Dataset Information

A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty.

ABSTRACT:

Background

The Centers for Medicare and Medicaid Services removed total hip arthroplasty (THA) from the inpatient-only list. This has created significant confusion regarding which patients qualify for an inpatient designation. The purpose of this study is to develop and validate a novel predictive tool for preoperatively objectively determining "outpatient" vs "inpatient" status for THA in the Medicare population.

Methods

A cohort of Medicare patients undergoing primary THA between January 2017 and September 2019 was retrospectively reviewed. A machine learning model was trained using 80% of the THA patients, and the remaining 20% was used for testing the model performance in terms of accuracy and the average area under the receiver operating characteristic curve. Feature importance was obtained for each feature used in the model.

Results

One thousand ninety-one patients had outpatient stays, and 318 qualified for inpatient designation. Significant associations were demonstrated between inpatient designations and the following: higher BMI, increased patient age, better preoperative functional scores, higher American Society of Anesthesiologist Physical Status Classification, higher Modified Frailty Index, higher Charlson Comorbidity Index, female gender, and numerous comorbidities. The XGBoost model for predicting an inpatient or outpatient stay was 78.7% accurate with the area under the receiver operating characteristic curve to be 81.5%.

Conclusions

Using readily available key baseline characteristics, functional scores and comorbidities, this machine-learning model accurately predicts an "outpatient" or "inpatient" stay after THA in the Medicare population. BMI, age, functional scores, and American Society of Anesthesiologist Physical Status Classification had the highest influence on this predictive model.

SUBMITTER: Kugelman DN

PROVIDER: S-EPMC8076615 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundRemoval of total joint arthroplasty from the inpatient-only list has created significant confusion regarding which patients qualify for an inpatient designation. The purpose of this study is to develop and validate a novel predictive tool for assessing who will be an outpatient vs inpatient after total knee arthroplasty (TKA).MethodsA cohort of Medicare patients undergoing primary TKA between January 2018 and September 2019 were retrospectively reviewed. Baseline demographics and patient characteristics were obtained, and their distributions for outpatient (less than 2 midnights) and inpatient stay were assessed. Subsequently, a XGBoost machine learning model was trained using 80% of the TKA patients, and the remaining 20% of patients were involved in testing the model's performance in terms of accuracy and the average area under the receive operating characteristic curve.ResultsEight hundred ninety-nine Medicare patients underwent TKA at our institution between January 2018 and September 2019. Of which, 625 patients had outpatients stays, and 274 qualified for inpatient designation. Significant associations were demonstrated between inpatient visits and the following factors: higher body mass index, increased age, better functional scores, multidimensional fatigue inventory, Charlson Comorbidity Index, American Society of Anesthesiologists score, female gender, cardiac history, and the Revised Cardiac Risk Index. The XGBoost model for predicting an inpatient or outpatient stay was 63.3% accurate, with area under the receive operating characteristic curve of 68.8%.ConclusionsUsing readily available key baseline characteristics, functional scores, and comorbidities, this machine-learning model accurately predicts the probability of an "outpatient" vs "inpatient" stay after TKA in the Medicare population. body mass index, age, VR12 functional scores, and multidimensional fatigue inventory scores had the highest influence on this predictive model.

Project description:BackgroundLength of stay after total hip arthroplasty (THA) has decreased over the last two decades. However, published studies that have examined same-day and early discharge protocols after THA have been done in highly selected patient groups operated on by senior surgeons in a nonrandomized fashion without control subjects.Questions/purposesThe purpose of this study was to evaluate and compare patients undergoing THA who are discharged on the same day as the surgery ("outpatient," less than 12-hour stay) with those who are discharged after an overnight hospital stay ("inpatient") with regard to the following outcomes: (1) postoperative pain; (2) perioperative complications and healthcare provider visits (readmission, emergency department or physician office); and (3) relative work effort for the surgeon's office staff.MethodsA prospective, randomized study was conducted at two high-volume adult reconstruction centers between July 2014 and September 2015. Patients who were younger than 75 years of age at surgery, who could ambulate without a walker, who were not on chronic opioids, and whose body mass index was less than 40 kg/m2 were invited to participate. All patients had a primary THA performed by the direct anterior approach with spinal anesthesia at a hospital facility. Study data were evaluated using an intention-to-treat analysis. A total of 220 patients participated, of whom 112 were randomized to the outpatient group and 108 were randomized to the inpatient group. Of the 112 patients randomized to outpatient surgery, 85 (76%) were discharged as planned. Of the remaining 27 patients, 26 were discharged after one night in the hospital and one was discharged after two nights. Of the 108 patients randomized to inpatient surgery with an overnight hospital stay, 81 (75%) were discharged as planned. Of the remaining 27 patients, 18 met the discharge criteria on the day of their surgery and elected to leave the same day, whereas nine patients stayed two or more nights.ResultsOn the day of surgery, there was no difference in visual analog scale (VAS) pain among patients who were randomized to discharge on the same day and those who were randomized to remain in the hospital overnight (outpatient 2.8 ± 2.5, inpatient 3.3 ± 2.3, mean difference -0.5, 95% confidence interval [CI], -1.1 to 0.1, p = 0.12). On the first day after surgery, outpatients had higher VAS pain (at home) than inpatients (3.7 ± 2.3 versus 2.8 ± 2.1, mean difference 0.9, 95% CI, 0.3-1.5, p = 0.005). With the numbers available, there was no difference in the number of reoperations, hospital readmissions without reoperation, emergency department visits without hospital readmission, or acute office visits. At 4-week followup, there was no difference in the number of phone calls and emails with the surgeon's office (outpatient: 2.4 ± 1.9, inpatient: 2.4 ± 2.2, mean difference 0, 95% CI, -0.5 to 0.6, p = 0.94).ConclusionsOutpatient THA can be implemented in a defined patient population without requiring additional work for the surgeon's office. Because 24% (27 of 112) of patients planning to have outpatient surgery were not able to be discharged the same day, facilities to accommodate an overnight stay should be available.Level of evidenceLevel I, therapeutic study.

Project description:BackgroundThe length of hospital stay after lower limb arthroplasty has rapidly decreased in the last decade, largely in part due to the rise of improved perioperative protocols, but also as a response to the increased economic demand associated with the rapid growth in hip and knee arthroplasty procedures. In line with this, the development of a new pathway after lower limb arthroplasty that allows for the surgery to be performed in an outpatient setting and permits for same-day discharge after the procedure is increasingly being offered. Although costs and complications between the inpatient and outpatient models have been compared, there appears to be little known about the effects on a patient's physical function after undergoing hip or knee outpatient arthroplasty. Therefore, this systematic review aims to explore the available evidence for the effect on functional outcomes following inpatient versus outpatient hip or knee arthroplasty.MethodsThis systematic review adhered to the PRISMA guidelines and was prospectively registered ( https://osf.io/8bfae/ ). An electronic search of three online databases (PubMed, CINAHL and EMBASE) was conducted to identify eligible studies. All studies investigating inpatient and outpatient comparator groups, for a population of patients undergoing hip or knee arthroplasty, that assessed one or more functional outcomes, were included. A methodological quality appraisal was undertaken for the final studies contained in this review. A narrative synthesis of results is described along with quantitative outcomes presented in tables and figures.ResultsA total of seven studies containing 1,876 participants were included in this review. Four studies assessed a THA population, two assessed TKA and one assessed both. Functional outcomes varied, with 20 different functional outcomes utilised, of which 18 were patient-reported tools. Results of functional outcomes offered mixed support for both inpatient and outpatient pathways.ConclusionsThe results of this review suggest that outpatient or inpatient pathway selection for hip or knee arthroplasty should not be based on the superiority of functional outcomes alone. However, given there is growing evidence in support of an outpatient pathway in select patients with respect to cost savings and without any increase in complications, it could be proposed that an equivalency of post-operative function between the two settings makes same-day discharge favourable. Publicly registered with Open Science Framework ( https://osf.io/8bfae/ ).