RESUMO
PURPOSE: Histopathologic features are critical for studying risk factors of colorectal polyps, but remain deeply embedded within unstructured pathology reports, requiring costly and time-consuming manual abstraction for research. In this study, we developed and evaluated a natural language processing (NLP) pipeline to automatically extract histopathologic features of colorectal polyps from pathology reports, with an emphasis on individual polyp size. These data were then linked with structured electronic health record (EHR) data, creating an analysis-ready epidemiologic data set. METHODS: We obtained 24,584 pathology reports from colonoscopies performed at the University of Utah's Gastroenterology Clinic. Two investigators annotated 350 reports to determine inter-rater agreement, develop an annotation scheme, and create a reference standard for performance evaluation. The pipeline was then developed, and performance was compared against the reference for extracting polyp location, histology, size, shape, dysplasia, and the number of polyps. Finally, the pipeline was applied to 24,225 unseen reports and NLP-extracted data were linked with structured EHR data. RESULTS: Across all features, our pipeline achieved a precision of 98.9%, a recall of 98.0%, and an F1-score of 98.4%. In patients with polyps, the pipeline correctly extracted 95.6% of sizes, 97.2% of polyp locations, 97.8% of histology, 98.3% of shapes, and 98.3% of dysplasia levels. When applied to unseen data, the pipeline classified 12,889 patients as having polyps, 4,907 patients without polyps, and extracted the features of 28,387 polyps. Tubular adenomas were the most common subtype (55.9%), 8.1% of polyps were advanced adenomas, and the mean polyp size was 0.57 (±0.4) cm. CONCLUSION: Our pipeline extracted histopathologic features of colorectal polyps from colonoscopy pathology reports, most notably individual polyp sizes, with considerable accuracy. This study demonstrates the utility of NLP for extracting polyp features and linking these data with EHR data to create an epidemiologic data set to study colorectal polyp risk factors and outcomes.
Assuntos
Adenoma , Pólipos do Colo , Neoplasias Colorretais , Humanos , Pólipos do Colo/diagnóstico , Pólipos do Colo/epidemiologia , Pólipos do Colo/patologia , Neoplasias Colorretais/diagnóstico , Neoplasias Colorretais/epidemiologia , Neoplasias Colorretais/patologia , Processamento de Linguagem Natural , Adenoma/diagnóstico , Adenoma/epidemiologia , Adenoma/patologia , Estudos Epidemiológicos , HiperplasiaRESUMO
BACKGROUND: Regulating meal timing may have efficacy for improving metabolic health for preventing or managing chronic disease. However, the reliability of measuring meal timing with commonly used dietary assessment tools needs characterization prior to investigating meal timing and health outcomes in epidemiologic studies. OBJECTIVES: To evaluate the reliability of estimating meal timing parameters, including overnight fasting duration, the midpoint of overnight fasting time, the number of daily eating episodes, the period with the largest percentage of daily caloric intake, and late last eating episode (> 09:00 pm) from repeated 24-h dietary recalls (24HRs). METHODS: Intraclass correlation coefficients (ICC), Light's Kappa estimates, and 95% CIs were calculated from repeated 24HR administered in 3 epidemiologic studies: The United States-based Interactive Diet and Activity Tracking in AARP (IDATA) study (n = 996, 6 24HR collected over 12-mo), German EPIC-Potsdam Validation Study (European Prospective Investigation into Cancer and Nutrition Potsdam Germany cohort) (n = 134, 12 24HR collected over 12-mo) and EPIC-Potsdam BMBF-II Study (Federal Ministry of Education and Research, "Bundesministerium für Bildung und Forschung") (n = 725, 4 24HR collected over 36 mo). RESULTS: Measurement reliability of overnight fasting duration based on a single 24HR was "poor" in all studies [ICC range: 0.27; 95% CI: 0.23, 0.32 - 0.46; 95% CI: 0.43, 0.50]. Reliability was "moderate" with 3 24HR (ICC range: 0.53; 95% CI: 0.47, 0.58 in IDATA, 0.62; 95% CI: 0.52, 0.69 in the EPIC-Potsdam Validation Study, and 0.72; 95% CI: 0.70-0.75 in the EPIC-Potsdam BMBF-II Study). Results were similar for the midpoint of overnight fasting time and the number of eating episodes. Reliability of measuring late eating was "fair" in IDATA (Light's Kappa: 0.30; 95% CI: 0.21, 0.39) and "slight" in the EPIC-Potsdam Validation study and the EPIC-Potsdam BMBF-II study (Light's Kappa: 0.19; 95% CI: 0.15, 0.25 and 0.09; 95% CI: 0.06, 0.12, respectively). Reliability estimates differed by sex, BMI, weekday, and season of 24HR administration in some studies. CONCLUSIONS: Our results show that ≥ 3 24HR over a 1-3-y period are required for reliable estimates of meal timing variables.
Assuntos
Dieta , Ingestão de Energia , Humanos , Estudos Prospectivos , Reprodutibilidade dos Testes , Ingestão de Energia/fisiologia , RefeiçõesRESUMO
BACKGROUND: Individuals diagnosed with an obesity-related cancer (ORC survivors) are at an elevated risk of incident diabetes compared with cancer-free individuals, but whether this confers survival disadvantage is unknown. METHODS: We assessed the rate of incident diabetes in ORC survivors and evaluated the association of incident diabetes with all-cause and cancer-specific mortality among females with ORC in the Women's Health Initiative cohort (N = 14,651). Cox proportional hazards regression models stratified by exposure-risk periods (0-1, >1-3, >3-5, >5-7, and >7-10 years) from ORC diagnosis and time-varying exposure (diabetes) analyses were performed. RESULTS: Among the ORC survivors, a total of 1.3% developed diabetes within ≤1 year of follow-up and 2.5%, 2.3%, 2.3%, and 3.6% at 1-3, 3-5, 5-7, and 7-10 years of follow-up, respectively, after an ORC diagnosis. The median survival for those diagnosed with diabetes within 1-year of cancer diagnosis and those with no diabetes diagnosis in that time frame was 8.8 [95% confidence interval (CI), 7.0-14.5) years and 16.6 (95% CI, 16.1-17.0) years, respectively. New-onset compared with no diabetes as a time-varying exposure was associated with higher risk of all-cause (HR, 1.27; 95% CI, 1.16-1.40) and cancer-specific (HR, 1.17; 95% CI, 0.99-1.38) mortality. When stratified by exposure-risk periods, incident diabetes in ≤1 year of follow-up was associated with higher all-cause (HR, 1.76; 95% CI, 1.40-2.20) and cancer-specific (HR0-1, 1.82; 95% CI, 1.28-2.57) mortality, compared with no diabetes diagnosis. CONCLUSIONS: Incident diabetes was associated with worse cancer-specific and all-cause survival, particularly in the year after cancer diagnosis. IMPACT: These findings draw attention to the importance of diabetes prevention efforts among cancer survivors to improve survival outcomes.
Assuntos
Diabetes Mellitus , Neoplasias , Feminino , Humanos , Fatores de Risco , Saúde da Mulher , Obesidade/complicações , Obesidade/epidemiologia , Diabetes Mellitus/epidemiologia , Modelos de Riscos Proporcionais , Neoplasias/diagnóstico , Neoplasias/epidemiologia , Neoplasias/complicaçõesRESUMO
Context: Polycystic ovarian syndrome (PCOS) is a complex disorder in which metabolic abnormalities are associated with reproductive dysfunction. Women with PCOS have increased ceramide concentrations. Previous studies demonstrated that treating metabolic abnormalities of PCOS with metformin improved glucose effectiveness after 12 weeks. Objective: We evaluated whether, in women with PCOS, lower baseline ceramide, diacylglycerol (DAG), and triacylglycerol (TAG) concentrations were associated with improved metabolic response to metformin. Methods: Women (n = 29), aged 29 ± 5 years and diagnosed with PCOS by the NIH criteria underwent an intravenous glucose tolerance test (IVGTT) before and after 12-week treatment with metformin (1500â mg per day). Metabolic responders were defined by improved glucose effectiveness, specifically, the ability of glucose to stimulate uptake and suppress production, after metformin treatment. Results: Twelve weeks of metformin resulted in weight loss (-1.7 ± 2.6â kg, P < 0.01) and a reduction in BMI (-0.6 ± 0.9â kg/m2, P < 0.01) with no change in HbA1c. The concentrations of Cer(d18:1/22:0), Cer(d18:1/24:0), total ceramides, total Cer(d16:0), total Cer(d18:2), DAG, dihydrosphingomyelin (DHSM), and TAG decreased after metformin treatment (P < 0.05). Baseline total Cer(d16:0) concentration <204.1â pmol/mL was 82% sensitive (AUC 0.72, P = 0.03) and total DHSM concentration <32237â pmol/mL was 100% specific (AUC 0.73, P = 0.03) in predicting improved metabolic response to metformin, as measured by IVGTT. Conclusion: Lower total Cer(16:0) and DHSM concentrations are associated with a beneficial metabolic response to metformin in women with PCOS. Based on the known association between higher ceramide levels and type 2 diabetes, the data suggest that metformin improves metabolic parameters in women with mild metabolic derangements.
RESUMO
BACKGROUND: Obesity is a prevalent health threat and risk factor for type 2 diabetes. In this study, we evaluate the relationship between ceramides, which inhibit insulin secretion and sensitivity, and markers of glucose homeostasis and diabetes remission or recursion in patients who have undergone a Roux-en-Y gastric bypass (RYGB). METHODS: The Utah Obesity Study is a prospective cohort study, with targeted ceramide and dihydroceramide measurements performed on banked serum samples. The Utah Obesity Study consists of 1,156 participants in three groups: a RYGB surgery group, a non-surgery group denied insurance coverage, and severely obese population controls. Clinical examinations and ceramide assessments were performed at baseline and 2 and 12 years after RYGB surgery. FINDINGS: Surgery patients (84% female, 42.2 ± 10.6 years of age at baseline) displayed lower levels of several serum dihydroceramides and ceramides at 2 and 12 years after RYGB. By contrast, neither the control group (77% female, 48.7± 6.4 years of age at baseline) nor the non-surgery group (95% female, 43.0± 11.4 years of age at baseline) experienced significant decreases in any species. Using a linear mixed effect model, we found that multiple dihydroceramides and ceramides positively associated with the glycemic control measures HOMA-IR and HbA1c. In surgery group participants with prevalent diabetes, ceramides inversely predict diabetes remission, independent of changes in weight. CONCLUSIONS: Ceramide decreases may explain the insulin sensitization and diabetes resolution observed in most RYGB surgery patients. FUNDING: Funded by the National Institutes of health (NIH), The Juvenile Diabetes Research Foundation, and the American Heart Association.