Dataset Information

The added value of text from Dutch general practitioner notes in predictive modeling.

ABSTRACT:

Objective

This work aims to explore the value of Dutch unstructured data, in combination with structured data, for the development of prognostic prediction models in a general practitioner (GP) setting.

Materials and methods

We trained and validated prediction models for 4 common clinical prediction problems using various sparse text representations, common prediction algorithms, and observational GP electronic health record (EHR) data. We trained and validated 84 models internally and externally on data from different EHR systems.

Results

On average, over all the different text representations and prediction algorithms, models only using text data performed better or similar to models using structured data alone in 2 prediction tasks. Additionally, in these 2 tasks, the combination of structured and text data outperformed models using structured or text data alone. No large performance differences were found between the different text representations and prediction algorithms.

Discussion

Our findings indicate that the use of unstructured data alone can result in well-performing prediction models for some clinical prediction problems. Furthermore, the performance improvement achieved by combining structured and text data highlights the added value. Additionally, we demonstrate the significance of clinical natural language processing research in languages other than English and the possibility of validating text-based prediction models across various EHR systems.

Conclusion

Our study highlights the potential benefits of incorporating unstructured data in clinical prediction models in a GP setting. Although the added value of unstructured data may vary depending on the specific prediction task, our findings suggest that it has the potential to enhance patient care.

SUBMITTER: Seinen TM

PROVIDER: S-EPMC10654855 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The added value of text from Dutch general practitioner notes in predictive modeling.

Seinen Tom M TM Kors Jan A JA van Mulligen Erik M EM Fridgeirsson Egill E Rijnbeek Peter R PR

Journal of the American Medical Informatics Association : JAMIA 20231101 12

<h4>Objective</h4>This work aims to explore the value of Dutch unstructured data, in combination with structured data, for the development of prognostic prediction models in a general practitioner (GP) setting.<h4>Materials and methods</h4>We trained and validated prediction models for 4 common clinical prediction problems using various sparse text representations, common prediction algorithms, and observational GP electronic health record (EHR) data. We trained and validated 84 models internall ...[more]

PMID: 37587084

Similar Datasets

Project description:BackgroundPhysician notes routinely recorded during patient care represent a vast and underutilized resource for human disease studies on a population scale. Their use in research is primarily limited by the need to separate confidential patient information from clinical annotations, a process that is resource-intensive when performed manually. This study seeks to create an automated method for de-identifying physician notes that does not require large amounts of private information: in addition to training a model to recognize Protected Health Information (PHI) within private physician notes, we reverse the problem and train a model to recognize non-PHI words and phrases that appear in public medical texts.MethodsPublic and private medical text sources were analyzed to distinguish common medical words and phrases from Protected Health Information. Patient identifiers are generally nouns and numbers that appear infrequently in medical literature. To quantify this relationship, term frequencies and part of speech tags were compared between journal publications and physician notes. Standard medical concepts and phrases were then examined across ten medical dictionaries. Lists and rules were included from the US census database and previously published studies. In total, 28 features were used to train decision tree classifiers.ResultsThe model successfully recalled 98% of PHI tokens from 220 discharge summaries. Cost sensitive classification was used to weight recall over precision (98% F10 score, 76% F1 score). More than half of the false negatives were the word "of" appearing in a hospital name. All patient names, phone numbers, and home addresses were at least partially redacted. Medical concepts such as "elevated white blood cell count" were informative for de-identification. The results exceed the previously approved criteria established by four Institutional Review Boards.ConclusionsThe results indicate that distributional differences between private and public medical text can be used to accurately classify PHI. The data and algorithms reported here are made freely available for evaluation and improvement.

Project description:BackgroundEmergency medical services (EMS) personnel must rapidly assess and transport patients with time-sensitive conditions to optimise patient outcomes. Serum lactate, a valuable in-hospital biomarker, has become more accessible in EMS settings through point-of-care (POC) testing. Although POC lactate levels are valuable in specific patient groups, its broader application in EMS remains unclear. This study assessed the additional predictive value of POC lactate levels in a general adult EMS population.MethodsThis prospective observational study (March 2018 to September 2019) involved two EMS organisations in Västra Götaland, Sweden. Patients were triaged using the Rapid Triage and Treatment System (RETTS). POC lactate levels were measured using StatStrip Xpress devices. Non-consecutive patients who received EMS and were aged 18 years and above were available for inclusion if triaged into RETTS levels: red, orange, yellow, or green if respiratory rate of ≥ 22 breaths/min. Outcomes were adverse outcomes, including a time-sensitive diagnosis, sequential organ failure assessment (SOFA) score ≥ 2, and 30-day mortality. Statistical analyses included descriptive statistics, imputation, and regression models to assess the impact of the addition of POC lactate levels to a base model (comprising patient age, sex, presence of past medical conditions, vital signs, pain, EMS response time, assessed triage condition, and triage level) and a RETTS triage model.ResultsOf 4,546 patients (median age 75 [57, 84] years; 49% male), 32.4% had time-sensitive conditions, 12.5% met the SOFA criteria, and 7.4% experienced 30-day mortality. The median POC lactate level was 1.7 (1.2, 2.5) mmol/L. Patients with time-sensitive conditions had higher lactate levels (1.9 mmol/L) than those with non-time-sensitive conditions (1.6 mmol/L). The probability of a time-sensitive condition increased with increasing lactate level. The addition of POC lactate marginally enhanced the predictive models, with a 1.5% and 4% increase for the base and RETTS triage models, respectively. POC lactate level as a sole predictor showed chance-only level predictive performance.ConclusionsPrehospital POC lactate assessment provided limited additional predictive value in a general adult EMS population. However, it may be beneficial in specific patient subgroups, emphasizing the need for its judicious use in prehospital settings.

Project description:Background: Lipidomics is emerging for biomarker discovery in cardiovascular disease, and circulating lipids are increasingly incorporated in risk models to predict cardiovascular events. Moreover, specific classes of lipids, such as sphingomyelins, ceramides, and triglycerides, have been related to coronary artery disease (CAD) severity and plaque characteristics. To avoid unnecessary testing, it is important to identify individuals at low CAD risk. The only pretest model available so far to rule out the presence of coronary atherosclerosis in patients with chest pain, but normal coronary arteries, is the minimal risk tool (MRT). Aim: Using state-of-the-art statistical methods, we aim to verify the additive predictive value of a set of lipids, derived from targeted plasma lipidomics of suspected CAD patients, to a re-estimated version of the MRT for ruling out the presence of coronary atherosclerosis assessed by coronary CT angiography (CCTA). Methods: Two hundred and fifty-six subjects with suspected stable CAD recruited from five European countries within H2020-SMARTool, undergoing CCTA and blood sampling for clinical biochemistry and lipidomics, were selected. The MRT was validated by regression methods and then re-estimated (reMRT). The reMRT was used as a baseline model in a likelihood ratio test approach to assess the added predictive value of each lipid from 13 among ceramides, triglycerides, and sphingomyelins. Except for one lipid, the analysis was carried out on more than 240 subjects for each lipid. A sensitivity analysis was carried out by considering two alternative models developed on the cohort as baseline models. Results: In 205 subjects, coronary atherosclerosis ranged from minimal lesions to overt obstructive CAD, while in 51 subjects (19.9%) the coronary arteries were intact. Four triglycerides and seven sphingomyelins were significantly (p < 0.05) and differentially expressed in the two groups and, at a lesser extent, one ceramide (p = 0.067). The probability of being at minimal risk was significantly better estimated by adding either Cer(d18:1/16:0) (p = 0.01), SM(40:2) (p = 0.04), or SM(41:1) at a lesser extent (p = 0.052) to reMRT than by applying the reMRT alone. The sensitivity analysis confirmed the relevance of these lipids. Furthermore, the addition of SM(34:1), SM(38:2), SM(41:2), and SM(42:4) improved the predictive performance of at least one of the other baseline models. None of the selected triglycerides was found to provide an added value. Conclusions: Plasma lipidomics can be a promising source of diagnostic and prognostic biomarkers in cardiovascular disease, exploitable not only to assess the risk of adverse events but also to identify subjects without coronary atherosclerosis, thus reducing unnecessary further testing in normal subjects.

Project description:ObjectivesChronic gastrointestinal symptoms are common among children and affect their daily activities and quality of life. The majority will be diagnosed with a functional gastrointestinal disorder. Effective reassurance and education are, therefore, key components of the physician's management. Qualitative studies have shown how parents and children experience specialist paediatric care, yet less is known about general practitioners (GPs), who manage most cases in the Netherlands and have a more personal and enduring relationship with their patients. Therefore, this study evaluates the expectations and experiences of parents of children visiting a GP for chronic gastrointestinal symptoms.DesignWe conducted a qualitative interview study. Online interviews were audio and video recorded, transcribed verbatim and independently analysed by the first two authors. Data were collected and analysed concurrently until data saturation was reached. Using thematic analysis, we developed a conceptual framework reflecting respondent expectations and experiences. We performed a member check of the interview synopsis and the conceptual framework.SettingDutch primary care.ParticipantsWe purposively sampled participants from a randomised controlled trial evaluating the effectiveness of faecal calprotectin testing in children with chronic gastrointestinal complaints in primary care. Thirteen parents and two children participated.ResultsThree key themes emerged: disease burden, GP-patient relationship and reassurance. Often, the experienced disease burden and the pre-existing GP-patient relationship influenced expectations (eg, for further investigations or a sympathetic ear), and when a GP fulfilled these expectations, a trusting GP-patient relationship ensued that facilitated reassurance. We found that individual needs influenced these themes and their interrelationships.ConclusionInsights provided by this framework could help GPs managing children with chronic gastrointestinal symptoms in daily practice and may therewith improve the consultation experience for parents. Further research should evaluate whether this framework also holds true for children.Trial registration numberNL7690.

Dataset Information

The added value of text from Dutch general practitioner notes in predictive modeling.

Objective

Materials and methods

Results

Discussion

Conclusion

Publications

The added value of text from Dutch general practitioner notes in predictive modeling.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets