9 research outputs found
Validity of Major Osteoporotic Fracture Diagnoses in the Danish National Patient Registry
No full textAnne Clausen,1,2 Sören Möller,1,2 Michael Kriegbaum Skjødt,1,3,4 Rasmus Bank Lynggaard,5 Pernille Just Vinholt,5,6 Martin Lindberg-Larsen,7 Jens Søndergaard,8 Bo Abrahamsen,1,4 Katrine Hass Rubin1,2 1Research Unit OPEN, Department of Clinical Research, University of Southern Denmark, Odense, Denmark; 2OPEN - Open Patient Data Explorative Network, Odense University Hospital, Odense, Denmark; 3Department of Medicine, Herlev Hospital, Copenhagen, Denmark; 4Department of Medicine, Holbæk Hospital, Holbæk, Denmark; 5Department of Clinical Biochemistry, Odense University Hospital, Odense, Denmark; 6Department of Clinical Research, University of Southern Denmark, Odense, Denmark; 7Department of Orthopaedic Surgery and Traumatology, Odense University Hospital, Odense, Denmark; 8The Research Unit of General Practice, Department of Public Health, University of Southern Denmark, Odense, DenmarkCorrespondence: Katrine Hass Rubin, Tel +45 21261966, Email [email protected]: To evaluate the validity of diagnosis codes for Major Osteoporotic Fracture (MOF) in the Danish National Patient Registry (NPR) and secondly to evaluate whether the fracture was incident/acute using register-based definitions including date criteria and procedural codes.Methods: We identified a random sample of 2400 records with a diagnosis code for a MOF in the NPR with dates in the year of 2018. Diagnoses were coded with the 10th revision of the International Classification of Diseases (ICD-10). The sample included 2375 unique fracture patients from the Region of Southern Denmark. Medical records were retrieved for the study population and reviewed by an algorithmic search function and medical doctors to verify the MOF diagnoses. Register-based definitions of incident/acute MOF was evaluated in NPR data by applying date criteria and procedural codes.Results: The PPV for MOF diagnoses overall was 0.99 (95% CI: 0.98;0.99) and PPV=0.99 for the four individual fracture sites, respectively. Further, analyses of incident/acute fractures applying date criteria, procedural codes and using patients’ first contact in the NPR resulted in PPV=0.88 (95% CI: 0.84;0.91) for hip fractures, PPV=0.78 (95% CI: 0.74;0.83) for humerus fractures, PPV=0.78 (95% CI: 0.73;0.83) for clinical vertebral fractures and PPV=0.87 (95% CI: 0.83;0.90) for wrist fractures.Conclusion: ICD-10 coded MOF diagnoses are valid in the NPR. Furthermore, a set of register-based criteria can be applied to qualify if the MOF fracture was incident/acute. Thus, the NPR is a valuable and reliable data source for epidemiological research on osteoporotic fractures.Keywords: major osteoporotic fractures, validity, positive predictive value, the Danish National Patient Register, algorithmic search function, epidemiolog
Identification of hematuria with a natural language processing model and validation of hematuria diagnosecodes
No full textDoctors identify hemorrhage better during chart review when assisted by artificial intelligence
No full textObjectives: This study evaluated if medical doctors could identify more hemorrhage events during chart review in a clinical setting when assisted by an artificial intelligence (AI) model, and medical doctors’ perception of using the AI model.Methods: To develop the AI model, sentences from 900 electronic health records were labeled as positive or negative for hemorrhage and categorized into one of twelve anatomical locations. The AI model was evaluated on a test cohort consisting of 566 admissions. Using eye-tracking technology, we investigated medical doctors’ reading workflow during manual chart review. Moreover, we performed a clinical use study where medical doctors read two admissions with and without AI assistance to evaluate performance when, and perception of using the AI model.Results: The AI model had a sensitivity of 93.7% and a specificity of 98.1% on the test cohort. In the use studies, we found that medical doctors missed more than 33% of relevant sentences when doing chart review without AI assistance. Hemorrhage events described in paragraphs were more often overlooked compared to bullet-pointed hemorrhage mentions. With AI assisted chart review, medical doctors identified 48 and 49 percentage points more hemorrhage events than without assistance in two admissions, and they were generally positive towards using the AI model as a supporting tool.Conclusions: Medical doctors identified more hemorrhage events with AI assisted chart review and they were generally positive towards using the AI model
Natural language processing for identifying major bleeding risk in hospitalised medical patients
No full textBackground: Major bleeding is a severe complication in critically ill medical patients, resulting in significant morbidity, mortality, and healthcare costs. This study aims to assess the incidence and risk factors for major bleeding in hospitalised medical patients using a Natural Language Processing (NLP) model. Methods: We conducted a retrospective, cross-sectional observational study using electronic health records of adult patients admitted through the Emergency Department at Odense University Hospital from January 2017 to December 2022. Major bleeding during admission was identified and validated using a natural language model, with events classified according to current guidelines. Risk factors, including demographics, comorbidities, and biochemical values at admission, were evaluated. Two risk assessment models (RAMs) were developed using Cox proportional hazards regression. Validation included, bootstrapping, K-fold cross validation, and cluster analyses. Results: Of the 46,439 eligible patients, 1246 (2.7 %) experienced major bleeding. Risk factors for major bleeding included older age, male sex, alcohol consumption, higher systolic blood pressure, lower haemoglobin, and higher creatinine. RAM 1, which included biochemical data and comorbidities, demonstrated robust predictive performance (Harrell's C-statistic = 0.726). RAM 2, a simplified model without comorbidities, maintained similar predictive accuracy (C-statistic = 0.721), indicating its potential utility in clinical settings with limited resources for detailed patient histories. Results were consistent throughout validation. Conclusion: This study highlights the incidence and risk factors of major bleeding in medical patients, emphasizing the predictive value of routinely measured biochemical markers. Furthermore, it shows the applicability of NLP models in identifying bleeding episodes in EHR text.</p
Validation of anorexia nervosa and Bulimia nervosa diagnosis coding in Danish hospitals assisted by a natural language processing model
No full textIntroduction: The Danish Health Care Registers rely on the International Statistical Classification of Diseases and Related Health Problems (ICD)-classification and stand as a widely utilized resource for health epidemiological research. Eating disorders are multifaceted syndromes where two distinctive diagnoses are defined, anorexia nervosa (AN) and bulimia nervosa (BN). However, the validity of the registered diagnoses remains to be verified. Manuel chart review is often the method for validation of diagnosis codes, but there is limited research on how natural language processing (NLP) models could enhance this process. Objective: To investigate the accuracy of the clinical use of ICD-10 diagnosis codes F50.0, F50.1, F50.2, and F50.3 in the Danish Health Care Registers, using a manual chart review assisted by NLP. Method: From a cohort of all individuals attending hospitals in Region of Southern Denmark with registered electronic health information, we extracted medical information from the electronic health journal on 100 individuals with each of the four diagnosis codes. After extraction, an NLP model with regular expression search patterns identified relevant text passages for manual chart review. Results: Overall, 372 of the 400 diagnosis codes (93%) were correct. A diagnosis code for AN was correct in 90% of instances, 96% for atypical AN, 96% for BN and 90% for an atypical BN diagnosis code. Conclusion: We found that the accuracy of a diagnosis code F50.0, F50.1, F50.2, and F50.3 to be high. This confirms that the generally well-documented validity of the Danish health care registers also applies to the eating disorder diagnoses.</p
Cumulative rib fracture risk after stereotactic body radiotherapy in patients with localized non-small cell lung cancer
No full textINTRODUCTION: Rib fracture is a known complication after stereotactic body radiotherapy (SBRT). Patient-related parameters are essential to provide patient-tailored risk estimation, however, their impact on rib fracture is less documented compared to dosimetric parameters. This study aimed to predict the risk of rib fractures in patients with localized non-small cell lung cancer (NSCLC) post-SBRT based on both patient-related and dosimetric parameters with death as a competing risk.MATERIALS AND METHODS: In total, 602 patients with localized NSCLC treated with SBRT between 2010-2020 at Odense University Hospital, Denmark were included. All patients received SBRT with 45-66 Gray (Gy)/3 fractions. Rib fractures were identified in CT-scans using a word embedding model. The cumulative incidence function was based on cause-specific Cox hazard models with variable selection based on cross-validation model likelihood performed using 50 bootstraps.RESULTS: In total, 19 % of patients experienced a rib fracture. The cumulative risk of rib fracture increased rapidly from 6-54 months post-SBRT. Female gender, bone density, near max dose to the rib, V30 and V40 to the rib, gross tumor volume, and mean lung dose were significantly associated with rib fracture risk in univariable analysis. The final multi-variable model consisted of V20 and V30 to the rib and mean lung dose.CONCLUSION: Female gender and low bone density in male patients are significant predictors of rib fracture risk. The final model predicting cumulative rib fracture risk of 19 % in patients with localized NSCLC treated with SBRT contained no patient-related parameters, suggesting that dosimetric parameters are the primary drivers.</p
Response to commentary on “Cumulative rib fracture risk after stereotactic body radiotherapy in patients with localized non-small cell lung cancer” by Tugcu et al
No full textValidity of Major Osteoporotic Fracture Diagnoses in the Danish National Patient Registry
No full textObjective: To evaluate the validity of diagnosis codes for Major Osteoporotic Fracture (MOF) in the Danish National Patient Registry (NPR) and secondly to evaluate whether the fracture was incident/acute using register-based definitions including date criteria and procedural codes. Methods: We identified a random sample of 2400 records with a diagnosis code for a MOF in the NPR with dates in the year of 2018. Diagnoses were coded with the 10th revision of the International Classification of Diseases (ICD-10). The sample included 2375 unique fracture patients from the Region of Southern Denmark. Medical records were retrieved for the study population and reviewed by an algorithmic search function and medical doctors to verify the MOF diagnoses. Register-based definitions of incident/acute MOF was evaluated in NPR data by applying date criteria and procedural codes. Results: The PPV for MOF diagnoses overall was 0.99 (95% CI: 0.98;0.99) and PPV=0.99 for the four individual fracture sites, respectively. Further, analyses of incident/acute fractures applying date criteria, procedural codes and using patients’ first contact in the NPR resulted in PPV=0.88 (95% CI: 0.84;0.91) for hip fractures, PPV=0.78 (95% CI: 0.74;0.83) for humerus fractures, PPV=0.78 (95% CI: 0.73;0.83) for clinical vertebral fractures and PPV=0.87 (95% CI: 0.83;0.90) for wrist fractures. Conclusion: ICD-10 coded MOF diagnoses are valid in the NPR. Furthermore, a set of register-based criteria can be applied to qualify if the MOF fracture was incident/acute. Thus, the NPR is a valuable and reliable data source for epidemiological research on osteoporotic fractures.</p
Whole-blood culture-derived cytokine combinations for the diagnosis of tuberculosis
No full textIntroduction: The diagnosis of tuberculosis (TB) disease and TB infection (TBI) remains a challenge, and there is a need for non-invasive and blood-based methods to differentiate TB from conditions mimicking TB (CMTB), TBI, and healthy controls (HC). We aimed to determine whether combination of cytokines and established biomarkers could discriminate between 1) TB and CMTB 2) TB and TBI 3) TBI and HC. Methods: We used hemoglobin, total white blood cell count, neutrophils, monocytes, C-reactive protein, and ten Meso Scale Discovery analyzed cytokines (interleukin (IL)-1β, IL-2, IL-4, IL-6, IL-8, IL-10, IL-12p70, IL-13, interferon (IFN)-ɣ, and tumor necrosis factor (TNF)-α) in TruCulture whole blood tubes stimulated by lipopolysaccharides (LPS), zymosan (ZYM), anti-CD3/28 (CD3), and unstimulated (Null) to develop three index tests able to differentiate TB from CMTB and TBI, and TBI from HC. Results: In 52 persons with CMTB (n=9), TB (n=23), TBI (n=10), and HC (n=10), a combination of cytokines (LPS-IFN-ɣ, ZYM-IFN-ɣ, ZYM-TNF-α, ZYM-IL-1β, LPS-IL-4, and ZYM-IL-6) and neutrophil count could differentiate TB from CMTB with a sensitivity of 52.2% (95% CI: 30.9%-73.4%) and a specificity of 100 % (66.4%-100%). Null- IFN-ɣ, Null-IL-8, CD3-IL-6, CD3-IL-8, CD3-IL-13, and ZYM IL-1b discriminated TB from TBI with a sensitivity of 73.9% (56.5% - 91.3%) and a specificity of 100% (69.2-100). Cytokines and established biomarkers failed to differentiate TBI from HC with ≥ 98% specificity. Discussion: Selected cytokines may serve as blood-based add-on tests to detect TB in a low-endemic setting, although these results need to be validated.</p
