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.

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.

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.

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.

Validation of the Enriching New-Onset Diabetes for Pancreatic Cancer Model in a Diverse and Integrated Healthcare Setting.

BACKGROUND: The risk of pancreatic cancer is elevated among people with new-onset diabetes (NOD). Based on Rochester Epidemiology Project Data, the Enriching New-Onset Diabetes for Pancreatic Cancer (END-PAC) model was developed and validated. AIMS: We validated the END-PAC model in a cohort of patients with NOD using retrospectively collected data from a large integrated health maintenance organization. METHODS: A retrospective cohort of patients between 50 and 84 years of age meeting the criteria for NOD in 2010-2014 was identified. Each patient was assigned a risk score (< 1: low risk; 1-2: intermediate risk; ≥ 3: high risk) based on the values of the predictors specified in the END-PAC model. Patients who developed pancreatic ductal adenocarcinoma (PDAC) within 3 years were identified using the Cancer Registry and California State Death files. Area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were estimated. RESULTS: Out of the 13,947 NOD patients who were assigned a risk score, 99 developed PDAC in 3 years (0.7%). Of the 3038 patients who had a high risk, 62 (2.0%) developed PDAC in 3 years. The risk increased to 3.0% in white patients with a high risk. The AUC was 0.75. At the 3+ threshold, the sensitivity, specificity, PPV, and NPV were 62.6%, 78.5%, 2.0%, and 99.7%, respectively. CONCLUSIONS: It is critical that prediction models are validated before they are implemented in various populations and clinical settings. More efforts are needed to develop screening strategies most appropriate for patients with NOD in real-world settings.

Loss of executive function after dialysis initiation in adults with chronic kidney disease.

The association of dialysis initiation with changes in cognitive function among patients with advanced chronic kidney disease is poorly described. To better define this, we enrolled participants with advanced chronic kidney disease from the Chronic Renal Insufficiency Cohort in a prospective study of cognitive function. Eligible participants had a glomerular filtration rate of 20 ml/min/1.73m2 or less, or dialysis initiation within the past two years. We evaluated cognitive function by a validated telephone battery at regular intervals over two years and analyzed test scores as z scores. Of 212 participants, 123 did not transition to dialysis during follow-up, 37 transitioned to dialysis after baseline, and 52 transitioned to dialysis prior to baseline. In adjusted analyses, the transition to dialysis was associated with a significant loss of executive function, but no significant changes in global cognition or memory. The estimated net difference in cognitive z scores at two years for participants who transitioned to dialysis during follow-up compared to participants who did not transition to dialysis was -0.01 (95% confidence interval -0.13, 0.11) for global cognition, -0.24 (-0.51, 0.03) for memory, and -0.33 (-0.60, -0.07) for executive function. Thus, among adults with advanced chronic kidney disease, dialysis initiation was associated with loss of executive function with no change in other aspects of cognition. Larger studies are needed to evaluate cognition during dialysis initiation.

Different components of blood pressure are associated with increased risk of atherosclerotic cardiovascular disease versus heart failure in advanced chronic kidney disease.

Blood pressure is a modifiable risk for cardiovascular disease (CVD). Among hemodialysis patients, there is a U-shaped association between blood pressure and risk of death. However, few studies have examined the association between blood pressure and CVD in patients with stage 4 and 5 chronic kidney disease. Here we studied 1795 Chronic Renal Insufficiency Cohort (CRIC) Study participants with estimated glomerular filtration rate <30 ml/min per 1.73 m2 and not on dialysis. The association of systolic (SBP), diastolic (DBP), and pulse pressure with the risk of physician-adjudicated atherosclerotic CVD (stroke, myocardial infarction, or peripheral arterial disease) and heart failure was tested using Cox regression adjusted for demographics, comorbidity and medications. There was a significant association with higher SBP (adjusted hazard ratio 2.04 [95% confidence interval: 1.46-2.84]) for SBP over 140 vs under 120 mmHg, higher DBP (2.52 [1.54-4.11]) for DBP >90 mm Hg versus <80 mm Hg and higher pulse pressure (2.67 [1.82-3.92]) for pulse pressure >68 mm Hg versus <51 mm Hg with atherosclerotic CVD. For heart failure, there was a significant association with higher pulse pressure only (1.42 [1.05-1.92]) for pulse pressure >68 mm Hg versus <51 mmHg, but not for SBP or DBP. Thus, among participants with stage 4 and 5 chronic kidney disease, there was an independent association between higher SBP, DBP, and pulse pressure with the risk of atherosclerotic CVD, whereas only higher pulse pressure was independently associated with a greater risk of heart failure. Further trials are needed to determine whether aggressive reduction of blood pressure decreases the risk of CVD events in patients with stage 4 and 5 chronic kidney disease.

The Associations between Peripheral Artery Disease and Physical Outcome Measures in Men and Women with Chronic Kidney Disease.

BACKGROUND: Peripheral artery disease (PAD) is highly prevalent and associated with significant morbidity and mortality, but sex-based differences are incompletely understood. We sought to define the associations between PAD and physical outcome measures and to determine if these associations differed by sex in the Chronic Renal Insufficiency Cohort. METHODS: Among 3,543 participants, we assessed the cross-sectional relationship between PAD severity defined by ankle-brachial index; and (1) physical activity (metabolic equivalent [MET]-hr/wk), (2) walking pace (slow versus medium and/or fast), and (3) physical function (12-item Short Form Health Survey [SF-12]) at baseline. RESULTS: In a multivariable linear regression model, PAD severity was not associated with physical activity defined by total MET-hr per wk in men or women (P = 0.432). However, PAD severity was significantly associated with walking activity (P = 0.037), although this relationship did not differ by sex (P = 0.130). Similarly, PAD severity was significantly associated with walking pace (P < 0.001), although this relationship did not differ by sex (P = 0.086). In contrast, there was an independent association between PAD severity and SF-12 (P = 0.018), with a significant interaction by sex (P < 0.001). CONCLUSIONS: These data suggest that tools used to evaluate the functional consequences of PAD should focus on walking activity and walking pace, as well as physical function, where sex-specific associations should be accounted for.

Healthy lifestyle and risk of kidney disease progression, atherosclerotic events, and death in CKD: findings from the Chronic Renal Insufficiency Cohort (CRIC) Study.

BACKGROUND: In general populations, healthy lifestyle is associated with fewer adverse outcomes. We estimated the degree to which adherence to a healthy lifestyle decreases the risk of renal and cardiovascular events among adults with chronic kidney disease (CKD). STUDY DESIGN: Prospective cohort. SETTING & PARTICIPANTS: 3,006 adults enrolled in the Chronic Renal Insufficiency Cohort (CRIC) Study. PREDICTORS: 4 lifestyle factors (regular physical activity, body mass index [BMI] of 20-<25kg/m(2), nonsmoking, and "healthy diet"), individually and in combination. OUTCOMES: CKD progression (50% decrease in estimated glomerular filtration rate or end-stage renal disease), atherosclerotic events (myocardial infarction, stroke, or peripheral arterial disease), and all-cause mortality. MEASUREMENTS: Multivariable-adjusted Cox proportional hazards. RESULTS: During a median follow-up of 4 years, we observed 726 CKD progression events, 355 atherosclerotic events, and 437 deaths. BMI≥25kg/m(2) and nonsmoking were associated with reduced risk of CKD progression (HRs of 0.75 [95% CI, 0.58-0.97] and 0.61 [95% CI, 0.45-0.82] for BMIs of 25 to <30 and ≥30kg/m(2), respectively, versus 20 to <25kg/m(2); HR for nonsmoking of 0.68 [95% CI, 0.55-0.84] compared to the current smoker reference group) and reduced risk of atherosclerotic events (HRs of 0.67 [95% CI, 0.46-0.96] for BMI of 25-<30 vs 20-<25kg/m(2) and 0.55 [95% CI, 0.40-0.75] vs current smoker). Factors associated with reduced all-cause mortality were regular physical activity (HR, 0.64 [95% CI, 0.52-0.79] vs inactive), BMI≥30kg/m(2) (HR, 0.64 [95% CI, 0.43-0.96] vs 20-<25kg/m(2)), and nonsmoking (HR, 0.45 [95% CI, 0.34-0.60] vs current smoker). BMI<20kg/m(2) was associated with increased all-cause mortality risk (HR, 2.11 [95% CI, 1.13-3.93] vs 20-<25kg/m(2)). Adherence to all 4 lifestyle factors was associated with a 68% lower risk of all-cause mortality compared to adherence to no lifestyle factors (HR, 0.32; 95% CI, 0.11-0.89). LIMITATIONS: Lifestyle factors were measured only once. CONCLUSIONS: Regular physical activity, nonsmoking, and BMI≥25kg/m(2) were associated with lower risk of adverse outcomes in this cohort of individuals with CKD.

Limited health literacy is associated with low glomerular filtration in the Chronic Renal Insufficiency Cohort (CRIC) study.

BACKGROUND: Low health literacy in the general population is associated with increased risk of death and hospitalization. The evaluation of health literacy in individuals with predialysis chronic kidney disease (CKD) is limited. METHODS: We conducted a cross-sectional study to evaluate the associations of limited health literacy with kidney function and cardiovascular disease (CVD) risk factors in 2,340 non-Hispanic (NH) Whites and Blacks aged 21 - 74 years with mild-to-moderate CKD. Limited health literacy was defined as a Short Test of Functional Health Literacy in Adults (STOFHLA) score ≤ 22. Outcomes evaluated included estimated glomerular filtration rate (eGFR), 24-hour urine protein excretion, and CVD risk factors. RESULTS: The prevalence of limited health literacy was 28% in NH-Blacks and 5% in NH-Whites. Compared with participants with adequate health literacy, those with limited health literacy were more likely to have lower eGFR (34 vs. 42 mL/min/1.73 m2); higher urine protein/24-hours (0.31 vs. 0.15 g); and higher self-reported CVD (61 vs. 37%); and were less likely to have BP < 130/80 mmHg (51 vs. 58%); p ≤ 0.01 for each comparison. After adjustment, limited health literacy was associated with self-reported CVD (OR 1.51, 95% CI 1.13 - 2.03) and lower eGFR (ß -2.47, p = 0.03). CONCLUSION: In this CKD cohort, limited health literacy was highly prevalent, especially among NH-Blacks, and it was associated with lower eGFR and a less favorable CVD risk factor profile. Further studies are needed to better understand these associations and inform the development of health literacy interventions among individuals with CKD.

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.

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.

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.

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.

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.

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 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.

Urine neutrophil gelatinase-associated lipocalin levels do not improve risk prediction of progressive chronic kidney disease.

Novel biomarkers may improve our ability to predict which patients with chronic kidney disease (CKD) are at higher risk for progressive loss of renal function. Here, we assessed the performance of urine neutrophil gelatinase-associated lipocalin (NGAL) for outcome prediction in a diverse cohort of 3386 patients with CKD in the Chronic Renal Insufficiency Cohort study. In this cohort, the baseline mean estimated glomerular filtration rate (eGFR) was 42.4 ml/min per 1.73 m(2), the median 24-h urine protein was 0.2 g/day, and the median urine NGAL concentration was 17.2 ng/ml. Over an average follow-up of 3.2 years, there were 689 cases in which the eGFR was decreased by half or incident end-stage renal disease developed. Even after accounting for eGFR, proteinuria, and other known CKD progression risk factors, urine NGAL remained a significant independent risk factor (Cox model hazard ratio 1.70 highest to lowest quartile). The association between baseline urine NGAL levels and risk of CKD progression was strongest in the first 2 years of biomarker measurement. Within this time frame, adding urine NGAL to a model that included eGFR, proteinuria, and other CKD progression risk factors led to net reclassification improvement of 24.7%, but the C-statistic remained nearly identical. Thus, while urine NGAL was an independent risk factor of progression among patients with established CKD of diverse etiology, it did not substantially improve prediction of outcome events.

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.

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.