One-year mortality of colorectal cancer patients: development and validation of a prediction model using linked national electronic data.
Ontology highlight
ABSTRACT: Background
The existing literature does not provide a prediction model for mortality of all colorectal cancer patients using contemporary national hospital data. We developed and validated such a model to predict colorectal cancer death within 90, 180 and 365 days after diagnosis.Methods
Cohort study using linked national cancer and death records. The development population included 27,480 patients diagnosed in England in 2015. The test populations were diagnosed in England in 2016 (n = 26,411) and Wales in 2015-2016 (n = 3814). Predictors were age, gender, socioeconomic status, referral source, performance status, tumour site, TNM stage and treatment intent. Cox regression models were assessed using Brier scores, c-indices and calibration plots.Results
In the development population, 7.4, 11.7 and 17.9% of patients died from colorectal cancer within 90, 180 and 365 days after diagnosis. T4 versus T1 tumour stage had the largest adjusted association with the outcome (HR 4.67; 95% CI: 3.59-6.09). C-indices were 0.873-0.890 (England) and 0.856-0.873 (Wales) in the test populations, indicating excellent separation of predicted risks by outcome status. Models were generally well calibrated.Conclusions
The model was valid for predicting short-term colorectal cancer mortality. It can provide personalised information to support clinical practice and research.
SUBMITTER: Cowling TE
PROVIDER: S-EPMC7652941 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeDe-implementation of low-value services among patients with limited life expectancy is challenging. Robust mortality prediction models using routinely collected health care data can enhance health care stakeholders' ability to identify populations with limited life expectancy. We developed and validated a claims-based prediction model for 5-year mortality using regularized regression methods.MethodsMedicare beneficiaries age 66 or older with an office visit and at least 12 months of pre-visit continuous Medicare A/B enrollment were identified in 2008. Five-year mortality was assessed through 2013. Secondary outcomes included 30-, 90-, and 180-day and 1-year mortality. Claims-based predictors, including comorbidities and indicators of disability, frailty, and functional impairment, were selected using regularized logistic regression, applying the least absolute shrinkage and selection operator (LASSO) in a random 80% training sample. Model performance was assessed and compared with the Gagne comorbidity score in the 20% validation sample.ResultsOverall, 183 204 (24%) individuals died. In addition to demographics, 161 indicators of comorbidity and function were included in the final model. In the validation sample, the c-statistic was 0.825 (0.823-0.828). Median-predicted probability of 5-year mortality was 14%; almost 4% of the cohort had a predicted probability greater than 80%. Compared with the Gagne score, the LASSO model led to improved 5-year mortality classification (net reclassification index = 9.9%; integrated discrimination index = 5.2%).ConclusionsOur claims-based model predicting 5-year mortality showed excellent discrimination and calibration, similar to the Gagne score model, but resulted in improved mortality classification. Regularized regression is a feasible approach for developing prediction tools that could enhance health care research and evaluation of care quality.
| S-EPMC6519458 | biostudies-literature
Project description:Background/objectivesA claims-based model predicting 5-year mortality (Lund-Lewis) was developed in a 2008 cohort of North Carolina (NC) Medicare beneficiaries and included indicators of comorbid conditions, frailty, disability, and functional impairment. The objective of this study was to validate the Lund-Lewis model externally within a nationwide sample of Medicare beneficiaries.DesignRetrospective validation study.SettingU.S. Medicare population.ParticipantsFrom a random sample of Medicare beneficiaries, we created four annual cohorts from 2008 to 2011 of individuals aged 66 and older with an office visit in that year. The annual cohorts ranged from 1.13 to 1.18 million beneficiaries.MeasurementsThe outcome was 5-year all-cause mortality. We assessed clinical indicators in the 12 months before the qualifying office visit and estimated predicted 5-year mortality for each beneficiary in the nationwide sample by applying estimates derived in the original NC cohort. Model performance was assessed by quantifying discrimination, calibration, and reclassification metrics compared with a model fit on a comorbidity score.ResultsAcross the annual cohorts, 5-year mortality ranged from 24.4% to 25.5%. The model had strong discrimination (C-statistics ranged across cohorts from .823 to .826). Reclassification measures showed improvement over a comorbidity score model for beneficiaries who died but reduced performance among beneficiaries who survived. The calibration slope ranged from .83 to .86; the model generally predicted a higher risk than observed.ConclusionThe Lund-Lewis model showed strong and consistent discrimination in a national U.S. Medicare sample, although calibration indicated slight overfitting. Future work should investigate methods for improving model calibration and evaluating performance within specific disease settings.
| S-EPMC7781164 | biostudies-literature
Project description:BackgroundNational linked mortality and census data have not previously been available for Australia. We estimated education-based mortality inequalities from linked census and mortality data that are suitable for international comparisons.MethodsWe used the Australian Bureau of Statistics Death Registrations to Census file, with data on deaths (2011-2012) linked probabilistically to census data (linkage rate 81%). To assess validity, we compared mortality rates by age group (25-44, 45-64, 65-84 years), sex and area-inequality measures to those based on complete death registration data. We used negative binomial regression to quantify inequalities in all-cause mortality in relation to five levels of education ['Bachelor degree or higher' (highest) to 'no Year 12 and no post-secondary qualification' (lowest)], separately by sex and age group, adjusting for single year of age and correcting for linkage bias and missing education data.ResultsMortality rates and area-based inequality estimates were comparable to published national estimates. Men aged 25-84 years with the lowest education had age-adjusted mortality rates 2.20 [95% confidence interval (CI): 2.08‒2.33] times those of men with the highest education. Among women, the rate ratio was 1.64 (1.55‒1.74). Rate ratios were 3.87 (3.38‒4.44) in men and 2.57 (2.15‒3.07) in women aged 25-44 years, decreasing to 1.68 (1.60‒1.76) in men and 1.44 (1.36‒1.53) in women aged 65-84 years. Absolute education inequalities increased with age. One in three to four deaths (31%) was associated with less than Bachelor level education.ConclusionsThese linked national data enabled valid estimates of education inequality in mortality suitable for international comparisons. The magnitude of relative inequality is substantial and similar to that reported for other high-income countries.
| S-EPMC7266531 | biostudies-literature
Project description:PurposeTo develop prediction models for short-term mortality risk assessment following colorectal cancer surgery.MethodsData was harmonized from four Danish observational health databases into the Observational Medical Outcomes Partnership Common Data Model. With a data-driven approach using the Least Absolute Shrinkage and Selection Operator logistic regression on preoperative data, we developed 30-day, 90-day, and 1-year mortality prediction models. We assessed discriminative performance using the area under the receiver operating characteristic and precision-recall curve and calibration using calibration slope, intercept, and calibration-in-the-large. We additionally assessed model performance in subgroups of curative, palliative, elective, and emergency surgery.ResultsA total of 57,521 patients were included in the study population, 51.1% male and with a median age of 72 years. The model showed good discrimination with an area under the receiver operating characteristic curve of 0.88, 0.878, and 0.861 for 30-day, 90-day, and 1-year mortality, respectively, and a calibration-in-the-large of 1.01, 0.99, and 0.99. The overall incidence of mortality were 4.48% for 30-day mortality, 6.64% for 90-day mortality, and 12.8% for 1-year mortality, respectively. Subgroup analysis showed no improvement of discrimination or calibration when separating the cohort into cohorts of elective surgery, emergency surgery, curative surgery, and palliative surgery.ConclusionWe were able to train prediction models for the risk of short-term mortality on a data set of four combined national health databases with good discrimination and calibration. We found that one cohort including all operated patients resulted in better performing models than cohorts based on several subgroups.
| S-EPMC10904562 | biostudies-literature
Project description:BackgroundElectronic medical records (EMR) can be a cost-effective source for hypertension surveillance. However, diagnosis of hypertension in EMR is commonly under-coded and warrants the needs to review blood pressure and antihypertensive drugs for hypertension case identification.MethodsWe included all the patients actively registered in The Health Improvement Network (THIN) database, UK, on 31 December 2011. Three case definitions using diagnosis code, antihypertensive drug prescriptions and abnormal blood pressure, respectively, were used to identify hypertension patients. We compared the prevalence and treatment rate of hypertension in THIN with results from Health Survey for England (HSE) in 2011.ResultsCompared with prevalence reported by HSE (29.7%), the use of diagnosis code alone (14.0%) underestimated hypertension prevalence. The use of any of the definitions (38.4%) or combination of antihypertensive drug prescriptions and abnormal blood pressure (38.4%) had higher prevalence than HSE. The use of diagnosis code or two abnormal blood pressure records with a 2-year period (31.1%) had similar prevalence and treatment rate of hypertension with HSE.ConclusionsDifferent definitions should be used for different study purposes. The definition of 'diagnosis code or two abnormal blood pressure records with a 2-year period' could be used for hypertension surveillance in THIN.
| S-EPMC5072168 | biostudies-literature
Project description:BackgroundChronic kidney disease (CKD) is a major public health concern in the United States with high prevalence, growing incidence, and serious adverse outcomes.ObjectiveWe aimed to develop and validate a model to identify patients at risk of receiving a new diagnosis of CKD (incident CKD) during the next 1 year in a general population.MethodsThe study population consisted of patients who had visited any care facility in the Maine Health Information Exchange network any time between January 1, 2013, and December 31, 2015, and had no history of CKD diagnosis. Two retrospective cohorts of electronic medical records (EMRs) were constructed for model derivation (N=1,310,363) and validation (N=1,430,772). The model was derived using a gradient tree-based boost algorithm to assign a score to each individual that measured the probability of receiving a new diagnosis of CKD from January 1, 2014, to December 31, 2014, based on the preceding 1-year clinical profile. A feature selection process was conducted to reduce the dimension of the data from 14,680 EMR features to 146 as predictors in the final model. Relative risk was calculated by the model to gauge the risk ratio of the individual to population mean of receiving a CKD diagnosis in next 1 year. The model was tested on the validation cohort to predict risk of CKD diagnosis in the period from January 1, 2015, to December 31, 2015, using the preceding 1-year clinical profile.ResultsThe final model had a c-statistic of 0.871 in the validation cohort. It stratified patients into low-risk (score 0-0.005), intermediate-risk (score 0.005-0.05), and high-risk (score ? 0.05) levels. The incidence of CKD in the high-risk patient group was 7.94%, 13.7 times higher than the incidence in the overall cohort (0.58%). Survival analysis showed that patients in the 3 risk categories had significantly different CKD outcomes as a function of time (P<.001), indicating an effective classification of patients by the model.ConclusionsWe developed and validated a model that is able to identify patients at high risk of having CKD in the next 1 year by statistically learning from the EMR-based clinical history in the preceding 1 year. Identification of these patients indicates care opportunities such as monitoring and adopting intervention plans that may benefit the quality of care and outcomes in the long term.
| S-EPMC5550735 | biostudies-literature
Project description:BACKGROUND:Predicting death in a cohort of clinically diverse, multicondition hospitalized patients is difficult. Prognostic models that use electronic medical record (EMR) data to determine 1-year death risk can improve end-of-life planning and risk adjustment for research. OBJECTIVE:Determine if the final set of demographic, vital sign, and laboratory data from a hospitalization can be used to accurately quantify 1-year mortality risk. DESIGN:A retrospective study using electronic medical record data linked with the state death registry. PARTICIPANTS:A total of 59,848 hospitalized patients within a six-hospital network over a 4-year period. MAIN MEASURES:The last set of vital signs, complete blood count, basic and complete metabolic panel, demographic information, and ICD codes. The outcome of interest was death within 1 year. KEY RESULTS:Model performance was measured on the validation data set. Random forests (RF) outperformed logisitic regression (LR) models in discriminative ability. An RF model that used the final set of demographic, vitals, and laboratory data from the final 48 h of hospitalization had an AUC of 0.86 (0.85-0.87) for predicting death within a year. Age, blood urea nitrogen, platelet count, hemoglobin, and creatinine were the most important variables in the RF model. Models that used comorbidity variables alone had the lowest AUC. In groups of patients with a high probability of death, RF models underestimated the probability by less than 10%. CONCLUSION:The last set of EMR data from a hospitalization can be used to accurately estimate the risk of 1-year mortality within a cohort of multicondition hospitalized patients.
| S-EPMC5975145 | biostudies-literature
Project description:ObjectivesIdentification of patients at increased mortality risk is important in the context of increasing multimorbidity and an ageing population, to help facilitate the planning and delivery of services. The aim of this study was to examine 1-year all-cause mortality in a cohort of primary care patients in whom inflammatory markers including C reactive protein (CRP), erythrocyte sedimentation rate (ESR) and plasma viscosity (PV), had been tested.DesignObservational cohort study using general practitioner Electronic Health Records from the Clinical Practice Research Datalink, with linkage to Office for National Statistics (ONS) Death Registry.SettingUK Primary Care.Participants159 325 patients with inflammatory marker tests done in 2014 and 39 928 age, sex and practice-matched controls without inflammatory marker testing. ONS Death registry data were available for 109 966 participants.Primary and secondary outcome measuresOne-year mortality in those with raised inflammatory markers compared with normal inflammatory markers and untested controls. Subanalyses stratified 1-year mortality by age group, gender and cause of death.ResultsPatients with a raised inflammatory marker (n=47 797) had an overall 1-year all-cause mortality of 6.89%, compared with 1.41% in those with normal inflammatory markers (p<0.001) and 1.62% in untested controls. A raised CRP is associated with the highest mortality rate at 8.76% compared with 4.99% for ESR and 4.66% for PV. One-year mortality is higher in men with a raised inflammatory marker compared with women (9.78% vs 5.29%). The C-statistic of a simple mortality prediction model containing age, sex and CRP test result is 0.89.ConclusionsInflammatory markers are a strong predictor of all-cause mortality in primary care, with a C-statistic comparable to several previously developed frailty indices. Future research should consider the added value of CRP testing, in combination with other risk factors, to improve prediction of mortality in primary care. Evidence- based interventions for frailty are needed alongside predictive tools.
| S-EPMC7566728 | biostudies-literature
Project description:Early readmission following hip fracture (HFx) is associated with high morbidity and mortality. We conducted a survival analysis of patients with readmission within 1 year after HFx to elucidate the trend and predictors for readmission. We used Taiwan National Health Insurance Database to recruit HFx patients who underwent operations between 2000 and 2009. Patients < 60 years; with pathological fractures; involved in major traffic accidents; with previous pelvis, femur, and hip operations; or who died during the index admission were excluded. We used the Chi-square test, logistic regression, Kaplan-Meier method, and Cox proportional hazards model to analyze variables, including age, gender, hospital stay duration, index admission time, and comorbidity on readmission. 5,442 subjects (61.2% female) met the criteria with mean age of 78.8 years. Approximately 15% and 43% HFx patients were readmitted within 30 days (early) and between 30 days and 1 year (late) after discharge, respectively. Highest readmission incidence was observed within the first 30 days. Most common causes of readmission in early and late groups were respiratory system diseases and injuries, respectively. Cox model showed male, old age, hospital stay > 9 days, Charlson Comorbidity Index ≥ 1, index admission during 2000-2003, and internal fixation of HFx were independent predictors of readmission. One-year mortality of the early and the late readmission groups was 44.9% and 32.3%, much higher than overall mortality which was 16.8%. Predictive factors for readmission within 1 year included male, old age, comorbidities, and longer hospital stay. One-year mortality in readmitted patients was significantly higher. HFx patients with these factors need careful follow-up, especially within 30 days after discharge.
| S-EPMC5524803 | biostudies-other
Project description:BackgroundMany patients with atrial fibrillation (AF) remain undiagnosed despite availability of interventions to reduce stroke risk. Predictive models to date are limited by data requirements and theoretical usage. We aimed to develop a model for predicting the 2-year probability of AF diagnosis and implement it as proof-of-concept (POC) in a production electronic health record (EHR).MethodsWe used a nested case-control design using data from the Indiana Network for Patient Care. The development cohort came from 2016 to 2017 (outcome period) and 2014 to 2015 (baseline). A separate validation cohort used outcome and baseline periods shifted 2 years before respective development cohort times. Machine learning approaches were used to build predictive model. Patients ≥ 18 years, later restricted to age ≥ 40 years, with at least two encounters and no AF during baseline, were included. In the 6-week EHR prospective pilot, the model was silently implemented in the production system at a large safety-net urban hospital. Three new and two previous logistic regression models were evaluated using receiver-operating characteristics. Number, characteristics, and CHA2DS2-VASc scores of patients identified by the model in the pilot are presented.ResultsAfter restricting age to ≥ 40 years, 31,474 AF cases (mean age, 71.5 years; female 49%) and 22,078 controls (mean age, 59.5 years; female 61%) comprised the development cohort. A 10-variable model using age, acute heart disease, albumin, body mass index, chronic obstructive pulmonary disease, gender, heart failure, insurance, kidney disease, and shock yielded the best performance (C-statistic, 0.80 [95% CI 0.79-0.80]). The model performed well in the validation cohort (C-statistic, 0.81 [95% CI 0.8-0.81]). In the EHR pilot, 7916/22,272 (35.5%; mean age, 66 years; female 50%) were identified as higher risk for AF; 5582 (70%) had CHA2DS2-VASc score ≥ 2.ConclusionsUsing variables commonly available in the EHR, we created a predictive model to identify 2-year risk of developing AF in those previously without diagnosed AF. Successful POC implementation of the model in an EHR provided a practical strategy to identify patients who may benefit from interventions to reduce their stroke risk.
| S-EPMC8019173 | biostudies-literature