90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model

Data-Driven Approach to Development of a Risk Score for Periprosthetic Joint Infections in Total Joint Arthroplasty Using Electronic Health Records

BACKGROUND

Periprosthetic joint infection (PJI) is an uncommon, but serious complication in total joint arthroplasty. Personalized risk prediction and risk factor management may allow better preoperative assessment and improved outcomes. We evaluated different data-driven approaches to develop surgery-specific PJI prediction models using large-scale data from the electronic health records (EHRs).

METHODS

A large institutional arthroplasty registry was leveraged to collect data from 58,574 procedures of 41,844 patients who underwent at least one primary and/or revision hip and/or knee arthroplasty between 2000 and 2019. The registry dataset was augmented with additional clinical, procedural, and laboratory data from the EHRs for more than 100 potential predictor variables. The main outcome was PJI within the first year after surgery. We implemented both traditional and machine learning methods for model development (lasso regression, relaxed lasso regression, ridge regression, random forest, stepwise regression, extreme gradient boosting, neural network) and used 10-fold cross-validation to calculate measures of model performance in terms of discrimination (c-statistic) and calibration.

RESULTS

All models discriminated similarly in predicting PJI risk, with negligible differences of less than 0.08 between the best- and worst-performing models. The relaxed and fully relaxed lasso models using the Cox model structure outperformed the other models with concordances of 0.787 in primary hip arthroplasty and 0.722 in revision hip arthroplasty, with the number of predictors ranging from nine to 41. The concordances with the relaxed lasso models were 0.681 in primary and 0.699 in revision knee arthroplasty, with a higher number of predictors in the models. Predictors included in the models varied substantially across the four surgical groups.

CONCLUSIONS

The incorporation of additional data from the EHRs offers limited improvement in PJI risk stratification. Furthermore, improvement in PJI risk prediction was modest with the machine learning approaches and may not justify the added complexity.

Predictive analysis of economic and clinical outcomes in total knee arthroplasty: Identifying high-risk patients for increased costs and length of stay

PURPOSE

The purpose of this study was to predict high-risk patients who experience significant increases in hospital charges and length of stay (LOS) following specific postoperative complications.

METHODS

This study analyzed over two million patients from the Nationwide Inpatient Sample database undergoing elective total knee arthroplasty (TKA) for primary osteoarthritis. Baseline demographics, clinical characteristics and incidence of postoperative complications were examined. A neural network model was utilized to predict high-risk patients who fall into the top 25% for both LOS and total hospital charges after complications such as sepsis or surgical site infection (SSI).

RESULTS

The most common complications were blood loss anaemia (14.6%), acute kidney injury (1.6%) and urinary tract infection (0.9%). Patients with complications incurred significantly higher total charges (mean $66,804) and longer LOS (mean 2.9 days) compared to those without complications (mean $58,545 and 2.1 days, respectively). The neural network model demonstrated strong predictive performance, with an area under the curve of 0.83 for the training set and 0.78 for the testing set. Key complications like sepsis and SSIs significantly impacted hospital charges and LOS. For example, a 57-year-old patient with diabetes and sepsis had a 100% probability of being in the top 25% for both total charges and LOS.

CONCLUSION

Postoperative complications in TKA patients significantly increase hospital charges and LOS. The neural network model effectively predicted high-risk patients after specific complications occurred, offering a potential tool for improving patient management and resource allocation.

LEVELS OF EVIDENCE

Level III.

Observational Health Data Science and Informatics and Hand Surgery Research: Past, Present, and Future

Single center studies are limited by bias, lack of generalizability and variability, and inability to study rare conditions. Multicenter observational research could address many of those concerns, especially in hand surgery where multicenter research is currently quite limited; however, there are numerous barriers including regulatory issues, lack of common terminology, and variable data set structures. The Observational Health Data Sciences and Informatics (OHDSI) program aims to surmount these limitations by enabling large-scale, collaborative research across multiple institutions. The OHDSI uses the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) to standardize health care data into a common language, enabling consistent and reliable analysis. The OMOP CDM has been transformative in converting multiple databases into a standardized code with a single vocabulary, allowing for coherent analysis across multiple data sets. Building upon the OMOP CDM, OHDSI provides an extensive suite of open-source tools for all research stages, from data extraction to statistical modeling. By keeping sensitive data local and only sharing summary statistics, OHDSI ensures compliance with privacy regulations while allowing for large-scale analyses. For hand surgery, OHDSI can enhance research depth, understanding of outcomes, risk factors, complications, and device performance, ultimately leading to better patient care.

Repeatable process for extracting health data from HL7 CDA documents

OBJECTIVE

This study aims to address the gap in the literature on converting real-world Clinical Document Architecture (CDA) data into the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), focusing on the initial steps preceding the mapping phase. We highlight the importance of a repeatable Extract-Transform-Load (ETL) pipeline for health data extraction from HL7 CDA documents in Estonia for research purposes.

METHODS

We developed a repeatable ETL pipeline to facilitate the extraction, cleaning, and restructuring of health data from CDA documents to OMOP CDM, ensuring a high-quality and structured data format. This pipeline was designed to adapt to continuously updated data exchange format changes and handle various CDA document subsets for different scientific studies.

RESULTS

We demonstrated via selected use cases that our pipeline successfully transformed a significant portion of diagnosis codes, body weight and eGFR measurements, and PAP test results from CDA documents into OMOP CDM, showing the ease of extracting structured data. However, challenges such as harmonising diverse coding systems and extracting lab results from free-text sections were encountered. The iterative development of the pipeline facilitated swift error detection and correction, enhancing the process's efficiency.

CONCLUSION

After a decade of focused work, our research has led to the development of an ETL pipeline that effectively transforms HL7 CDA documents into OMOP CDM in Estonia, addressing key data extraction and transformation challenges. The pipeline's repeatability and adaptability to various data subsets make it a valuable resource for researchers dealing with health data. While tested on Estonian data, the principles outlined are broadly applicable, potentially aiding in handling health data standards that vary by country. Despite newer health data standards emerging, the relevance of CDA for retrospective health studies ensures the continuing importance of this work.

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.

Prediction of 30-day, 90-day, and 1-year mortality after colorectal cancer surgery using a data-driven approach

PURPOSE

To develop prediction models for short-term mortality risk assessment following colorectal cancer surgery.

METHODS

Data was harmonized from four Danish observational health databases into the Observational Medical Outcomes Partnership Common Data Model. With a data-driven approach using the Least Absolute Shrinkage and Selection Operator logistic regression on preoperative data, we developed 30-day, 90-day, and 1-year mortality prediction models. We assessed discriminative performance using the area under the receiver operating characteristic and precision-recall curve and calibration using calibration slope, intercept, and calibration-in-the-large. We additionally assessed model performance in subgroups of curative, palliative, elective, and emergency surgery.

RESULTS

A total of 57,521 patients were included in the study population, 51.1% male and with a median age of 72 years. The model showed good discrimination with an area under the receiver operating characteristic curve of 0.88, 0.878, and 0.861 for 30-day, 90-day, and 1-year mortality, respectively, and a calibration-in-the-large of 1.01, 0.99, and 0.99. The overall incidence of mortality were 4.48% for 30-day mortality, 6.64% for 90-day mortality, and 12.8% for 1-year mortality, respectively. Subgroup analysis showed no improvement of discrimination or calibration when separating the cohort into cohorts of elective surgery, emergency surgery, curative surgery, and palliative surgery.

CONCLUSION

We were able to train prediction models for the risk of short-term mortality on a data set of four combined national health databases with good discrimination and calibration. We found that one cohort including all operated patients resulted in better performing models than cohorts based on several subgroups.

Objective assessment of physician work in infrainguinal arterial bypass surgery

OBJECTIVE

The purpose of this study is obtain robust objective data from the Vascular Quality Initiative on physician work in infrainguinal artery bypass surgery. Operative time, patient comorbidities, anatomical complexity, consequences of adverse outcomes, and postoperative length of stay all factor into procedure relative value unit assignment and physician reimbursement.

METHODS

Baseline demographics and comorbidities were identified among 74,920 infrainguinal bypass surgeries in Vascular Quality Initiative between 2003 and 2022. Investigation into areas of progressive complexity over time was conducted. Bypasses were divided into 10 cohorts based on inflow and target arteries and conduit type. Mean operative times, lengths of stay, major morbidity rates, and 90-day mortality rates were identified across the various bypasses. Comparison of relative value unit per minute service time during the acute inpatient hospital admission was performed between the most 4 common bypasses and 14 commonly performed highly invasive major surgeries across several subdisciplines.

RESULTS

Patients undergoing infrainguinal arterial bypass have an advanced combination of medical complexities highlighted by diabetes mellitus in 40%, hypertension in 88%, body mass index >30 in 30%, coronary artery disease that has clinically manifested in 31%, renal insufficiency in 19%, chronic obstructive pulmonary disease in 27%, and prior lower extremity arterial intervention (endovascular and open combined) in >50%. The need for concomitant endarterectomy at the proximal anastomosis site of infrainguinal bypasses has increased over time (P < .001). The indication for bypass being limb-threatening ischemia as defined by ischemic rest pain, pedal tissue loss, or acute ischemia has also increased over time (P < .001), indicating more advanced extent of arterial occlusion in patients undergoing infrainguinal bypass. Finally, there has been a significant (P < .001) progression in the percentage of patients who have undergone a prior ipsilateral lower extremity endovascular intervention at the time of their bypass (increasing from 9.9% in 2003-2010 to 31.9% in the 2018-2022 eras). Among the 18 procedures investigated, the 4 most commonly performed infrainguinal bypasses were included in the analysis. These ranked 14th, 16th, 17th and 18th as the most poorly compensated per minute service time during the acute operative inpatient stay.

CONCLUSIONS

Infrainguinal arterial bypass surgery has an objectively undervalued physician work relative value unit compared with other highly invasive major surgeries across several subdisciplines. There are elements of progressive complexity in infrainguinal bypass patients over the past 20 years among a patient cohort with a very high comorbidity rate, indicating escalating intensity for infrainguinal bypass.

Evaluating a novel approach to stimulate open science collaborations: a case series of "study-a-thon" events within the OHDSI and European IMI communities

Objective

We introduce and review the concept of a study-a-thon as a catalyst for open science in medicine, utilizing harmonized real world, observation health data, tools, skills, and methods to conduct network studies, generating insights for those wishing to use study-a-thons for future research.

Materials and Methods

A series of historical study-a-thons since 2017 to present were reviewed for thematic insights as to the opportunity to accelerate the research method to conduct studies across therapeutic areas. Review of publications and experience of the authors generated insights to illustrate the conduct of study-a-thons, key learning, and direction for those wishing to conduct future such study-a-thons.

Results

A review of six study-a-thons have provided insights into their scientific impact, and 13 areas of insights for those wishing to conduct future study-a-thons. Defining aspects of the study-a-thon method for rapid, collaborative research through network studies reinforce the need to clear scientific rationale, tools, skills, and methods being collaboratively to conduct a focused study. Well-characterized preparatory, execution and postevent phases, coalescing skills, experience, data, clinical input (ensuring representative clinical context to the research query), and well-defined, logical steps in conducting research via the study-a-thon method are critical.

Conclusions

A study-a-thon is a focused multiday research event generating reliable evidence on a specific medical topic across different countries and health systems. In a study-a-thon, a multidisciplinary team collaborate to create an accelerated contribution to scientific evidence and clinical practice. It critically accelerates the research process, without inhibiting the quality of the research output and evidence generation, through a reproducible process.