Search Results

You are looking at 1 - 2 of 2 items for

  • Author or Editor: Whitney E. Muhlestein x
  • Refine by Access: all x
Clear All Modify Search
Full access

Whitney E. Muhlestein, Dallin S. Akagi, Amy R. McManus, and Lola B. Chambless

OBJECTIVE

Efficient allocation of resources in the healthcare system enables providers to care for more and needier patients. Identifying drivers of total charges for transsphenoidal surgery (TSS) for pituitary tumors, which are poorly understood, represents an opportunity for neurosurgeons to reduce waste and provide higher-quality care for their patients. In this study the authors used a large, national database to build machine learning (ML) ensembles that directly predict total charges in this patient population. They then interrogated the ensembles to identify variables that predict high charges.

METHODS

The authors created a training data set of 15,487 patients who underwent TSS between 2002 and 2011 and were registered in the National Inpatient Sample. Thirty-two ML algorithms were trained to predict total charges from 71 collected variables, and the most predictive algorithms combined to form an ensemble model. The model was internally and externally validated to demonstrate generalizability. Permutation importance and partial dependence analyses were performed to identify the strongest drivers of total charges. Given the overwhelming influence of length of stay (LOS), a second ensemble excluding LOS as a predictor was built to identify additional drivers of total charges.

RESULTS

An ensemble model comprising 3 gradient boosted tree classifiers best predicted total charges (root mean square logarithmic error = 0.446; 95% CI 0.439–0.453; holdout = 0.455). LOS was by far the strongest predictor of total charges, increasing total predicted charges by approximately $5000 per day.

In the absence of LOS, the strongest predictors of total charges were admission type, hospital region, race, any postoperative complication, and hospital ownership type.

CONCLUSIONS

ML ensembles predict total charges for TSS with good fidelity. The authors identified extended LOS, nonelective admission type, non-Southern hospital region, minority race, postoperative complication, and private investor hospital ownership as drivers of total charges and potential targets for cost-lowering interventions.

Restricted access

Whitney E. Muhlestein, Kate W. C. Chang, Brandon W. Smith, Lynda J. S. Yang, and Susan H. Brown

OBJECTIVE

Standard, physician-elicited clinical assessment tools for the evaluation of function after nerve reconstruction for neonatal brachial plexus palsy (NBPP) do not accurately reflect real-world arm function. Wearable activity monitors allow for the evaluation of patient-initiated, spontaneous arm movement during activities of daily living. In this pilot study, the authors demonstrate the feasibility of using body-worn sensor technology to quantify spontaneous arm movement in children with NBPP 10 years after nerve reconstruction and report the timing and magnitude of recovered arm movement.

METHODS

Eight children with NBPP who underwent brachial plexus reconstruction approximately 10 years prior were recruited to take part in this single-institution prospective pilot study. Per the treatment protocol of the authors’ institution, operated patients had severe, nonrecovering nerve function at the time of surgery. The patients were fitted with an activity monitoring device on each of the affected and unaffected arms, which were worn for 7 consecutive days. The duration (VT) and power (VM) with which each arm moved during the patient’s normal daily activities were extracted from the accelerometry data and ratios comparing the affected and unaffected arms were calculated. Demographic data and standard physician-elicited clinical measures of upper-extremity function were also collected.

RESULTS

Three children underwent nerve grafting and transfer and 5 children underwent graft repair only. The mean (± SD) active range of motion was 98° ± 53° for shoulder abduction, 130° ± 24° for elbow flexion, and 39° ± 34° for shoulder external rotation. The median Medical Research Council grade was at least 2.5 for all muscle groups. The median Mallet grade was at least 2 for all categories, and 13.5 total. The VT ratio was 0.82 ± 0.08 and the VM ratio was 0.53 ± 0.12.

CONCLUSIONS

Wearable activity monitors such as accelerometers can be used to quantify spontaneous arm movement in children who underwent nerve reconstruction for NBPP at long-term follow-up. These data more accurately reflect complex, goal-oriented movement needed to perform activities of daily living. Notably, despite severe, nonrecovering nerve function early in life, postsurgical NBPP patients use their affected arms more than 80% of the time that they use their unaffected arms, paralleling results in patients with NBPP who recovered spontaneously. These data represent the first long-term, real-world evidence to support brachial plexus reconstruction for patients with NBPP.