Brief Report: Participation Among Transition-Aged Youth With Traumatic Brain Injury in the State/Federal Vocational Rehabilitation System

This study aimed to understand the level of participation among transition-aged youth with traumatic brain injury (TBI) in the State/Federal Vocational Rehabilitation (VR) System in the context of the Workforce Innovation and Opportunity Act (WIOA). Case closures, case duration, and case expenditures in Federal fiscal years (FYs) 2014, 2015, and 2016 were examined among transition-aged youth (i.e., State VR clients under the age of 22 years at application) with TBI, autism spectrum order (ASD), and intellectual disability (ID), using a nonexperimental and descriptive design. A disproportionate number of transition-aged youth with ASD and ID had closed State VR cases compared with transition-aged youth with TBI. Alternatively, there were greater State VR case duration levels and case service expenditures for persons with TBI compared with those with ASD or ID. The disproportionate participation with State VR was consistent among these three groups via eligibility for services under the Individuals with Disabilities Education Act. This article highlights areas of attention concerning transition-aged youth with TBI and will hopefully stimulate future dialogue, research, and policy development concerning participation with State VR for this population.

A Machine Learning Study to Improve Surgical Case Duration Prediction

Since the emergence of COVID-19, many hospitals have encountered challenges in performing efficient scheduling and good resource management to ensure the quality of healthcare provided to patients is not compromised. Operating room (OR) scheduling is one of the issues that has gained our attention because it is related to workflow efficiency and critical care of hospitals. Automatic scheduling and high predictive accuracy of surgical case duration have a critical role in improving OR utilization. To estimate surgical case duration, many hospitals rely on historic averages based on a specific surgeon or a specific procedure type obtained from electronic medical record (EMR) scheduling systems. However, the low predictive accuracy with EMR data leads to negative impacts on patients and hospitals, such as rescheduling of surgeries and cancellation. In this study, we aim to improve the prediction of surgical case duration with advanced machine learning (ML) algorithms. We obtained a large data set containing 170,748 surgical cases (from Jan 2017 to Dec 2019) from a hospital. The data covered a broad variety of details on patients, surgeries, specialties and surgical teams. In addition, a more recent data set with 8,672 cases (from Mar to Apr 2020) was available to be used for external evaluation. We computed historic averages from the EMR data for surgeon- or procedure-specific cases, and they were used as baseline models for comparison. Subsequently, we developed our models using linear regression, random forest and extreme gradient boosting (XGB) algorithms. All models were evaluated with R-square (R2), mean absolute error (MAE), and percentage overage (actual duration longer than prediction), underage (shorter than prediction) and within (within prediction). The XGB model was superior to the other models, achieving a higher R2 (85 %) and percentage within (48 %) as well as a lower MAE (30.2 min). The total prediction errors computed for all models showed that the XGB model had the lowest inaccurate percentage (23.7 %). Overall, this study applied ML techniques in the field of OR scheduling to reduce the medical and financial burden for healthcare management. The results revealed the importance of surgery and surgeon factors in surgical case duration prediction. This study also demonstrated the importance of performing an external evaluation to better validate the performance of ML models.

A Machine Learning Study to Improve Surgical Case Duration Prediction

Predictive accuracy of surgical case duration plays a critical role in reducing cost of operation room (OR) utilization. The most common approaches used by hospitals rely on historic averages based on a specific surgeon or a specific procedure type obtained from the electronic medical record (EMR) scheduling systems. However, low predictive accuracy of EMR leads to negative impacts on patients and hospitals, such as rescheduling of surgeries and cancellation. In this study, we aim to improve prediction of operation case duration with advanced machine learning (ML) algorithms. We obtained a large data set containing 170,748 operation cases (from Jan 2017 to Dec 2019) from a hospital. The data covered a broad variety of details on patients, operations, specialties and surgical teams. Meanwhile, a more recent data with 8,672 cases (from Mar to Apr 2020) was also available to be used for external evaluation. We computed historic averages from EMR for surgeon- or procedure-specific and they were used as baseline models for comparison. Subsequently, we developed our models using linear regression, random forest and extreme gradient boosting (XGB) algorithms. All models were evaluated with R-squre (R2), mean absolute error (MAE), and percentage overage (case duration > prediction + 10 % & 15 mins), underage (case duration < prediction - 10 % & 15 mins) and within (otherwise). The XGB model was superior to the other models by having higher R2 (85 %) and percentage within (48 %) as well as lower MAE (30.2 mins). The total prediction errors computed for all the models showed that the XGB model had the lowest inaccurate percent (23.7 %). As a whole, this study applied ML techniques in the field of OR scheduling to reduce medical and financial burden for healthcare management. It revealed the importance of operation and surgeon factors in operation case duration prediction. This study also demonstrated the importance of performing an external evaluation to better validate performance of ML models.

Postoperative Complications Causing Readmission in 30 Days after Total Knee Arthroplasty: A Retrospective Nested Case-Control Study of Risk Factors Based on Propensity Score Matching

We performed this study to identify independent risk factors for life-threatening postoperative complications causing 30-day readmissions after total knee arthroplasty (TKA). Improved understanding of these risks may improve efficiency and safety of treatment. We performed a retrospective, nested case-control study using an open-access database of 2,622 patients who underwent primary TKA at a tertiary academic medical center in Singapore between January 2013 and June 2014. Patients were grouped according to the incidence of complications. Multivariate logistic analysis was performed to identify predictive factors for TKA complications. The incidence of postoperative complications was 1.72%. Compared with cases performed with an operative time < 70 minutes, increased operative time was associated with a higher risk of complications. Case duration > 90 minutes was associated with an increased risk (adjusted odds ratio [aOR] = 4.57, p = 0.001; case duration ≥ 111 minutes, aOR = 4.64, p = 0.04; and case duration between 91 and 110 minutes, aOR = 3.20, p = 0.03). The correlation between operative time and complications was nonlinear. Cerebrovascular accident (CVA) or transient ischemic attack (TIA) was an independent risk factor for increased complication rate (aOR = 11.59, p = 0.02). Operative duration has been identified as an independent risk factor for complications after TKA. As it remains a modifiable factor to which doctors are interested in bringing quality improvement, the risk of postoperative complications will be reduced by minimizing the operative duration.

Simultaneous patient presentation for endovascular thrombectomy in acute ischemic stroke

BackgroundIncreased demand for endovascular thrombectomy has increased the likelihood of simultaneous patient presentation leading to competing demand for time-critical treatment that could adversely impact patient outcomes. We aimed to quantify the occurrence of simultaneous patient presentation at different patient volumes.MethodsEmpirical distributions for time of patient presentation and case duration were used to probabilistically generate arrival time and case duration for a set annual patient volume, ranging from 1 to 500 cases per year, for 16 000 independent trials at each volume. Time series were generated for each trial to represent the number of cases being performed at each minute of the year. Time series were used to calculate daily thrombectomy demand, annual concurrent demand, and hourly excess demand.ResultsThe patient volumes at which at least one annual occurrence of concurrent demand by two patients was 50% and 97.5% likely were 45 and 101, respectively. The volumes at which at least one annual occurrence of concurrent demand by three patients was 50% and 97.5% likely were 216 and 387, respectively. There was dramatic variation in the occurrence of excess demand by two or more patients throughout the day.ConclusionsThe occurrence of simultaneous presentation by multiple patients for endovascular thrombectomy varies with annual patient volume and time of day. Understanding these trends and the associated patient impact can inform intelligent strategies at regional and national levels for optimizing patient care within real-world financial and operational constraints.