The aim of this thesis was to investigate if a text-mining tool is suitable for collecting real-world data from electronic health records to evaluate cancer treatments in clinical practice. By... Show moreThe aim of this thesis was to investigate if a text-mining tool is suitable for collecting real-world data from electronic health records to evaluate cancer treatments in clinical practice. By investigating a range of use cases including treatments of patients with renal cell carcinoma, hepatocellular carcinoma, melanoma, breast cancer, and COVID-19, it showed that the text-mining tool is a suitable method of data needed for the evaluation of treatment patterns, effectiveness, safety, prognostic factors, and guideline adherence. The discussion showed that enhancing the data quality and actively using real-world data for treatment evaluation regarding treatment policies are some of the next steps. Show less
Candel, B.G.J.; Ingen, I.B. van; Doormalen, I.P.H. van; Raven, W.; Mignot-Evers, L.A.A.; Jonge, E. de; Groot, B. de 2021
Purpose To assess how often baseline systolic blood pressure (SBP) could be retrieved from the Electronic Health Record (EHR) in older Emergency Department (ED) patients. Second, to assess whether... Show morePurpose To assess how often baseline systolic blood pressure (SBP) could be retrieved from the Electronic Health Record (EHR) in older Emergency Department (ED) patients. Second, to assess whether the difference between baseline SBP and initial SBP in the ED (Delta SBP) was associated with 30-day mortality. Methods A multicenter hypothesis-generating cohort study including patients >= 70 years. EHRs were searched for baseline SBPs. The association between Delta SBP and 30-day mortality was investigated. Results Baseline SBP was found in 220 out of 300 patients (73.3%; 95%CI 68.1-78.0%). In 72 patients with normal initial SBPs (133-166 mmHg) in the ED, fifteen (20.8%) had a negative Delta SBP with 20.0% mortality. A negative Delta SBP was associated with 30-day mortality (AHR 4.7; 1.7-12.7). Conclusion Baseline SBPs are often available in older ED patients. The Delta SBP has prognostic value and could be used as an extra variable to recognize hypotension in older ED patients. Future studies should clarify whether the Delta SBP improves risk stratification in the ED.Key summary pointsAim To investigate whether a baseline systolic blood pressure (SBP) in older Emergency Department (ED) patients of >= 70 years has prognostic value, when compared with the initial SBP at presentation in the ED (= Delta SBP). Findings A baseline SBP could be retrieved from the Electronic Health Record for most older ED patients (73.3%). A negative Delta SBP was associated with 30-day mortality. In 20% of the patients with a normal initial SBP in the ED, the Delta SBP was negative, with a high mortality rate. Message A baseline SBP value could be retrieved from the Electronic Health Record in most hospitalized ED patients >= 70 years. In addition, the 21% with a normal SBP at ED presentation had a negative Delta SBP and these patients had an increased risk for 30-day mortality. As a result, Delta SBP may contribute to improved risk stratification and may help to recognize hypotension in older patients. Show less
Maarseveen, T.D.; Maurits, M.P.; Niemantsverdriet, E.; Helm-van Mil, A.H.M. van der; Huizinga, T.W.J.; Knevel, R. 2021
Background Electronic health records (EHRs) offer a wealth of observational data. Machine-learning (ML) methods are efficient at data extraction, capable of processing the information-rich free... Show moreBackground Electronic health records (EHRs) offer a wealth of observational data. Machine-learning (ML) methods are efficient at data extraction, capable of processing the information-rich free-text physician notes in EHRs. The clinical diagnosis contained therein represents physician expert opinion and is more consistently recorded than classification criteria components. Objectives To investigate the overlap and differences between rheumatoid arthritis patients as identified either from EHR free-text through the extraction of the rheumatologist diagnosis using machine-learning (ML) or through manual chart-review applying the 1987 and 2010 RA classification criteria. Methods Since EHR initiation, 17,662 patients have visited the Leiden rheumatology outpatient clinic. For ML, we used a support vector machine (SVM) model to identify those who were diagnosed with RA by their rheumatologist. We trained and validated the model on a random selection of 2000 patients, balancing PPV and sensitivity to define a cutoff, and assessed performance on a separate 1000 patients. We then deployed the model on our entire patient selection (including the 3000). Of those, 1127 patients had both a 1987 and 2010 EULAR/ACR criteria status at 1 year after inclusion into the local prospective arthritis cohort. In these 1127 patients, we compared the patient characteristics of RA cases identified with ML and those fulfilling the classification criteria. Results The ML model performed very well in the independent test set (sensitivity=0.85, specificity=0.99, PPV=0.86, NPV=0.99). In our selection of patients with both EHR and classification information, 373 were recognized as RA by ML and 357 and 426 fulfilled the 1987 or 2010 criteria, respectively. Eighty percent of the ML-identified cases fulfilled at least one of the criteria sets. Both demographic and clinical parameters did not differ between the ML extracted cases and those identified with EULAR/ACR classification criteria. Conclusions With ML methods, we enable fast patient extraction from the huge EHR resource. Our ML algorithm accurately identifies patients diagnosed with RA by their rheumatologist. This resulting group of RA patients had a strong overlap with patients identified using the 1987 or 2010 classification criteria and the baseline (disease) characteristics were comparable. ML-assisted case labeling enables high-throughput creation of inclusive patient selections for research purposes. Show less