Development and Validation of a Colorectal Cancer Prediction Model: A Nationwide Cohort-Based Study.

BACKGROUND: Early diagnosis of colorectal cancer (CRC) is critical to increasing survival rates. Computerized risk prediction models hold great promise for identifying individuals at high risk for CRC. In order to utilize such models effectively in a population-wide screening setting, development and validation should be based on cohorts that are similar to the target population. AIM: Establish a risk prediction model for CRC diagnosis based on electronic health records (EHR) from subjects eligible for CRC screening. METHODS: A retrospective cohort study utilizing the EHR data of Clalit Health Services (CHS). The study includes CHS members aged 50-74 who were eligible for CRC screening from January 2013 to January 2019. The model was trained to predict receiving a CRC diagnosis within 2 years of the index date. Approximately 20,000 EHR demographic and clinical features were considered. RESULTS: The study includes 2935 subjects with CRC diagnosis, and 1,133,457 subjects without CRC diagnosis. Incidence values of CRC among subjects in the top 1% risk scores were higher than baseline (2.3% vs 0.3%; lift 8.38; P value < 0.001). Cumulative event probabilities increased with higher model scores. Model-based risk stratification among subjects with a positive FOBT, identified subjects with more than twice the risk for CRC compared to FOBT alone. CONCLUSIONS: We developed an individualized risk prediction model for CRC that can be utilized as a complementary decision support tool for healthcare providers to precisely identify subjects at high risk for CRC and refer them for confirmatory testing.

Developing a COVID-19 mortality risk prediction model when individual-level data are not available.

At the COVID-19 pandemic onset, when individual-level data of COVID-19 patients were not yet available, there was already a need for risk predictors to support prevention and treatment decisions. Here, we report a hybrid strategy to create such a predictor, combining the development of a baseline severe respiratory infection risk predictor and a post-processing method to calibrate the predictions to reported COVID-19 case-fatality rates. With the accumulation of a COVID-19 patient cohort, this predictor is validated to have good discrimination (area under the receiver-operating characteristics curve of 0.943) and calibration (markedly improved compared to that of the baseline predictor). At a 5% risk threshold, 15% of patients are marked as high-risk, achieving a sensitivity of 88%. We thus demonstrate that even at the onset of a pandemic, shrouded in epidemiologic fog of war, it is possible to provide a useful risk predictor, now widely used in a large healthcare organization.

Epidemiology and Clinical Outcomes of Hospitalizations for Acute Respiratory or Febrile Illness and Laboratory-Confirmed Influenza Among Pregnant Women During Six Influenza Seasons, 2010-2016.

BACKGROUND: Pregnant women are at increased risk of seasonal influenza hospitalizations, but data about the epidemiology of severe influenza among pregnant women remain largely limited to pandemics. METHODS: To describe the epidemiology of hospitalizations for acute respiratory infection or febrile illness (ARFI) and influenza-associated ARFI among pregnant women, administrative and electronic health record data were analyzed from retrospective cohorts of pregnant women hospitalized with ARFI who had testing for influenza viruses by reverse-transcription polymerase chain reaction (RT-PCR) in Australia, Canada, Israel, and the United States during 2010-2016. RESULTS: Of 18 048 ARFI-coded hospitalizations, 1064 (6%) included RT-PCR testing for influenza viruses, 614 (58%) of which were influenza positive. Of 614 influenza-positive ARFI hospitalizations, 35% were in women with low socioeconomic status, 20% with underlying conditions, and 67% in their third trimesters. The median length of influenza-positive hospitalizations was 2 days (interquartile range, 1-4), 18% (95% confidence interval [CI], 15%-21%) resulted in delivery, 10% (95% CI, 8%-12%) included a pneumonia diagnosis, 5% (95% CI, 3%-6%) required intensive care, 2% (95% CI, 1%-3%) included a sepsis diagnosis, and <1% (95% CI, 0%-1%) resulted in respiratory failure. CONCLUSIONS: Our findings characterize seasonal influenza hospitalizations among pregnant women and can inform assessments of the public health and economic impact of seasonal influenza on pregnant women.

Influenza Vaccine Effectiveness Against Hospitalization in Fully and Partially Vaccinated Children in Israel: 2015-2016, 2016-2017, and 2017-2018.

BACKGROUND: Influenza vaccine effectiveness (VE) varies by season, circulating influenza strain, age, and geographic location. There have been few studies of influenza VE among hospitalized children, particularly in Europe and the Middle East. METHODS: We estimated VE against influenza hospitalization among children aged 6 months to 8 years at Clalit Health Services hospitals in Israel in the 2015-2016, 2016-2017, and 2017-2018 influenza seasons, using the test-negative design. Estimates were computed for full and partial vaccination. RESULTS: We included 326 influenza-positive case patients and 2821 influenza-negative controls (140 case patients and 971 controls from 2015-2016, 36 case patients and 1069 controls from 2016-2017, and 150 case patients and 781 controls from 2017-2018). Over all seasons, VE was 53.9% for full vaccination (95% confidence interval [CI], 38.6%-68.3%), and 25.6% for partial vaccination (-3% to 47%). In 2015-2016, most viruses were influenza A(H1N1) and vaccine lineage-mismatched influenza B/Victoria; the VE for fully vaccinated children was statistically significant for influenza A (80.7%; 95% CI, 40.3%-96.1%) but not B (23.0%; -38.5% to 59.4%). During 2016-2017, influenza A(H3N2) predominated, and VE was (70.8%; 95% CI, 17.4%-92.4%). In 2017-2018, influenza A(H3N2), H1N1 and lineage-mismatched influenza B/Yamagata cocirculated; VE was statistically significant for influenza B (63.0%; 95% CI, 24.2%-83.7%) but not influenza A (46.3%; -7.2% to 75.3%). CONCLUSIONS: Influenza vaccine was effective in preventing hospitalizations among fully vaccinated Israeli children over 3 influenza seasons, but not among partially vaccinated children. There was cross-lineage protection in a season where the vaccine contained B/Victoria and the circulating strain was B/Yamagata, but not in a season with the opposite vaccine-circulating strain distribution.