External validation of bloodstream infection mortality risk score in a population-based cohort

419 Background: Median OS of mCRC is 2 years, but the prognosis of individual pts can be highly variable. Our study objective was to develop a scoring system to improve the prognostication of mCRC pts at baseline assessment. Methods: Pts diagnosed with mCRC from 2006 to 2008, referred to 1 of 5 regional cancer centers in British Columbia, and received CT were reviewed. Pts with ECOG >3 were excluded due to their uniform poor prognosis. Univariate analyses were performed on baseline variables and those significantly associated with prognosis were included in a multivariate stepwise selection. Each significant factor was given a weighted score (range 1-5) based on the regression coefficients. Patients were assigned a composite risk score (range 0-15) based on their baseline variables, and then separated into quartiles for OS using cut-point analysis and Kaplan-Meier methods. Validation was conducted with the bootstrap technique. C-index statistic was 0.75, which indicated good discrimination. Results: A total of 505 mCRC pts were included: median age 63 (range 22-86), 58% male, 75% ECOG 0-1, 58% colon primary, 34% >1 metastatic site, and 46% smokers. Median pre-treatment CEA was 16.8 ng/ml. In this cohort, 64% were metastatic at presentation, 81% underwent primary tumor resection, 23% received prior adjuvant CT, and 72% were treated with palliative CT. ECOG 2-3 (HR 3.1, 95%CI 2.4-4.2), no primary resection (HR 2.3, 95%CI 1.6-3.3), colon primary (HR 1.6, 95%CI 1.2-2.1), >1 metastatic site (HR 1.6, 95%CI 1.2-2.1), CEA level >4 ng/ml (HR 1.2, 0.8-1.6), male (HR 1.2, 95%CI 0.8-1.6), and smoker (HR 1.4, 95%CI 1.0-1.8) were significant in the multivariate model and assigned points corresponding to their effect size. Median OS varied significantly depending on the composite risk score (Table). Conclusions: In this population-based analysis, the BCCA mCRC score was a simple method that used baseline variables to improve the prognostication of mCRC pts. This model requires external validation. [Table: see text]

Download Full-text

Faculty Opinions recommendation of The MIDA Mortality Risk Score: development and external validation of a prognostic model for early and late death in degenerative mitral regurgitation.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.732307818.793564313 ◽

2019 ◽

Author(s):

Wendy Tsang

Keyword(s):

Mitral Regurgitation ◽

Risk Score ◽

Mortality Risk ◽

Prognostic Model ◽

External Validation ◽

Late Death

Download Full-text

Development and validation of a deep learning algorithm based on fundus photographs for estimating the CAIDE dementia risk score

10.1101/2021.08.17.21262156 ◽

2021 ◽

Author(s):

Rong Hua ◽

Jianhao Xiong ◽

Gail Li ◽

Yidan Zhu ◽

Zongyuan Ge ◽

...

Keyword(s):

Deep Learning ◽

Risk Score ◽

Learning Algorithm ◽

External Validation ◽

Population Based ◽

Validation Dataset ◽

Internal Validation ◽

Deep Learning Algorithm ◽

Dementia Risk ◽

Fundus Photographs

AbstractImportanceThe Cardiovascular Risk Factors, Aging, and Incidence of Dementia (CAIDE) dementia risk score is a recognized tool for dementia risk stratification. However, its application is limited due to the requirements for multidimensional information and fasting blood draw. Consequently, effective, convenient and noninvasive tool for screening individuals with high dementia risk in large population-based settings is urgently needed.ObjectiveTo develop and validate a deep learning algorithm using retinal fundus photographs for estimating the CAIDE dementia risk score and identifying individuals with high dementia risk.DesignA deep learning algorithm trained via fundus photographs was developed, validated internally and externally with cross-sectional design.SettingPopulation-based.ParticipantsA health check-up population with 271,864 adults were randomized into a development dataset (95%) and an internal validation dataset (5%). The external validation used data from the Beijing Research on Ageing and Vessel (BRAVE) with 1,512 individuals.ExposuresThe estimated CAIDE dementia risk score generated from the algorithm.Main Outcome and MeasureThe algorithm’s performance for identifying individuals with high dementia risk was evaluated by area under the receiver operating curve (AUC) with 95% confidence interval (CI).ResultsThe study involved 258,305 participants (mean aged 42.1 ± 13.4 years, men: 52.7%) in development, 13,559 (mean aged 41.2 ± 13.3 years, men: 52.5%) in internal validation, and 1,512 (mean aged 59.8 ± 7.3 years, men: 37.1%) in external validation. The adjusted coefficient of determination (R2) between the estimated and actual CAIDE dementia risk score was 0.822 in the internal and 0.300 in the external validations, respectively. The algorithm achieved an AUC of 0.931 (95%CI, 0.922–0.939) in the internal validation group and 0.782 (95%CI, 0.749–0.815) in the external group. Besides, the estimated CAIDE dementia risk score was significantly associated with both comprehensive cognitive function and specific cognitive domains.Conclusions and RelevanceThe present study demonstrated that the deep learning algorithm trained via fundus photographs could well identify individuals with high dementia risk in a population-based setting. Our findings suggest that fundus photography may be utilized as a noninvasive and more expedient method for dementia risk stratification.Key PointsQuestionCan a deep learning algorithm based on fundus images estimate the CAIDE dementia risk score and identify individuals with high dementia risk?FindingsThe algorithm developed by fundus photographs from 258,305 check-up participants could well identify individuals with high dementia risk, with area under the receiver operating characteristic curve of 0.931 in internal validation and 0.782 in external validation dataset, respectively. Besides, the estimated CAIDE dementia risk score generated from the algorithm exhibited significant association with cognitive function.MeaningThe deep learning algorithm based on fundus photographs has potential to screen individuals with high dementia risk in population-based settings.

Download Full-text

External Validation of Difficult-to-Treat Resistance Prevalence and Mortality Risk in Gram-Negative Bloodstream Infection Using Electronic Health Record Data From 140 US Hospitals

Open Forum Infectious Diseases ◽

10.1093/ofid/ofz110 ◽

2019 ◽

Vol 6 (4) ◽

Cited By ~ 15

Author(s):

Sameer S Kadri ◽

Yi Ling (Elaine) Lai ◽

Emily E Ricotta ◽

Jeffrey R Strich ◽

Ahmed Babiker ◽

...

Keyword(s):

Bloodstream Infection ◽

Mortality Risk ◽

External Validation ◽

Acute Illness ◽

First Line ◽

Electronic Health Record Data ◽

Health Records ◽

Gram Negative ◽

Record Data ◽

Electronic Health

Abstract Difficult-to-treat resistance (DTR; ie, co-resistance to all first-line antibiotics) in gram-negative bloodstream infection (GNBSI) is associated with decreased survival in administrative data models. We externally validated DTR prevalence and associated mortality risk in GNBSI using detailed clinical data from electronic health records to adjust for baseline differences in acute illness severity.

Download Full-text

Adding Estimated Cardiorespiratory Fitness to the Framingham Risk Score and Mortality Risk in a Korean Population-Based Cohort Study

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph19010510 ◽

2022 ◽

Vol 19 (1) ◽

pp. 510

Author(s):

Inhwan Lee ◽

Jeonghyeon Kim ◽

Hyunsik Kang

Keyword(s):

Cohort Study ◽

Cardiorespiratory Fitness ◽

Risk Score ◽

Mortality Risk ◽

Framingham Risk Score ◽

Population Based ◽

Added Value ◽

Cvd Risk ◽

Framingham Risk ◽

Cvd Mortality

Background: The added value of non-exercise-based estimation of cardiorespiratory fitness (eCRF) to cardiovascular disease (CVD) risk factors for mortality risk has not been examined in Korean populations. Methods: This population-based prospective cohort study examined the relationship of the 10-year Framingham risk score (FRS) for CVD risk and eCRF with all-cause and CVD mortality in a representative sample of Korean adults aged 30 years and older. Data regarding a total of 38,350 participants (16,505 men/21,845 women) were obtained from the 2007–2015 Korea National Health and Nutrition Examination Survey (KNHANES). All-cause and CVD mortality were the main outcomes. The 10-year FRS point sum and eCRF level were the main exposures. Results: All-cause and CVD mortality was positively correlated with the 10-year FRS point summation and inversely correlated with eCRF level in this study population. The protective of high eCRF against all-cause and CVD mortality was more prominent in the middle and high FRS category than in the low FRS category. Notably, the FRS plus eCRF model has better predictor power for estimating mortality risk compared to the FRS only model. Conclusions: The current findings indicate that eCRF can be used as an alternative to objectively measured CRF for mortality risk prediction.

Download Full-text

Abstract # OR-20: External Validation of the Leicester Self-Assessment Diabetes Risk Score in a Population with Intellectual Disability

Endocrine Practice ◽

10.1016/s1530-891x(20)43810-8 ◽

2016 ◽

Vol 22 ◽

pp. 12

Author(s):

Laura Gray ◽

Yogini Chudasama ◽

Alison Dunkley ◽

Freya Tyrer ◽

Rebecca Spong ◽

...

Keyword(s):

Intellectual Disability ◽

Risk Score ◽

External Validation ◽

Diabetes Risk ◽

Self Assessment ◽

Diabetes Risk Score

Download Full-text

Predicting sentinel node positivity in melanoma patients: external validation of a risk‐prediction calculator (the MIA nomogram) using a large European population‐based patient cohort

British Journal of Dermatology ◽

10.1111/bjd.19895 ◽

2021 ◽

Author(s):

M.A. El Sharouni ◽

A.H.R. Varey ◽

A.J. Witkamp ◽

T. Ahmed ◽

V. Sigurdsson ◽

...

Keyword(s):

Sentinel Node ◽

Risk Prediction ◽

External Validation ◽

Population Based ◽

European Population ◽

Patient Cohort ◽

Melanoma Patients

Download Full-text

Comparing the characteristics and predicting the survival of patients with head and neck melanoma versus body melanoma: a population-based study

BMC Cancer ◽

10.1186/s12885-021-08105-y ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Yuxin Ding ◽

Runyi Jiang ◽

Yuhong Chen ◽

Jing Jing ◽

Xiaoshuang Yang ◽

...

Keyword(s):

Head And Neck ◽

Health Management ◽

External Validation ◽

Area Under The Curve ◽

Population Based ◽

Survival Prediction ◽

Cancer Specific Survival ◽

Cox Models ◽

Lentigo Maligna Melanoma ◽

Clinical Tools

Abstract Background Previous studies reported cutaneous melanoma in head and neck (HNM) differed from those in other regions (body melanoma, BM). Individualized tools to predict the survival of patients with HNM or BM remain insufficient. We aimed at comparing the characteristics of HNM and BM, developing and validating nomograms for predicting the survival of patients with HNM or BM. Methods The information of patients with HNM or BM from 2004 to 2015 was obtained from the Surveillance, Epidemiology, and End Results (SEER) database. The HNM group and BM group were randomly divided into training and validation cohorts. We used the Kaplan-Meier method and multivariate Cox models to identify independent prognostic factors. Nomograms were developed via the rms and dynnom packages, and were measured by the concordance index (C-index), the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and calibration plots. Results Of 70,605 patients acquired, 21% had HNM and 79% had BM. The HNM group contained more older patients, male sex and lentigo maligna melanoma, and more frequently had thicker tumors and metastases than the BM group. The 5-year cancer-specific survival (CSS) and overall survival (OS) rates were 88.1 ± 0.3% and 74.4 ± 0.4% in the HNM group and 92.5 ± 0.1% and 85.8 ± 0.2% in the BM group, respectively. Eight variables (age, sex, histology, thickness, ulceration, stage, metastases, and surgery) were identified to construct nomograms of CSS and OS for patients with HNM or BM. Additionally, four dynamic nomograms were available on web. The internal and external validation of each nomogram showed high C-index values (0.785–0.896) and AUC values (0.81–0.925), and the calibration plots showed great consistency. Conclusions The characteristics of HNM and BM are heterogeneous. We constructed and validated four nomograms for predicting the 3-, 5- and 10-year CSS and OS probabilities of patients with HNM or BM. These nomograms can serve as practical clinical tools for survival prediction and individual health management.

Download Full-text