Towards global model generalizability: independent cross-site feature evaluation for patient-level risk prediction models using the OHDSI network.

BACKGROUND: Predictive models show promise in healthcare, but their successful deployment is challenging due to limited generalizability. Current external validation often focuses on model performance with restricted feature use from the original training data, lacking insights into their suitability at external sites. Our study introduces an innovative methodology for evaluating features during both the development phase and the validation, focusing on creating and validating predictive models for post-surgery patient outcomes with improved generalizability. METHODS: Electronic health records (EHRs) from 4 countries (United States, United Kingdom, Finland, and Korea) were mapped to the OMOP Common Data Model (CDM), 2008-2019. Machine learning (ML) models were developed to predict post-surgery prolonged opioid use (POU) risks using data collected 6 months before surgery. Both local and cross-site feature selection methods were applied in the development and external validation datasets. Models were developed using Observational Health Data Sciences and Informatics (OHDSI) tools and validated on separate patient cohorts. RESULTS: Model development included 41 929 patients, 14.6% with POU. The external validation included 31 932 (UK), 23 100 (US), 7295 (Korea), and 3934 (Finland) patients with POU of 44.2%, 22.0%, 15.8%, and 21.8%, respectively. The top-performing model, Lasso logistic regression, achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 during local validation and 0.69 (SD = 0.02) (averaged) in external validation. Models trained with cross-site feature selection significantly outperformed those using only features from the development site through external validation (P < .05). CONCLUSIONS: Using EHRs across four countries mapped to the OMOP CDM, we developed generalizable predictive models for POU. Our approach demonstrates the significant impact of cross-site feature selection in improving model performance, underscoring the importance of incorporating diverse feature sets from various clinical settings to enhance the generalizability and utility of predictive healthcare models.

RHEA: Real-World Observational Health Data Exploration Application.

We developed a standardized framework named RHEA to represent longitudinal status of patient with cancer. RHEA generates a dashboard to visualize patients' data in the Observational Medical Outcomes Partnership-Common Data Model format. The generated dashboard consists of three main parts for providing the macroscopic characteristics of the patient: 1) cohort-level visualization, 2) individual-level visualization and 3) cohort generation.

Perioperative adverse cardiac events and mortality after non-cardiac surgery: a multicenter study.

BACKGROUND: Perioperative adverse cardiac events (PACE), a composite of myocardial infarction, coronary revascularization, congestive heart failure, arrhythmic attack, acute pulmonary embolism, cardiac arrest, and stroke during 30-day postoperative period, is associated with long-term mortality, but with limited clinical evidence. We compared long-term mortality with PACE using data from nationwide multicenter electronic health records. METHODS: Data from 7 hospitals, converted to Observational Medical Outcomes Partnership Common Data Model, were used. We extracted records of 277,787 adult patients over 18 years old undergoing non-cardiac surgery for the first time at the hospital and had medical records for more than 180 days before surgery. We performed propensity score matching and then an aggregated meta­analysis. RESULTS: After 1:4 propensity score matching, 7,970 patients with PACE and 28,807 patients without PACE were matched. The meta­analysis showed that PACE was associated with higher one-year mortality risk (hazard ratio [HR]: 1.33, 95% CI [1.10, 1.60], P = 0.005) and higher three-year mortality (HR: 1.18, 95% CI [1.01, 1.38], P = 0.038). In subgroup analysis, the risk of one-year mortality by PACE became greater with higher-risk surgical procedures (HR: 1.20, 95% CI [1.04, 1.39], P = 0.020 for low-risk surgery; HR: 1.69, 95% CI [1.45, 1.96], P < 0.001 for intermediate-risk; and HR: 2.38, 95% CI [1.47, 3.86], P = 0.034 for high-risk). CONCLUSIONS: A nationwide multicenter study showed that PACE was significantly associated with increased one-year mortality. This association was stronger in high-risk surgery, older, male, and chronic kidney disease subgroups. Further studies to improve mortality associated with PACE are needed.

Effect of statin use on head and neck cancer prognosis in a multicenter study using a Common Data Model.

Few studies have found an association between statin use and head and neck cancer (HNC) outcomes. We examined the effect of statin use on HNC recurrence using the converted Observational Medical Outcome Partnership (OMOP) Common Data Model (CDM) in seven hospitals between 1986 and 2022. Among the 9,473,551 eligible patients, we identified 4669 patients with HNC, of whom 398 were included in the target cohort, and 4271 were included in the control cohort after propensity score matching. A Cox proportional regression model was used. Of the 4669 patients included, 398 (8.52%) previously received statin prescriptions. Statin use was associated with a reduced rate of 3- and 5-year HNC recurrence compared to propensity score-matched controls (risk ratio [RR], 0.79; 95% confidence interval [CI], 0.61-1.03; and RR 0.89; 95% CI 0.70-1.12, respectively). Nevertheless, the association between statin use and HNC recurrence was not statistically significant. A meta-analysis of recurrence based on subgroups, including age subgroups, showed similar trends. The results of this propensity-matched cohort study may not provide a statistically significant association between statin use and a lower risk of HNC recurrence. Further retrospective studies using nationwide claims data and prospective studies are warranted.

Ranitidine Use and Incident Cancer in a Multinational Cohort.

Importance: Ranitidine, the most widely used histamine-2 receptor antagonist (H2RA), was withdrawn because of N-nitrosodimethylamine impurity in 2020. Given the worldwide exposure to this drug, the potential risk of cancer development associated with the intake of known carcinogens is an important epidemiological concern. Objective: To examine the comparative risk of cancer associated with the use of ranitidine vs other H2RAs. Design, Setting, and Participants: This new-user active comparator international network cohort study was conducted using 3 health claims and 9 electronic health record databases from the US, the United Kingdom, Germany, Spain, France, South Korea, and Taiwan. Large-scale propensity score (PS) matching was used to minimize confounding of the observed covariates with negative control outcomes. Empirical calibration was performed to account for unobserved confounding. All databases were mapped to a common data model. Database-specific estimates were combined using random-effects meta-analysis. Participants included individuals aged at least 20 years with no history of cancer who used H2RAs for more than 30 days from January 1986 to December 2020, with a 1-year washout period. Data were analyzed from April to September 2021. Exposure: The main exposure was use of ranitidine vs other H2RAs (famotidine, lafutidine, nizatidine, and roxatidine). Main Outcomes and Measures: The primary outcome was incidence of any cancer, except nonmelanoma skin cancer. Secondary outcomes included all cancer except thyroid cancer, 16 cancer subtypes, and all-cause mortality. Results: Among 1 183 999 individuals in 11 databases, 909 168 individuals (mean age, 56.1 years; 507 316 [55.8%] women) were identified as new users of ranitidine, and 274 831 individuals (mean age, 58.0 years; 145 935 [53.1%] women) were identified as new users of other H2RAs. Crude incidence rates of cancer were 14.30 events per 1000 person-years (PYs) in ranitidine users and 15.03 events per 1000 PYs among other H2RA users. After PS matching, cancer risk was similar in ranitidine compared with other H2RA users (incidence, 15.92 events per 1000 PYs vs 15.65 events per 1000 PYs; calibrated meta-analytic hazard ratio, 1.04; 95% CI, 0.97-1.12). No significant associations were found between ranitidine use and any secondary outcomes after calibration. Conclusions and Relevance: In this cohort study, ranitidine use was not associated with an increased risk of cancer compared with the use of other H2RAs. Further research is needed on the long-term association of ranitidine with cancer development.

Efficacy of Co-Medications in Patients with Alcoholic Liver Disease.

BACKGROUND: Alcoholic liver disease (ALD) is still increasing and leads to acute liver injury but also liver cirrhosis and subsequent complications such as liver failure or hepatocellular carcinoma (HCC). As most patients fail to achieve alcohol abstinence, it is essential to identify alternative treatment options in order to improve the outcome of ALD patients. METHODS: Evaluating two large cohorts of patients with ALD from the USA and Korea with a total of 12,006 patients, we investigated the effect on survival of aspirin, metformin, metoprolol, dopamine, and dobutamine drugs in patients with ALD between 2000 and 2020. Patient data were obtained through the "The Observational Health Data Sciences and Informatics consortium," an open-source, multi-stakeholder, and interdisciplinary collaborative effort. RESULTS: The use of aspirin (p = 0.000, p = 0.000), metoprolol (p = 0.002, p = 0.000), and metformin (p = 0.000, p = 0.000) confers a survival benefit for both AUSOM- and NY-treated cohorts. Need of catecholamines dobutamine (p = 0.000, p = 0.000) and dopamine (p = 0.000, p = 0.000) was strongly indicative of poor survival. ß-Blocker treatment with metoprolol (p = 0.128, p = 0.196) or carvedilol (p = 0.520, p = 0.679) was not shown to be protective in any of the female subgroups. CONCLUSION: Overall, our data fill a large gap in long-term, real-world data on patients with ALD, confirming an impact of metformin, acetylsalicylic acid, and ß-blockers on ALD patient's survival. However, gender and ethnic background lead to diverse efficacy in those patients.

Association of 5α-Reductase Inhibitor Prescription With Bladder Cancer Progression in Males in South Korea.

Importance: The antiandrogenic effect of the 5α-reductase inhibitor (5-ARI) has been investigated for its role in preventing male-predominant cancers. Although 5-ARI has been widely associated with prostate cancer, its association with urothelial bladder cancer (BC), another cancer experienced predominantly by males, has been less explored. Objective: To assess the association between 5-ARI prescription prior to BC diagnosis and reduced risk of BC progression. Design, Setting, and Participants: This cohort study analyzed patient claims data from the Korean National Health Insurance Service database. The nationwide cohort included all male patients with BC diagnosis in this database from January 1, 2008, to December 31, 2019. Propensity score matching was conducted to balance the covariates between 2 treatment groups: α-blocker only group and 5-ARI plus α-blocker group. Data were analyzed from April 2021 to March 2023. Exposure: Newly dispensed prescriptions of 5-ARIs at least 12 months prior to cohort entry (BC diagnosis), with a minimum of 2 prescriptions filled. Main Outcomes and Measures: The primary outcomes were the risks of bladder instillation and radical cystectomy, and the secondary outcome was all-cause mortality. To compare the risk of outcomes, the hazard ratio (HR) was estimated using a Cox proportional hazards regression model and difference in restricted mean survival time analysis. Results: The study cohort initially included 22 845 males with BC. After propensity score matching, 5300 patients each were assigned to the α-blocker only group (mean [SD] age, 68.3 [8.8] years) and 5-ARI plus α-blocker group (mean [SD] age, 67.8 [8.6] years). Compared with the α-blocker only group, the 5-ARI plus α-blocker group had a lower risk of mortality (adjusted HR [AHR], 0.83; 95% CI, 0.75-0.91), bladder instillation (crude HR, 0.84; 95% CI, 0.77-0.92), and radical cystectomy (AHR, 0.74; 95% CI, 0.62-0.88). The differences in restricted mean survival time were 92.6 (95% CI, 25.7-159.4) days for all-cause mortality, 88.1 (95% CI, 25.2-150.9) days for bladder instillation, and 68.0 (95% CI, 31.6-104.3) days for radical cystectomy. The incidence rates per 1000 person-years were 85.59 (95% CI, 80.53-90.88) for bladder instillation and 19.57 (95% CI, 17.41-21.91) for radical cystectomy in the α-blocker only group and 66.43 (95% CI, 62.22-70.84) for bladder instillation and 13.56 (95% CI, 11.86-15.45) for radical cystectomy in the 5-ARI plus α-blocker group. Conclusions and relevance: Results of this study suggest an association between prediagnostic prescription of 5-ARI and reduced risk of BC progression.

Machine learning-based prediction model for postoperative delirium in non-cardiac surgery.

BACKGROUND: Postoperative delirium is a common complication that is distressing. This study aimed to demonstrate a prediction model for delirium. METHODS: Among 203,374undergoing non-cardiac surgery between January 2011 and June 2019 at Samsung Medical Center, 2,865 (1.4%) were diagnosed with postoperative delirium. After comparing performances of machine learning algorithms, we chose variables for a prediction model based on an extreme gradient boosting algorithm. Using the top five variables, we generated a prediction model for delirium and conducted an external validation. The Kaplan-Meier and Cox survival analyses were used to analyse the difference of delirium occurrence in patients classified as a prediction model. RESULTS: The top five variables selected for the postoperative delirium prediction model were age, operation duration, physical status classification, male sex, and surgical risk. An optimal probability threshold in this model was estimated to be 0.02. The area under the receiver operating characteristic (AUROC) curve was 0.870 with a 95% confidence interval of 0.855-0.885, and the sensitivity and specificity of the model were 0.76 and 0.84, respectively. In an external validation, the AUROC was 0.867 (0.845-0.877). In the survival analysis, delirium occurred more frequently in the group of patients predicted as delirium using an internal validation dataset (p < 0.001). CONCLUSION: Based on machine learning techniques, we analyzed a prediction model of delirium in patients who underwent non-cardiac surgery. Screening for delirium based on the prediction model could improve postoperative care. The working model is provided online and is available for further verification among other populations. TRIAL REGISTRATION: KCT 0006363.

Prediction Model for 30-Day Mortality after Non-Cardiac Surgery Using Machine-Learning Techniques Based on Preoperative Evaluation of Electronic Medical Records.

BACKGROUND: Machine-learning techniques are useful for creating prediction models in clinical practice. This study aimed to construct a prediction model of postoperative 30-day mortality based on an automatically extracted electronic preoperative evaluation sheet. METHODS: We used data from 276,341 consecutive adult patients who underwent non-cardiac surgery between January 2011 and December 2020 at a tertiary center for model development and internal validation, and another dataset from 63,384 patients between January 2011 and October 2021 at another center for external validation. Postoperative 30-day mortality was 0.16%. We developed an extreme gradient boosting (XGB) prediction model using only variables from preoperative evaluation sheets. RESULTS: The model yielded an area under the curve of 0.960 and an area under the precision and recall curve of 0.216, which were 0.932 and 0.122, respectively, in the external validation set. The optimal threshold calculated by Youden's J statistic had a sensitivity of 0.885 and specificity of 0.914. In an additional analysis with balanced distribution, the model showed a similar predictive value. CONCLUSION: We presented a machine-learning prediction model for 30-day mortality after non-cardiac surgery using preoperative variables automatically extracted from electronic medical records and validated the model in a multi-center setting. Our model may help clinicians predict postoperative outcomes.

Real-world treatment intensities and pathways of macular edema following retinal vein occlusion in Korea from Common Data Model in ophthalmology.

Despite many studies, optimal treatment sequences or intervals are still questionable in retinal vein occlusion (RVO) macular edema. The aim of this study was to examine the real-world treatment patterns of RVO macular edema. A retrospective analysis of the Observational Medical Outcomes Partnership Common Data Model, a distributed research network, of four large tertiary referral centers (n = 9,202,032) identified 3286 eligible. We visualized treatment pathways (prescription volume and treatment sequence) with sunburst and Sankey diagrams. We calculated the average number of intravitreal injections per patient in the first and second years to evaluate the treatment intensities. Bevacizumab was the most popular first-line drug (80.9%), followed by triamcinolone (15.1%) and dexamethasone (2.28%). Triamcinolone was the most popular drug (8.88%), followed by dexamethasone (6.08%) in patients who began treatment with anti-vascular endothelial growth factor (VEGF) agents. The average number of all intravitreal injections per person decreased in the second year compared with the first year. The average number of injections per person in the first year increased throughout the study. Bevacizumab was the most popular first-line drug and steroids were considered the most common as second-line drugs in patients first treated with anti-VEGF agents. Intensive treatment patterns may cause an increase in intravitreal injections.

Cycle-consistent adversarial networks improves generalizability of radiomics model in grading meningiomas on external validation.

The heterogeneity of MRI is one of the major reasons for decreased performance of a radiomics model on external validation, limiting the model's generalizability and clinical application. We aimed to establish a generalizable radiomics model to predict meningioma grade on external validation through leveraging Cycle-Consistent Adversarial Networks (CycleGAN). In this retrospective study, 257 patients with meningioma were included in the institutional training set. Radiomic features (n = 214) were extracted from T2-weighted (T2) and contrast-enhanced T1 (T1C) images. After radiomics feature selection, extreme gradient boosting classifiers were developed. The models were validated in the external validation set consisting of 61 patients with meningiomas. To reduce the gap in generalization associated with the inter-institutional heterogeneity of MRI, the smaller image set style of the external validation was translated into the larger image set style of the institutional training set using CycleGAN. On external validation before CycleGAN application, the performance of the combined T2 and T1C models showed an area under the curve (AUC), accuracy, and F1 score of 0.77 (95% confidence interval 0.63-0.91), 70.7%, and 0.54, respectively. After applying CycleGAN, the performance of the combined T2 and T1C models increased, with an AUC, accuracy, and F1 score of 0.83 (95% confidence interval 0.70-0.97), 73.2%, and 0.59, respectively. Quantitative metrics (by Fréchet Inception Distance) showed that CycleGAN can decrease inter-institutional image heterogeneity while preserving predictive information. In conclusion, leveraging CycleGAN may be helpful to increase the generalizability of a radiomics model in differentiating meningioma grade on external validation.

Renin-Angiotensin-Aldosterone System Inhibitors and Risk of Cancer: A Population-Based Cohort Study Using a Common Data Model.

Studies have reported conflicting results on the association between the use of renin-angiotensin-aldosterone system (RAAS) inhibitors and cancer development. We compared the incidence of cancer between patients using RAAS inhibitors and other antihypertensive drugs. This retrospective observational cohort study used data from seven hospitals in Korea that were converted for use in the Observational Medical Outcomes Partnership Common Data Model. A total of 166,071 patients on antihypertensive therapy across the databases of the seven hospitals were divided into two groups according to the use of RAAS inhibitors. The primary outcome was the occurrence of cancer. A total of 166,071 patients across the databases of the seven hospitals was included in the final analysis; 26,650 (16%) were in the RAAS inhibitors group and 139,421 (84%) in the other antihypertensive drugs group. The meta-analysis of the whole cohort showed a lower incidence of cancer occurrence in the RAAS inhibitor group (9.90 vs. 13.28 per 1000 person years; HR, 0.81; 95% confidence interval [CI], 0.75-0.88). After propensity-score matching, the RAAS inhibitor group consistently showed a lower incidence of cancer (9.90 vs. 13.28 per 1000 person years; HR, 0.86; 95% CI, 0.81-0.91). The patients using RAAS inhibitors showed a lower incidence of cancer compared with those using other antihypertensive drugs. These findings support the association between the use of RAAS inhibitors and cancer occurrence.

Seek COVER: using a disease proxy to rapidly develop and validate a personalized risk calculator for COVID-19 outcomes in an international network.

BACKGROUND: We investigated whether we could use influenza data to develop prediction models for COVID-19 to increase the speed at which prediction models can reliably be developed and validated early in a pandemic. We developed COVID-19 Estimated Risk (COVER) scores that quantify a patient's risk of hospital admission with pneumonia (COVER-H), hospitalization with pneumonia requiring intensive services or death (COVER-I), or fatality (COVER-F) in the 30-days following COVID-19 diagnosis using historical data from patients with influenza or flu-like symptoms and tested this in COVID-19 patients. METHODS: We analyzed a federated network of electronic medical records and administrative claims data from 14 data sources and 6 countries containing data collected on or before 4/27/2020. We used a 2-step process to develop 3 scores using historical data from patients with influenza or flu-like symptoms any time prior to 2020. The first step was to create a data-driven model using LASSO regularized logistic regression, the covariates of which were used to develop aggregate covariates for the second step where the COVER scores were developed using a smaller set of features. These 3 COVER scores were then externally validated on patients with 1) influenza or flu-like symptoms and 2) confirmed or suspected COVID-19 diagnosis across 5 databases from South Korea, Spain, and the United States. Outcomes included i) hospitalization with pneumonia, ii) hospitalization with pneumonia requiring intensive services or death, and iii) death in the 30 days after index date. RESULTS: Overall, 44,507 COVID-19 patients were included for model validation. We identified 7 predictors (history of cancer, chronic obstructive pulmonary disease, diabetes, heart disease, hypertension, hyperlipidemia, kidney disease) which combined with age and sex discriminated which patients would experience any of our three outcomes. The models achieved good performance in influenza and COVID-19 cohorts. For COVID-19 the AUC ranges were, COVER-H: 0.69-0.81, COVER-I: 0.73-0.91, and COVER-F: 0.72-0.90. Calibration varied across the validations with some of the COVID-19 validations being less well calibrated than the influenza validations. CONCLUSIONS: This research demonstrated the utility of using a proxy disease to develop a prediction model. The 3 COVER models with 9-predictors that were developed using influenza data perform well for COVID-19 patients for predicting hospitalization, intensive services, and fatality. The scores showed good discriminatory performance which transferred well to the COVID-19 population. There was some miscalibration in the COVID-19 validations, which is potentially due to the difference in symptom severity between the two diseases. A possible solution for this is to recalibrate the models in each location before use.

Machine Learning Approach Using Routine Immediate Postoperative Laboratory Values for Predicting Postoperative Mortality.

BACKGROUND: Several prediction models have been proposed for preoperative risk stratification for mortality. However, few studies have investigated postoperative risk factors, which have a significant influence on survival after surgery. This study aimed to develop prediction models using routine immediate postoperative laboratory values for predicting postoperative mortality. METHODS: Two tertiary hospital databases were used in this research: one for model development and another for external validation of the resulting models. The following algorithms were utilized for model development: LASSO logistic regression, random forest, deep neural network, and XGBoost. We built the models on the lab values from immediate postoperative blood tests and compared them with the SASA scoring system to demonstrate their efficacy. RESULTS: There were 3817 patients who had immediate postoperative blood test values. All models trained on immediate postoperative lab values outperformed the SASA model. Furthermore, the developed random forest model had the best AUROC of 0.82 and AUPRC of 0.13, and the phosphorus level contributed the most to the random forest model. CONCLUSIONS: Machine learning models trained on routine immediate postoperative laboratory values outperformed previously published approaches in predicting 30-day postoperative mortality, indicating that they may be beneficial in identifying patients at increased risk of postoperative death.

Real-world incidence of endopthalmitis after intravitreal anti-VEGF injections in Korea: findings from the Common Data Model in ophthalmology.

OBJECTIVES: The aim of this study was to evaluate the real-world incidence of endophthalmitis after intravitreal anti-vascular endothelial growth factor (VEGF) injections using data from the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). METHODS: Patients with endophthalmitis that developed within 6 weeks after intravitreal anti-VEGF injections were identified in 3 large OMOP CDM databases. RESULTS: We identified 23,490 patients who received 128,123 intravitreal anti-VEGF injections. The incidence rates of endophthalmitis were 15.75 per 10,000 patients and 2.97 per 10,000 injections. The incidence rates of endophthalmitis for bevacizumab, ranibizumab, and aflibercept (per 10,000 injections) were 3.64, 1.39, and 0.76, respectively. The annual incidence has remained below 5.00 per 10,000 injections since 2011 despite the increasing number of intravitreal anti-VEGF injections. Bevacizumab presented a higher incidence rate for endophthalmitis than ranibizumab and aflibercept (incidence rate ratio, 3.17; p=0.021). CONCLUSIONS: The incidence of endophthalmitis after intravitreal anti-VEGF injections has stabilized since 2011 despite the explosive increase in anti-VEGF injections. The off-label use of bevacizumab accounted for its disproportionately high incidence of endophthalmitis. The OMOP CDM, which includes off-label uses, laboratory data, and a scalable standardized database, could provide a novel strategy to reveal real-world evidence, especially in ophthalmology.

Predictability of Mortality in Patients With Myocardial Injury After Noncardiac Surgery Based on Perioperative Factors via Machine Learning: Retrospective Study.

BACKGROUND: Myocardial injury after noncardiac surgery (MINS) is associated with increased postoperative mortality, but the relevant perioperative factors that contribute to the mortality of patients with MINS have not been fully evaluated. OBJECTIVE: To establish a comprehensive body of knowledge relating to patients with MINS, we researched the best performing predictive model based on machine learning algorithms. METHODS: Using clinical data from 7629 patients with MINS from the clinical data warehouse, we evaluated 8 machine learning algorithms for accuracy, precision, recall, F1 score, area under the receiver operating characteristic (AUROC) curve, and area under the precision-recall curve to investigate the best model for predicting mortality. Feature importance and Shapley Additive Explanations values were analyzed to explain the role of each clinical factor in patients with MINS. RESULTS: Extreme gradient boosting outperformed the other models. The model showed an AUROC of 0.923 (95% CI 0.916-0.930). The AUROC of the model did not decrease in the test data set (0.894, 95% CI 0.86-0.922; P=.06). Antiplatelet drugs prescription, elevated C-reactive protein level, and beta blocker prescription were associated with reduced 30-day mortality. CONCLUSIONS: Predicting the mortality of patients with MINS was shown to be feasible using machine learning. By analyzing the impact of predictors, markers that should be cautiously monitored by clinicians may be identified.

Angiotensin converting enzyme inhibitors and incidence of lung cancer in a population based cohort of common data model in Korea.

Contradictory findings exist about association of angiotensin-converting enzyme inhibitor (ACEi) and angiotensin receptor blocker (ARB) with lung cancer development. This was a retrospective observational cohort study that used data from 7 hospitals in Korea, converted to the Observational Medical Outcomes Partnership Common Data Model. The primary outcome was occurrence of lung cancer. A total of 207,794 patients across the 7 databases was included in the final analysis; 33,230 (16%) were prescribed ACEi and 174,564 (84%) were prescribed ARB. Crude analysis adjusted for sex and age showed higher incidence of lung cancer in the ACEi group compared to the ARB group (hazard ratio [HR], 1.46; 95% confidence rate [CI], 1.08-1.97). After propensity-score matching, 30,445 pairs were generated, and there was no difference in incidence of lung cancer between the two groups (HR, 0.93; 95% CI, 0.64-1.35). Patients prescribed ACEi showed no difference in incidence of lung cancer development compared to those using ARB. This finding provides evidence on the association between ACEi and occurrence of lung cancer.

A Framework (SOCRATex) for Hierarchical Annotation of Unstructured Electronic Health Records and Integration Into a Standardized Medical Database: Development and Usability Study.

BACKGROUND: Although electronic health records (EHRs) have been widely used in secondary assessments, clinical documents are relatively less utilized owing to the lack of standardized clinical text frameworks across different institutions. OBJECTIVE: This study aimed to develop a framework for processing unstructured clinical documents of EHRs and integration with standardized structured data. METHODS: We developed a framework known as Staged Optimization of Curation, Regularization, and Annotation of clinical text (SOCRATex). SOCRATex has the following four aspects: (1) extracting clinical notes for the target population and preprocessing the data, (2) defining the annotation schema with a hierarchical structure, (3) performing document-level hierarchical annotation using the annotation schema, and (4) indexing annotations for a search engine system. To test the usability of the proposed framework, proof-of-concept studies were performed on EHRs. We defined three distinctive patient groups and extracted their clinical documents (ie, pathology reports, radiology reports, and admission notes). The documents were annotated and integrated into the Observational Medical Outcomes Partnership (OMOP)-common data model (CDM) database. The annotations were used for creating Cox proportional hazard models with different settings of clinical analyses to measure (1) all-cause mortality, (2) thyroid cancer recurrence, and (3) 30-day hospital readmission. RESULTS: Overall, 1055 clinical documents of 953 patients were extracted and annotated using the defined annotation schemas. The generated annotations were indexed into an unstructured textual data repository. Using the annotations of pathology reports, we identified that node metastasis and lymphovascular tumor invasion were associated with all-cause mortality among colon and rectum cancer patients (both P=.02). The other analyses involving measuring thyroid cancer recurrence using radiology reports and 30-day hospital readmission using admission notes in depressive disorder patients also showed results consistent with previous findings. CONCLUSIONS: We propose a framework for hierarchical annotation of textual data and integration into a standardized OMOP-CDM medical database. The proof-of-concept studies demonstrated that our framework can effectively process and integrate diverse clinical documents with standardized structured data for clinical research.

Characterizing the Anticancer Treatment Trajectory and Pattern in Patients Receiving Chemotherapy for Cancer Using Harmonized Observational Databases: Retrospective Study.

BACKGROUND: Accurate and rapid clinical decisions based on real-world evidence are essential for patients with cancer. However, the complexity of chemotherapy regimens for cancer impedes retrospective research that uses observational health databases. OBJECTIVE: The aim of this study is to compare the anticancer treatment trajectories and patterns of clinical events according to regimen type using the chemotherapy episodes determined by an algorithm. METHODS: We developed an algorithm to extract the regimen-level abstracted chemotherapy episodes from medication records in a conventional Observational Medical Outcomes Partnership (OMOP) common data model (CDM) database. The algorithm was validated on the Ajou University School Of Medicine (AUSOM) database by manual review of clinical notes. Using the algorithm, we extracted episodes of chemotherapy from patients in the EHR database and the claims database. We also developed an application software for visualizing the chemotherapy treatment patterns based on the treatment episodes in the OMOP-CDM database. Using this software, we generated the trends in the types of regimen used in the institutions, the patterns of the iterative chemotherapy use, and the trajectories of cancer treatment in two EHR-based OMOP-CDM databases. As a pilot study, the time of onset of chemotherapy-induced neutropenia according to regimen was measured using the AUSOM database. The anticancer treatment trajectories for patients with COVID-19 were also visualized based on the nationwide claims database. RESULTS: We generated 178,360 treatment episodes for patients with colorectal, breast, and lung cancer for 85 different regimens. The algorithm precisely identified the type of chemotherapy regimen in 400 patients (average positive predictive value >98%). The trends in the use of routine clinical chemotherapy regimens from 2008-2018 were identified for 8236 patients. For a total of 12 regimens (those administered to the largest proportion of patients), the number of repeated treatments was concordant with the protocols for standard chemotherapy regimens for certain cases. In addition, the anticancer treatment trajectories for 8315 patients were shown, including 62 patients with COVID-19. A comparative analysis of neutropenia showed that its onset in colorectal cancer regimens tended to cluster between days 9-15, whereas it tended to cluster between days 2-8 for certain regimens for breast cancer or lung cancer. CONCLUSIONS: We propose a method for generating chemotherapy episodes for introduction into the oncology extension module of the OMOP-CDM databases. These proof-of-concept studies demonstrated the usability, scalability, and interoperability of the proposed framework through a distributed research network.