ABSTRACT
This paper showcases the results of the Extract-Transform-Load process mapping the Electronic Health Record of Papageorgiou General Hospital in Thessaloniki, Greece, to the Observational Medical Outcomes Partnership Common Data Model. We describe the staged process utilized to account for the intricate structure of the database, along with some general findings from the mapping. Finally, we investigate potential directions for future research.
Subject(s)
Electronic Health Records , Hospitals, General , Greece , Medical Record Linkage , Humans , Databases, FactualABSTRACT
Treatment effects are often anticipated to vary across groups of patients with different baseline risk. The Predictive Approaches to Treatment Effect Heterogeneity (PATH) statement focused on baseline risk as a robust predictor of treatment effect and provided guidance on risk-based assessment of treatment effect heterogeneity in a randomized controlled trial. The aim of this study is to extend this approach to the observational setting using a standardized scalable framework. The proposed framework consists of five steps: (1) definition of the research aim, i.e., the population, the treatment, the comparator and the outcome(s) of interest; (2) identification of relevant databases; (3) development of a prediction model for the outcome(s) of interest; (4) estimation of relative and absolute treatment effect within strata of predicted risk, after adjusting for observed confounding; (5) presentation of the results. We demonstrate our framework by evaluating heterogeneity of the effect of thiazide or thiazide-like diuretics versus angiotensin-converting enzyme inhibitors on three efficacy and nine safety outcomes across three observational databases. We provide a publicly available R software package for applying this framework to any database mapped to the Observational Medical Outcomes Partnership Common Data Model. In our demonstration, patients at low risk of acute myocardial infarction receive negligible absolute benefits for all three efficacy outcomes, though they are more pronounced in the highest risk group, especially for acute myocardial infarction. Our framework allows for the evaluation of differential treatment effects across risk strata, which offers the opportunity to consider the benefit-harm trade-off between alternative treatments.
ABSTRACT
BACKGROUND: Baseline outcome risk can be an important determinant of absolute treatment benefit and has been used in guidelines for "personalizing" medical decisions. We compared easily applicable risk-based methods for optimal prediction of individualized treatment effects. METHODS: We simulated RCT data using diverse assumptions for the average treatment effect, a baseline prognostic index of risk, the shape of its interaction with treatment (none, linear, quadratic or non-monotonic), and the magnitude of treatment-related harms (none or constant independent of the prognostic index). We predicted absolute benefit using: models with a constant relative treatment effect; stratification in quarters of the prognostic index; models including a linear interaction of treatment with the prognostic index; models including an interaction of treatment with a restricted cubic spline transformation of the prognostic index; an adaptive approach using Akaike's Information Criterion. We evaluated predictive performance using root mean squared error and measures of discrimination and calibration for benefit. RESULTS: The linear-interaction model displayed optimal or close-to-optimal performance across many simulation scenarios with moderate sample size (N = 4,250; ~ 785 events). The restricted cubic splines model was optimal for strong non-linear deviations from a constant treatment effect, particularly when sample size was larger (N = 17,000). The adaptive approach also required larger sample sizes. These findings were illustrated in the GUSTO-I trial. CONCLUSIONS: An interaction between baseline risk and treatment assignment should be considered to improve treatment effect predictions.
Subject(s)
Randomized Controlled Trials as Topic , Humans , Prognosis , Computer Simulation , Sample SizeABSTRACT
OBJECTIVE: This systematic review aims to assess how information from unstructured text is used to develop and validate clinical prognostic prediction models. We summarize the prediction problems and methodological landscape and determine whether using text data in addition to more commonly used structured data improves the prediction performance. MATERIALS AND METHODS: We searched Embase, MEDLINE, Web of Science, and Google Scholar to identify studies that developed prognostic prediction models using information extracted from unstructured text in a data-driven manner, published in the period from January 2005 to March 2021. Data items were extracted, analyzed, and a meta-analysis of the model performance was carried out to assess the added value of text to structured-data models. RESULTS: We identified 126 studies that described 145 clinical prediction problems. Combining text and structured data improved model performance, compared with using only text or only structured data. In these studies, a wide variety of dense and sparse numeric text representations were combined with both deep learning and more traditional machine learning methods. External validation, public availability, and attention for the explainability of the developed models were limited. CONCLUSION: The use of unstructured text in the development of prognostic prediction models has been found beneficial in addition to structured data in most studies. The text data are source of valuable information for prediction model development and should not be neglected. We suggest a future focus on explainability and external validation of the developed models, promoting robust and trustworthy prediction models in clinical practice.
Subject(s)
Machine Learning , PrognosisABSTRACT
OBJECTIVES: This systematic review aims to provide further insights into the conduct and reporting of clinical prediction model development and validation over time. We focus on assessing the reporting of information necessary to enable external validation by other investigators. MATERIALS AND METHODS: We searched Embase, Medline, Web-of-Science, Cochrane Library, and Google Scholar to identify studies that developed 1 or more multivariable prognostic prediction models using electronic health record (EHR) data published in the period 2009-2019. RESULTS: We identified 422 studies that developed a total of 579 clinical prediction models using EHR data. We observed a steep increase over the years in the number of developed models. The percentage of models externally validated in the same paper remained at around 10%. Throughout 2009-2019, for both the target population and the outcome definitions, code lists were provided for less than 20% of the models. For about half of the models that were developed using regression analysis, the final model was not completely presented. DISCUSSION: Overall, we observed limited improvement over time in the conduct and reporting of clinical prediction model development and validation. In particular, the prediction problem definition was often not clearly reported, and the final model was often not completely presented. CONCLUSION: Improvement in the reporting of information necessary to enable external validation by other investigators is still urgently needed to increase clinical adoption of developed models.
Subject(s)
Models, Statistical , PrognosisABSTRACT
OBJECTIVES: Develop simple and valid models for predicting mortality and need for intensive care unit (ICU) admission in patients who present at the emergency department (ED) with suspected COVID-19. DESIGN: Retrospective. SETTING: Secondary care in four large Dutch hospitals. PARTICIPANTS: Patients who presented at the ED and were admitted to hospital with suspected COVID-19. We used 5831 first-wave patients who presented between March and August 2020 for model development and 3252 second-wave patients who presented between September and December 2020 for model validation. OUTCOME MEASURES: We developed separate logistic regression models for in-hospital death and for need for ICU admission, both within 28 days after hospital admission. Based on prior literature, we considered quickly and objectively obtainable patient characteristics, vital parameters and blood test values as predictors. We assessed model performance by the area under the receiver operating characteristic curve (AUC) and by calibration plots. RESULTS: Of 5831 first-wave patients, 629 (10.8%) died within 28 days after admission. ICU admission was fully recorded for 2633 first-wave patients in 2 hospitals, with 214 (8.1%) ICU admissions within 28 days. A simple model-COVID outcome prediction in the emergency department (COPE)-with age, respiratory rate, C reactive protein, lactate dehydrogenase, albumin and urea captured most of the ability to predict death. COPE was well calibrated and showed good discrimination for mortality in second-wave patients (AUC in four hospitals: 0.82 (95% CI 0.78 to 0.86); 0.82 (95% CI 0.74 to 0.90); 0.79 (95% CI 0.70 to 0.88); 0.83 (95% CI 0.79 to 0.86)). COPE was also able to identify patients at high risk of needing ICU admission in second-wave patients (AUC in two hospitals: 0.84 (95% CI 0.78 to 0.90); 0.81 (95% CI 0.66 to 0.95)). CONCLUSIONS: COPE is a simple tool that is well able to predict mortality and need for ICU admission in patients who present to the ED with suspected COVID-19 and may help patients and doctors in decision making.
Subject(s)
COVID-19 , Emergency Service, Hospital , Hospital Mortality , Hospitals , Humans , Intensive Care Units , Retrospective Studies , SARS-CoV-2ABSTRACT
BACKGROUND: Recent evidence suggests that there is often substantial variation in the benefits and harms across a trial population. We aimed to identify regression modeling approaches that assess heterogeneity of treatment effect within a randomized clinical trial. METHODS: We performed a literature review using a broad search strategy, complemented by suggestions of a technical expert panel. RESULTS: The approaches are classified into 3 categories: 1) Risk-based methods (11 papers) use only prognostic factors to define patient subgroups, relying on the mathematical dependency of the absolute risk difference on baseline risk; 2) Treatment effect modeling methods (9 papers) use both prognostic factors and treatment effect modifiers to explore characteristics that interact with the effects of therapy on a relative scale. These methods couple data-driven subgroup identification with approaches to prevent overfitting, such as penalization or use of separate data sets for subgroup identification and effect estimation. 3) Optimal treatment regime methods (12 papers) focus primarily on treatment effect modifiers to classify the trial population into those who benefit from treatment and those who do not. Finally, we also identified papers which describe model evaluation methods (4 papers). CONCLUSIONS: Three classes of approaches were identified to assess heterogeneity of treatment effect. Methodological research, including both simulations and empirical evaluations, is required to compare the available methods in different settings and to derive well-informed guidance for their application in RCT analysis.
Subject(s)
Research Design , Humans , Randomized Controlled Trials as TopicABSTRACT
There is a strong and continuously growing interest in using large electronic healthcare databases to study health outcomes and the effects of pharmaceutical products. However, concerns regarding disease misclassification (i.e. classification errors of the disease status) and its impact on the study results are legitimate. Validation is therefore increasingly recognized as an essential component of database research. In this work, we elucidate the interrelations between the true prevalence of a disease in a database population (i.e. prevalence assuming no disease misclassification), the observed prevalence subject to disease misclassification, and the most common validity indices: sensitivity, specificity, positive and negative predictive value. Based on this, we obtained analytical expressions to derive all the validity indices and true prevalence from the observed prevalence and any combination of two other parameters. The analytical expressions can be used for various purposes. Most notably, they can be used to obtain an estimate of the observed prevalence adjusted for outcome misclassification from any combination of two validity indices and to derive validity indices from each other which would otherwise be difficult to obtain. To allow researchers to easily use the analytical expressions, we additionally developed a user-friendly and freely available web-application.
Subject(s)
Databases, Factual , Disease/classification , Algorithms , Electronic Health Records , Humans , User-Computer InterfaceABSTRACT
The aims of this study were: to compare total ghrelin concentration throughout pregnancy between lactating cows and heifers, and to study the response to acute feed restriction in pregnant or non-pregnant heifers. Blood samples were collected each month of pregnancy from cows (n = 5) and heifers (n = 5) and analyzed for total ghrelin concentration. Compared to pre-conception values, ghrelin concentrations tended to be greater during 3rd month of pregnancy in heifers, whereas they were higher in the 7th, 8th and 9th months in lactating cows, but no difference was detected between lactating cows and heifers. In experiment two, pregnant (n = 4) and non-pregnant (n = 4) heifers were fasted for 24 h. Blood samples were collected 0, 4, 8, 12, 16 and 24 h of fasting and were assayed for, insulin, glucose, cortisol, BHBA and NEFA concentrations, and at time points 0, 8, 16 and 24 for total ghrelin determination. Compared to satiety, ghrelin concentrations were higher at 8th, 16th and 24th hour of fasting in pregnant and at 8th hour in non-pregnant animals, but no difference was detected between pregnant and non-pregnant heifers. Pregnant heifers had lower glucose concentrations than non-pregnant ones. Insulin concentrations were reduced at 4 and 8 h of fasting in pregnant heifers, and stayed unaffected in non-pregnant ones. Cortisol concentrations increased after 4th hour and remained elevated throughout the sampling period in pregnant heifers, while they increased at 24th h in non-pregnant animals. Here, we provide evidence that total ghrelin concentrations rise in response to feed restriction. Albeit no group effect was evident, our results imply that a) during the last trimester of pregnancy total ghrelin is secreted in different pattern between lactating cows and heifers, b) pregnant animals are more responsive than non-pregnant ones to hunger induced stress.