 2-3 years before the index date also had very high predictive accuracy (accuracy 95%-98%; AUC 0.99-1.00). The QIF-based algorithm outperformed manual rereview of images for determination of PDAC risk. For patients with CP, the algorithms predicted PDAC perfectly (accuracy 100% and AUC 1.00). DISCUSSION: QIFs can accurately predict PDAC for both non-CP patients and patients with CP on CT imaging and represent promising biomarkers for early detection of pancreatic cancer.

Derivation and External Validation of Machine Learning-Based Model for Detection of Pancreatic Cancer.

INTRODUCTION: There is currently no widely accepted approach to screening for pancreatic cancer (PC). We aimed to develop and validate a risk prediction model for pancreatic ductal adenocarcinoma (PDAC), the most common form of PC, across 2 health systems using electronic health records. METHODS: This retrospective cohort study consisted of patients aged 50-84 years having at least 1 clinic-based visit over a 10-year study period at Kaiser Permanente Southern California (model training, internal validation) and the Veterans Affairs (VA, external testing). Random survival forests models were built to identify the most relevant predictors from >500 variables and to predict risk of PDAC within 18 months of cohort entry. RESULTS: The Kaiser Permanente Southern California cohort consisted of 1.8 million patients (mean age 61.6) with 1,792 PDAC cases. The 18-month incidence rate of PDAC was 0.77 (95% confidence interval 0.73-0.80)/1,000 person-years. The final main model contained age, abdominal pain, weight change, HbA1c, and alanine transaminase change (c-index: mean = 0.77, SD = 0.02; calibration test: P value 0.4, SD 0.3). The final early detection model comprised the same features as those selected by the main model except for abdominal pain (c-index: 0.77 and SD 0.4; calibration test: P value 0.3 and SD 0.3). The VA testing cohort consisted of 2.7 million patients (mean age 66.1) with an 18-month incidence rate of 1.27 (1.23-1.30)/1,000 person-years. The recalibrated main and early detection models based on VA testing data sets achieved a mean c-index of 0.71 (SD 0.002) and 0.68 (SD 0.003), respectively. DISCUSSION: Using widely available parameters in electronic health records, we developed and externally validated parsimonious machine learning-based models for detection of PC. These models may be suitable for real-time clinical application.

Risk Prediction of Pancreatic Cancer in Patients With Abnormal Morphologic Findings Related to Chronic Pancreatitis: A Machine Learning Approach.

BACKGROUND AND AIMS: A significant factor contributing to poor survival in pancreatic cancer is the often late stage at diagnosis. We sought to develop and validate a risk prediction model to facilitate the distinction between chronic pancreatitis-related vs potential early pancreatic ductal adenocarcinoma (PDAC)-associated changes on pancreatic imaging. METHODS: In this retrospective cohort study, patients aged 18-84 years whose abdominal computed tomography/magnetic resonance imaging reports indicated duct dilatation, atrophy, calcification, cyst, or pseudocyst between January 2008 and November 2019 were identified. The outcome of interest is PDAC in 3 years. More than 100 potential predictors were extracted. Random survival forests approach was used to develop and validate risk models. Multivariable Cox proportional hazard model was applied to estimate the effect of the covariates on the risk of PDAC. RESULTS: The cohort consisted of 46,041 (mean age 66.4 years). The 3-year incidence rate was 4.0 (95% confidence interval CI 3.6-4.4)/1000 person-years of follow-up. The final models containing age, weight change, duct dilatation, and either alkaline phosphatase or total bilirubin had good discrimination and calibration (c-indices 0.81). Patients with pancreas duct dilatation and at least another morphological feature in the absence of calcification had the highest risk (adjusted hazard ratio [aHR] = 14.15, 95% CI 8.7-22.6), followed by patients with calcification and duct dilatation (aHR = 7.28, 95% CI 4.09-12.96), and patients with duct dilation only (aHR = 6.22, 95% CI 3.86-10.03), compared with patients with calcifications alone as the reference group. CONCLUSION: The study characterized the risk of pancreatic cancer among patients with 5 abnormal morphologic findings based on radiology reports and demonstrated the ability of prediction algorithms to provide improved risk stratification of pancreatic cancer in these patients.

Risk prediction of pancreatic cancer using AI analysis of pancreatic subregions in computed tomography images.

Early detection of Pancreatic Ductal Adenocarcinoma (PDAC) is complicated as PDAC remains asymptomatic until cancer advances to late stages when treatment is mostly ineffective. Stratifying the risk of developing PDAC can improve early detection as subsequent screening of high-risk individuals through specialized surveillance systems reduces the chance of misdiagnosis at the initial stage of cancer. Risk stratification is however challenging as PDAC lacks specific predictive biomarkers. Studies reported that the pancreas undergoes local morphological changes in response to underlying biological evolution associated with PDAC development. Accurate identification of these changes can help stratify the risk of PDAC. In this retrospective study, an extensive radiomic analysis of the precancerous pancreatic subregions was performed using abdominal Computed Tomography (CT) scans. The analysis was performed using 324 pancreatic subregions identified in 108 contrast-enhanced abdominal CT scans with equal proportion from healthy control, pre-diagnostic, and diagnostic groups. In a pairwise feature analysis, several textural features were found potentially predictive of PDAC. A machine learning classifier was then trained to perform risk prediction of PDAC by automatically classifying the CT scans into healthy control (low-risk) and pre-diagnostic (high-risk) classes and specifying the subregion(s) likely to develop a tumor. The proposed model was trained on CT scans from multiple phases. Whereas using 42 CT scans from the venous phase, model validation was performed which resulted in ~89.3% classification accuracy on average, with sensitivity and specificity reaching 86% and 93%, respectively, for predicting the development of PDAC (i.e., high-risk). To our knowledge, this is the first model that unveiled microlevel precancerous changes across pancreatic subregions and quantified the risk of developing PDAC. The model demonstrated improved prediction by 3.3% in comparison to the state-of-the-art method that considers the global (whole pancreas) features for PDAC prediction.

Development of Parkinson Disease and Its Relationship with Incidentally Discovered White Matter Disease and Covert Brain Infarction in a Real-World Cohort.

OBJECTIVE: This study aimed to examine the relationship between covert cerebrovascular disease, comprised of covert brain infarction and white matter disease, discovered incidentally in routine care, and subsequent Parkinson disease. METHODS: Patients were ≥50 years and received neuroimaging for non-stroke indications in the Kaiser Permanente Southern California system from 2009 to 2019. Natural language processing identified incidentally discovered covert brain infarction and white matter disease and classified white matter disease severity. The Parkinson disease outcome was defined as 2 ICD diagnosis codes. RESULTS: 230,062 patients were included (median follow-up 3.72 years). A total of 1,941 Parkinson disease cases were identified (median time-to-event 2.35 years). Natural language processing identified covert cerebrovascular disease in 70,592 (30.7%) patients, 10,622 (4.6%) with covert brain infarction and 65,814 (28.6%) with white matter disease. After adjustment for known risk factors, white matter disease was associated with Parkinson disease (hazard ratio 1.67 [95%CI, 1.44, 1.93] for patients <70 years and 1.33 [1.18, 1.50] for those ≥70 years). Greater severity of white matter disease was associated with increased incidence of Parkinson disease(/1,000 person-years), from 1.52 (1.43, 1.61) in patients without white matter disease to 4.90 (3.86, 6.13) in those with severe disease. Findings were robust when more specific definitions of Parkinson disease were used. Covert brain infarction was not associated with Parkinson disease (adjusted hazard ratio = 1.05 [0.88, 1.24]). INTERPRETATION: Incidentally discovered white matter disease was associated with subsequent Parkinson disease, an association strengthened with younger age and increased white matter disease severity. Incidentally discovered covert brain infarction did not appear to be associated with subsequent Parkinson disease. ANN NEUROL 2022;92:620-630.