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 30-40% 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. MEHODS (RETROSPECTIVE COHORT STUDY): We used administrative data from a large managed care organization to identify 199,010 adults aged 18-85 who met study criteria for mild asthma between 2013-2018. An asthma-coded qualifying visit (index visit) was identified for each patient. We then used information at the index visit or from the year prior to the index visit to measure potential risk factors for AAEs in the subsequent year. An AAE was defined as either (1) an asthma-coded hospitalization or ED visit, or (2) an asthma-related systemic corticosteroid administration (intramuscular or intravenous) or oral corticosteroid dispensing. Poisson regression models with robust standard errors were utilized to estimate the adjusted risk ratios (aRR) for future AAEs. RESULTS: In the study cohort, mean age was 44, and 64% were female; 6.5% had AAEs within one year after the index visit. In multivariate models, age, gender, 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 those 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.

Clinical Prediction Models Combining Routine Clinical Measures Have High Accuracy in Identifying Youth-Onset Type 2 Diabetes Defined by Maintained Endogenous Insulin Secretion: The SEARCH for Diabetes in Youth Study.

OBJECTIVE: With high prevalence of obesity and overlapping features between diabetes subtypes, accurately classifying youth-onset diabetes can be challenging. We aimed to develop prediction models that, using characteristics available at diabetes diagnosis, can identify youth who will retain endogenous insulin secretion at levels consistent with type 2 diabetes (T2D). RESEARCH DESIGN AND METHODS: We studied 2,966 youth with diabetes in the prospective SEARCH for Diabetes in Youth study (diagnosis age ≤19 years) to develop prediction models to identify participants with fasting C-peptide ≥250 pmol/L (≥0.75 ng/mL) after >3 years' (median 74 months) diabetes duration. Models included clinical measures at the baseline visit, at a mean diabetes duration of 11 months (age, BMI, sex, waist circumference, HDL cholesterol), with and without islet autoantibodies (GADA, IA-2A) and a Type 1 Diabetes Genetic Risk Score (T1DGRS). RESULTS: Models using routine clinical measures with or without autoantibodies and T1DGRS were highly accurate in identifying participants with C-peptide ≥0.75 ng/mL (17% of participants; 2.3% and 53% of those with and without positive autoantibodies) (area under the receiver operating characteristic curve [AUCROC] 0.95-0.98). In internal validation, optimism was very low, with excellent calibration (slope 0.995-0.999). Models retained high performance for predicting retained C-peptide in older youth with obesity (AUCROC 0.88-0.96) and in subgroups defined by self-reported race/ethnicity (AUCROC 0.88-0.97), autoantibody status (AUCROC 0.87-0.96), and clinically diagnosed diabetes types (AUCROC 0.81-0.92). CONCLUSIONS: Prediction models combining routine clinical measures at diabetes diagnosis, with or without islet autoantibodies or T1DGRS, can accurately identify youth with diabetes who maintain endogenous insulin secretion in the range associated with T2D.

Association of Glycated Hemoglobin With a Risk of Pancreatic Cancer in High-Risk Individuals Based on Genetic and Family History.

INTRODUCTION: Screening for pancreatic cancer (PC) is suggested for high-risk individuals. Additional risk factors may enhance early detection in this population. METHODS: Retrospective cohort study among patients with germline variants and/or familial pancreatic cancer in an integrated healthcare system between 2003 and 2019. We calculated the incidence rate (IR) by risk category and performed a nested case-control study to evaluate the relationship between HbA1C and PC within 3 years before diagnosis (cases) or match date (controls). Cases were matched 1:4 by age, sex, and timing of HbA1c. Logistic regression was performed to assess an independent association with PC. RESULTS: We identified 5,931 high-risk individuals: 1,175(19.8%) familial PC, 45(0.8%) high-risk germline variants ( STK11, CDKN2A ), 4,097(69.1%) had other germline variants ( ATM, BRCA 1, BRCA 2, CASR, CDKN2A, CFTR, EPCAM, MLH1, MSH2, MSH6, PALB2, PRSS1, STK11, and TP53 ), and 614(10.4%) had both germline variants and family history. Sixty-eight patients (1.1%) developed PC; 50% were metastatic at diagnosis. High-risk variant was associated with greatest risk of PC, IR = 85.1(95% confidence interval: 36.7-197.6)/10,000 person-years; other germline variants and first-degree relative had IR = 33 (18.4, 59.3), whereas IR among ≥2 first-degree relative alone was 10.7 (6.1, 18.8). HbA1c was significantly higher among cases vs controls (median = 7.0% vs 6.4%, P = 0.02). In multivariable analysis, every 1% increase in HbA1c was associated with 36% increase in odds of PC (odds ratio 1.36, 95% confidence interval: 1.08-1.72). Pancreatitis was independently associated with a risk of PC (odds ratio 3.93, 95% confidence limit 1.19, 12.91). DISCUSSION: Risk of PC varies among high-risk individuals. HbA1c and history of pancreatitis may be useful additional markers for early detection in this patient population.

Household Food Insecurity Is Associated With Physical Activity in Youth and Young Adults With Diabetes: A Cross-Sectional Study.

BACKGROUND: Physical activity (PA) is essential for optimal diabetes management. Household food insecurity (HFI) may negatively affect diabetes management behaviors. The purpose of this study was to cross-sectionally examine the association between HFI and PA in youth and young adults (YYA) with type 1 (N = 1998) and type 2 (N = 391) diabetes from the SEARCH for Diabetes in Youth Study. METHODS: HFI was measured with the US Household Food Security Survey Module. PA was measured with the International Physical Activity Questionnaire Short Form. Walking, moderate-intensity PA (excluding walking), vigorous-intensity PA, moderate- to vigorous-intensity PA, and total PA were estimated as minutes per week, while time spent sitting was assessed in minutes per day. All were modeled with median regression. Meeting PA guidelines or not was modeled using logistic regression. RESULTS: YYA with type 1 diabetes who experienced HFI spent more time walking than those who were food secure. YYA with type 2 diabetes who experienced HFI spent more time sitting than those who were food secure. CONCLUSIONS: Future research should examine walking for leisure versus other domains of walking in relation to HFI and use objective PA measures to corroborate associations between HFI and PA in YYA with diabetes.

Clinical prediction models combining routine clinical measures identify participants with youth-onset diabetes who maintain insulin secretion in the range associated with type 2 diabetes: The SEARCH for Diabetes in Youth Study.

Objective: With the high prevalence of pediatric obesity and overlapping features between diabetes subtypes, accurately classifying youth-onset diabetes can be challenging. We aimed to develop prediction models that, using characteristics available at diabetes diagnosis, can identify youth who will retain endogenous insulin secretion at levels consistent with type 2 diabetes (T2D). Methods: We studied 2,966 youth with diabetes in the prospective SEARCH study (diagnosis age ≤19 years) to develop prediction models to identify participants with fasting c-peptide ≥250 pmol/L (≥0.75ng/ml) after >3 years (median 74 months) of diabetes duration. Models included clinical measures at baseline visit, at a mean diabetes duration of 11 months (age, BMI, sex, waist circumference, HDL-C), with and without islet autoantibodies (GADA, IA-2A) and a Type 1 Diabetes Genetic Risk Score (T1DGRS). Results: Models using routine clinical measures with or without autoantibodies and T1DGRS were highly accurate in identifying participants with c-peptide ≥0.75 ng/ml (17% of participants; 2.3% and 53% of those with and without positive autoantibodies) (area under receiver operator curve [AUCROC] 0.95-0.98). In internal validation, optimism was very low, with excellent calibration (slope=0.995-0.999). Models retained high performance for predicting retained c-peptide in older youth with obesity (AUCROC 0.88-0.96), and in subgroups defined by self-reported race/ethnicity (AUCROC 0.88-0.97), autoantibody status (AUCROC 0.87-0.96), and clinically diagnosed diabetes types (AUCROC 0.81-0.92). Conclusion: Prediction models combining routine clinical measures at diabetes diagnosis, with or without islet autoantibodies or T1DGRS, can accurately identify youth with diabetes who maintain endogenous insulin secretion in the range associated with type 2 diabetes.

Incidence of Diabetes Among Youth Before and During the COVID-19 Pandemic.

Importance: Prior research found increases in diabetes among youth during the COVID-19 pandemic, but few studies examined variation across sociodemographics. Objective: To examine diabetes incidence rates among a diverse population of youth in the US before and during the COVID-19 pandemic. Design, Setting, and Participants: This cohort study included data from Kaiser Permanente Southern California (KPSC) between January 1, 2016, and December 31, 2021. KPSC members aged from birth to 19 years with no history of diabetes were included. Individuals were followed up using electronic health records for diabetes incidence defined using diagnoses, laboratory values, and medications. Analyses were conducted between November 2022 and January 2023. Main Outcome and Measures: Age- and sex-standardized annual and quarterly incidence rates per 100 000 person-years (PYs) were calculated for type 1 diabetes and type 2 diabetes between 2016 and 2021. Rates were calculated within strata of age (<10 and 10-19 years), sex, and race and ethnicity (Asian/Pacific Islander, Hispanic, non-Hispanic Black, non-Hispanic White, and other/multiple/unknown). Using Poisson regression with robust error variances, incidence rate ratios (IRR) comparing 2020 to 2021 with 2016 to 2019 were calculated by diabetes type and within age, sex, and race and ethnicity strata and adjusting for health care utilization. Results: Between 2016 to 2021, there were 1200, 1100, and 63 patients with type 1 diabetes (mean [SD] age, 11.0 [4.5] years; 687 [57.3%] male), type 2 diabetes (mean [SD] age, 15.7 [2.7] years; 516 [46.9%] male), and other diabetes, respectively. Incidence of type 1 diabetes increased from 18.5 per 100 000 PYs in 2016 to 2019 to 22.4 per 100 000 PYs from 2020 to 2021 with increased IRRs among individuals aged 10 to 19 years, male individuals, and Hispanic individuals. Incidence of type 2 diabetes increased from 14.8 per 100 000 PYs from 2016 to 2019 to 24.7 per 100 000 PYs from 2020 to 2021 with increased IRRs among individuals aged 10 to 19 years, male and female individuals, and those with Black, Hispanic, and other/unknown race and ethnicity. Conclusions and Relevance: In this cohort study of youth in KPSC, incidence of diabetes increased during the COVID-19 pandemic and was more pronounced in specific racial and ethnic groups. Future research to understand differential impacts of physiologic and behavioral risk factors is warranted.

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.

Exploring Racial and Ethnic Differences in Arterial Stiffness Among Youth and Young Adults With Type 1 Diabetes.

Background We examined arterial stiffness in individuals with type 1 diabetes, and explored whether differences between Hispanic, non-Hispanic Black (NHB), and non-Hispanic White (NHW) individuals were attributable to modifiable clinical and social factors. Methods and Results Participants (n=1162; 22% Hispanic, 18% NHB, and 60% NHW) completed 2 to 3 research visits from ≈10 months to ≈11 years post type 1 diabetes diagnosis (mean ages of ≈9 to ≈20 years, respectively) providing data on socioeconomic factors, type 1 diabetes characteristics, cardiovascular risk factors, health behaviors, quality of clinical care, and perception of clinical care. Arterial stiffness (carotid-femoral pulse wave velocity [PWV], m/s) was measured at ≈20 years of age. We analyzed differences in PWV by race and ethnicity, then explored the individual and combined impact of the clinical and social factors on these differences. PWV did not differ between Hispanic (adjusted mean 6.18 [SE 0.12]) and NHW (6.04 [0.11]) participants after adjustment for cardiovascular risks (P=0.06) and socioeconomic factors (P=0.12), or between Hispanic and NHB participants (6.36 [0.12]) after adjustment for all factors (P=0.08). PWV was higher in NHB versus NHW participants in all models (all P<0.001). Adjustment for modifiable factors reduced the difference in PWV by 15% for Hispanic versus NHW participants; by 25% for Hispanic versus NHB; and by 21% for NHB versus NHW. Conclusions Cardiovascular and socioeconomic factors explain one-quarter of the racial and ethnic differences in PWV of young people with type 1 diabetes, but NHB individuals still experienced greater PWV. Exploration of pervasive inequities potentially driving these persistent differences is needed.

Comparison of Blood Pressure Measurements from Clinical Practice and a Research Study At Kaiser Permanente Southern California.

BACKGROUND: Accurate blood pressure (BP) measurement is essential to identify and manage hypertension. Prior studies have reported a difference between BP measured in routine patient care and in research studies. We aimed to investigate the agreement between BP measured in routine care and research-grade BP in Kaiser Permanente Southern California, a large, integrated healthcare system with initiatives to standardize BP measurements during routine patient care visits. METHODS: We included adults ≥65 years old with hypertension, taking antihypertensive medication, and participating in the Ambulatory Blood Pressure in Older Adults (AMBROSIA) study in 2019-2021. Clinic BP from routine care visits was extracted from the electronic health record. Research-grade BP was obtained by trained AMBROSIA study staff via an automatic oscillometric device. The mean difference between routine care and research-grade BP, limits of agreement, and correlation were assessed. RESULTS: We included 309 participants (mean age 75 years; 54% female; 49% non-Hispanic white). Compared with measurements from routine care, mean research-grade systolic BP (SBP) was 0.1 mm Hg higher (95% CI: -1.5 to 1.8) and diastolic BP (DBP) was 0.4 mm Hg lower (95% CI: -1.6 to 0.7). Limits of agreement were -29 to 30 mm Hg for SBP and -21 to 20 mm Hg for DBP. The intraclass correlation coefficient was 0.42 (95% CI: 0.33 to 0.51) for SBP and 0.43 (95% CI: 0.34 to 0.52) for DBP. CONCLUSIONS: High within-person variation and moderate correlation were present between BP measured in routine care and following a research protocol suggesting the importance of standardized measurements.

Association of Elevated Arterial Stiffness With Cardiac Target Organ Damage and Cardiac Autonomic Neuropathy in Young Adults With Diabetes: The SEARCH for Diabetes in Youth Study.

OBJECTIVE: Adults with diabetes are at risk for cardiovascular (CV) events, possibly due to increased arterial stiffness (AS) and cardiac autonomic neuropathy (CAN). We sought to determine whether 1) AS is associated with cardiac target organ damage in young adults with youth-onset diabetes, 2) whether CAN is associated with AS, as one possible etiology for increased AS in this cohort, and 3) whether these relationships differ by type of diabetes. RESEARCH DESIGN AND METHODS: Participants from the SEARCH for Diabetes in Youth Study (type 1 diabetes [T1D], n = 222; type 2 diabetes [T2D], n = 177; mean age 23 years) had clinical, echocardiographic, AS, and CAN assessed. Linear regression was performed to determine whether AS was associated with cardiac changes and CAN and whether relationships differed by diabetes type. RESULTS: AS was significantly associated with cardiac structure (left ventricular mass index, P < 0.0001), systolic function (ejection fraction, P = 0.03) and diastolic function (transmitral peak early [E]/atrial [A] wave velocities ratio, P = 0.008; early [e']/atrial [a'] waves, P = 0.02) after adjustments for CV risk factors. The association between AS and CAN was not significant when other important covariates were added. These relationships were mostly similar in both T1D and T2D. CONCLUSIONS: AS is associated with cardiac changes in young adults with diabetes. CAN-induced AS does not appear to be an etiology for cardiac abnormalities in this cohort.

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.

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.

Gastric Cancer Screening in First-Degree Relatives: A Pilot Study in a Diverse Integrated Healthcare System.

INTRODUCTION: Family history of gastric cancer has been shown as an independent risk factor of gastric cancer development and is associated with increased risk of progression to gastric cancer among patients with gastric intestinal metaplasia (GIM). METHODS: Between 2017 and 2020, we conducted a prospective pilot screening program of patients with a confirmed first-degree relative with gastric cancer to evaluate the feasibility of screening and prevalence of precursor lesions (e.g., GIM or dysplasia) on biopsy. RESULTS: A total of 61 patients completed screening by upper endoscopy with a mapping biopsy protocol: 27 (44%) were found to have GIM and 4 (7%) were found with low-grade dysplasia. DISCUSSION: Our pilot screening program identified a high prevalence of precursor lesions for gastric cancer among asymptomatic patients with a first-degree relative with gastric cancer. Careful endoscopic inspection and standardized biopsy protocols may aid in prompt identification of these precursor lesions in those at risk of gastric cancer.

Longitudinal Changes in Arterial Stiffness and Heart Rate Variability in Youth-Onset Type 1 Versus Type 2 Diabetes: The SEARCH for Diabetes in Youth Study.

OBJECTIVE: We compared arterial stiffness and heart rate variability (HRV) over time by diabetes type and determined the risk factors associated with worsening arterial stiffness and HRV in young adults with youth-onset diabetes. RESEARCH DESIGN AND METHODS: Arterial stiffness (pulse wave velocity, augmentation index) and six indices of heart rate variability were measured twice, 4.5 years apart, among participants with either youth-onset type 1 or type 2 diabetes in the SEARCH for Diabetes in Youth study. Multivariable linear regression models were used to assess risk factors associated with arterial stiffness and HRV at follow-up. RESULTS: Of 1,159 participants studied, 949 had type 1 diabetes (mean age 17.1 ± 4.7 years, 60.3% non-Hispanic White, 55% female) and 210 had type 2 diabetes (mean age 22.1 ± 3.5 years, 23.8% non-Hispanic White, 71% female) at initial assessment when diabetes duration was 7.9 years (both groups). Participants with type 2 versus type 1 diabetes had greater arterial stiffness and more abnormalities in HRV at initial and follow-up assessment and a greater change over time (all P < 0.05). Risk factors associated with worse arterial stiffness and HRV at follow-up in both types of diabetes included higher blood pressure, hemoglobin A1c, waist circumference, and triglycerides over time and longer diabetes duration. CONCLUSIONS: Arterial stiffness and HRV worsened over time with greater changes among participants with type 2 versus type 1 diabetes and among those with features of the metabolic syndrome. The risk factor profile documents potentially modifiable pathways to prevent or limit cardiovascular complications in young adults with youth-onset diabetes.

Household food insecurity is associated with diabetic ketoacidosis but not severe hypoglycemia or glycemic control in youth and young adults with youth-onset type 2 diabetes.

OBJECTIVE: To examine the association between household food insecurity (HFI), glycemic control, severe hypoglycemia and diabetic ketoacidosis (DKA) among youth and young adults (YYA) with youth-onset type 2 diabetes. RESEARCH DESIGN AND METHODS: This cross-sectional study included 395 YYA with type 2 diabetes from the SEARCH for Diabetes in Youth Study (2015-2019). HFI was reported by young adult participants or parents of minor participants via the US Household Food Security Survey Module. Glycemic control was assessed by HbA1c and analyzed as a continuous and categorical variable (optimal: <7.0%, suboptimal: ≥7.0%-9.0%, poor: >9.0%). Acute complications included self-reported severe hypoglycemia or DKA in the last 12 months. Adjusted logistic and linear regression were used for binary and continuous outcomes, respectively. RESULTS: Approximately 31% reported HFI in the past 12 months. Mean HbA1c among those with HFI was 9.2% compared to 9.5% without HFI. Of those with HFI, 56% had an HbA1c >9.0% compared to 55% without HFI. Adjusted models showed no associations between HFI and glycemic control. Of those with HFI, 14.4% reported experiencing DKA and 4.7% reported severe hypoglycemia. YYA with HFI had 3.08 times (95% CI: 1.18-8.06) the odds of experiencing DKA as those without HFI. There was no association between HFI and severe hypoglycemia. CONCLUSIONS: HFI was associated with markedly increased odds of DKA but not with glycemic control or severe hypoglycemia. Future research among YYA with type 2 diabetes should evaluate longitudinally whether alleviating HFI reduces DKA.