Neurosurgery clinical registry data collection utilizing Informatics for Integrating Biology and the Bedside and electronic health records at the University of Rochester

Leveraging Artificial Intelligence and Synthetic Data Derivatives for Spine Surgery Research

STUDY DESIGN

Retrospective cohort study.

OBJECTIVES

Leveraging electronic health records (EHRs) for spine surgery research is impeded by concerns regarding patient privacy and data ownership. Synthetic data derivatives may help overcome these limitations. This study's objective was to validate the use of synthetic data for spine surgery research.

METHODS

Data came from the EHR from 15 hospitals. Patients that underwent anterior cervical or posterior lumbar fusion (2010-2020) were included. Real data were obtained from the EHR. Synthetic data was generated to simulate the properties of the real data, without maintaining a one-to-one correspondence with real patients. Within each cohort, ability to predict 30-day readmissions and 30-day complications was evaluated using logistic regression and extreme gradient boosting machines (XGBoost).

RESULTS

We identified 9,072 real and 9,088 synthetic cervical fusion patients. Descriptive characteristics were nearly identical between the 2 datasets. When predicting readmission, models built using real and synthetic data both had c-statistics of .69-.71 using logistic regression and XGBoost. Among 12,111 real and 12,126 synthetic lumbar fusion patients, descriptive characteristics were nearly the same for most variables. Using logistic regression and XGBoost to predict readmission, discrimination was similar with models built using real and synthetic data (c-statistics .66-.69). When predicting complications, models derived using real and synthetic data showed similar discrimination in both cohorts. Despite some differences, the most influential predictors were similar in the real and synthetic datasets.

CONCLUSION

Synthetic data replicate most descriptive and predictive properties of real data, and therefore may expand EHR research in spine surgery.

Translating Data Analytics Into Improved Spine Surgery Outcomes: A Roadmap for Biomedical Informatics Research in 2021

STUDY DESIGN

Narrative review.

OBJECTIVES

There is growing interest in the use of biomedical informatics and data analytics tools in spine surgery. Yet despite the rapid growth in research on these topics, few analytic tools have been implemented in routine spine practice. The purpose of this review is to provide a health information technology (HIT) roadmap to help translate data assets and analytics tools into measurable advances in spine surgical care.

METHODS

We conducted a narrative review of PubMed and Google Scholar to identify publications discussing data assets, analytical approaches, and implementation strategies relevant to spine surgery practice.

RESULTS

A variety of data assets are available for spine research, ranging from commonly used datasets, such as administrative billing data, to emerging resources, such as mobile health and biobanks. Both regression and machine learning techniques are valuable for analyzing these assets, and researchers should recognize the particular strengths and weaknesses of each approach. Few studies have focused on the implementation of HIT, and a variety of methods exist to help translate analytic tools into clinically useful interventions. Finally, a number of HIT-related challenges must be recognized and addressed, including stakeholder acceptance, regulatory oversight, and ethical considerations.

CONCLUSIONS

Biomedical informatics has the potential to support the development of new HIT that can improve spine surgery quality and outcomes. By understanding the development life-cycle that includes identifying an appropriate data asset, selecting an analytic approach, and leveraging an effective implementation strategy, spine researchers can translate this potential into measurable advances in patient care.

Automated provision of clinical routine data for a complex clinical follow-up study: A data warehouse solution

A deep integration of routine care and research remains challenging in many respects. We aimed to show the feasibility of an automated transformation and transfer process feeding deeply structured data with a high level of granularity collected for a clinical prospective cohort study from our hospital information system to the study's electronic data capture system, while accounting for study-specific data and visits. We developed a system integrating all necessary software and organizational processes then used in the study. The process and key system components are described together with descriptive statistics to show its feasibility in general and to identify individual challenges in particular. Data of 2051 patients enrolled between 2014 and 2020 was transferred. We were able to automate the transfer of approximately 11 million individual data values, representing 95% of all entered study data. These were recorded in n = 314 variables (28% of all variables), with some variables being used multiple times for follow-up visits. Our validation approach allowed for constant good data quality over the course of the study. In conclusion, the automated transfer of multi-dimensional routine medical data from HIS to study databases using specific study data and visit structures is complex, yet viable.

The Japan Neurosurgical Database: Statistics Update 2018 and 2019

Each year, the Japan Neurosurgical Society (JNS) reports up-to-date statistics from the Japan Neurosurgical Database regarding case volume, patient demographics, and in-hospital outcomes of the overall cohort and neurosurgical subgroup according to the major classifications of main diagnosis. We hereby report patient demographics, in-hospital mortality, length of hospital stay, purpose of admission, number of medical management, direct surgery, endovascular treatment, and radiosurgery of the patients based on the major classifications and/or main diagnosis registered in 2018 and 2019 in the overall cohort (523283 and 571143 patients, respectively) and neurosurgical subgroup (177184 and 191595 patients, respectively). The patient demographics, disease severity, proportion of purpose of admission (e.g., operation, 33.9-33.5%) and emergent admission (68.4-67.8%), and in-hospital mortality (e.g., cerebrovascular diseases, 6.3-6.5%; brain tumor, 3.1-3%; and neurotrauma, 4.3%) in the overall cohort were comparable between 2018 and 2019. In total, 207783 and 225217 neurosurgical procedures were performed in the neurosurgical subgroup in 2018 and 2019, respectively, of which endovascular treatment comprised 19.1% and 20.3%, respectively. Neurosurgical management of chronic subdural hematoma (19.4-18.9%) and cerebral aneurysm (15.4-14.8%) was most common. Notably, the proportion of management of ischemic stroke/transient ischemic attack, including recombinant tissue plasminogen activator infusion and endovascular acute reperfusion therapy, increased from 7.5% in 2018 to 8.8% in 2019. The JNS statistical update represents a critical resource for the lay public, policy makers, media professionals, neurosurgeons, healthcare administrators, researchers, health advocates, and others seeking the best available data on neurosurgical practice.

Rationale and Design of the Brigham Cohort for psoriasis and psoriatic arthritis registry (COPPAR)

Background

Psoriasis (PsO) and psoriatic arthritis (PsA) are related conditions with poorly defined transition among them, risk factors for progression, complex treatment algorithms, and biomarkers for treatment response and long-term outcomes. We describe the development of a PsO/PsA registry at an academic medical center.

Methods

We developed a single-center PsO/PsA longitudinal disease registry including biorepository that captures relevant disease markers and treatment choices in a circumscribed population with a defined catchment area. We searched the electronic medical record for patients with visits in the last year for PsO or PsA. They formed the potentially eligible registry population. Baseline patient and provider questionnaires were developed using standardized measures, including demographics, comorbidities, medications, specific disease characteristics, functional status, quality of life, mental health, and resource use. An abbreviated set of items was collected every six month and at visits with treatment changes or disease flares. Biospecimens included blood (serum, plasma, DNA, RNA) and skin biopsy samples, with repeat collections of serum and plasma. Data from the EMR to augment the registry questionnaires are available on all patients.

Discussion

Searching the Brigham EMR system from 2013 through 2014, we found 1694 patients with PsO and 1028 with PsA. Their mean age was 55 years and 53% were female. Of these 17% had diabetes, 38% hyperlipidemia, and 45% hypertension. The median BMI was 29.6. PsA patients used more systemic prednisone, MTX, and TNF alpha inhibitors (47%, 60%, and 66%) compared to PsO patients (28%, 20% and 21%). We have collected plasma in 410 patients, DNA/RNA in 453 patients. In conclusion, we have developed a PsO/PsA registry to better define longitudinal disease characteristics, perform biomarker studies, and examine treatment trends.

Meaningful use: an electronic medical record tool for cerebrospinal fluid shunt history

The care of patients with shunted hydrocephalus can be complicated. The best assessment is provided when all data are available to the neurosurgery practitioner. However, data can be time-consuming to gather, especially in the setting of a busy practice, a trainee environment with duty-hour restrictions, and an electronic medical record (EMR) not specifically designed for the needs of subspecialists. For these reasons, the complete clinical picture, especially the historical component, is sometimes not assembled. To address these shortcomings, the authors created a patient-level electronic CSF shunt history tool that leverages the power of the EMR concordant with the United States Centers for Medicare and Medicaid Services meaningful use principles. It is immediately available within the EMR for all users in all patient care contexts (e.g., outpatient, inpatient, perioperative, emergency, and remote access), centrally located, and designed to capture the vast range of circumstances inherent to the hydrocephalus population. Essential shunt data can be rapidly acquired and, as such, may decrease the likelihood of error in diagnosis and/or treatment. The tool also has the potential to aid the practicing neurosurgeon from clinical, quality improvement, and research standpoints. The authors have endeavored to describe this tool in a manner that would allow an interested neurosurgeon to share this publication with health information technology professionals to facilitate the development of a similar tool within their institution's own EMR platform.