Machine Learning Model Developed to Aid in Patient Selection for Outpatient Total Joint Arthroplasty.
Ontology highlight
ABSTRACT:
SUBMITTER: Lopez CD
PROVIDER: S-EPMC8666332 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundAspirin and mechanical compression devices are approved means of venous thromboembolism (VTE) prophylaxis after total joint arthroplasty. Prior studies of mechanical compression pumps after joint arthroplasty have been limited to the inpatient setting. The purpose of this study was to evaluate outpatient compliance and utilization factors in a rural population after elective hip or knee arthroplasty.MethodsUtilization for portable pneumatic compression pumps after joint arthroplasty was prospectively recorded (hours). Compliance was defined as the recommended 20 hours per day. A questionnaire 2 weeks postoperatively assessed factors that may contribute to noncompliance. Patients were followed up for 90 days postoperatively to record VTE events.ResultsData were collected for 115 joint arthroplasty patients (50 hips, 65 knees). Postdischarge day one had the highest average usage at 13.2 hours/day (66.0%, range 0%-100%), but this number fell to 4.8 hours/day (24.0, range 0%-100%) by day 14. Patient compliance (>20 hours use/day) was highest on postdischarge day one at 40 patients (34.7%). By postdischarge day 14, patient compliance fell to 17 patients (14.8%). Difficulty using the pumps (P = .027) and pump-associated heat (P = .009) were significantly associated with patient compliance. A deep vein thrombosis and nonfatal pulmonary embolism were recorded in 2 separate patients.ConclusionsThis study demonstrated poor outpatient compliance with portable pneumatic compression devices. Poor compliance was related to pump heat and difficulty with pump use. Even with poor compliance, a low incidence of VTE events was observed.
| S-EPMC7083727 | biostudies-literature
Project description:BackgroundResearch in surgical fields other than orthopedics has demonstrated high patient satisfaction with non-traditional telerounding modalities.Questions/purposesWe sought to determine patient satisfaction and Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) scores of patients who experienced telerounding in the post-operative period after undergoing total joint arthroplasty (TJA).MethodsFifty consecutive TJA patients were prospectively enrolled to receive telerounding. The patients were divided into two groups based on their satisfaction with telerounding. The HCAHPS scores of the patients who received telerounding were compared with 50 control patients.ResultsOverall, the telerounding cohort had a positive reaction to telerounding. Comparing patients who were highly satisfied to those who were dissatisfied with telerounding, younger patients were found to be more frequently satisfied with telerounding. Compared with patients who did not receive telerounding, patients who experienced telerounding rated the hospital higher on a 10-point scale were more likely to recommend the hospital to others, more frequently believed their physicians treated them with courtesy and respect, and more often believed their physicians always listened to them carefully.ConclusionAn overwhelming majority of our patients found telerounding using FaceTime enhanced their care while recovering post-operatively from TJA. Those patients were typically younger and had significantly higher HCAHPS scores, which potentially can enhance the physician-patient relationship.
| S-EPMC7646716 | biostudies-literature
Project description:BackgroundThe 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.MethodsA 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.ResultsOne 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%.ConclusionsUsing 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.
| S-EPMC8076615 | biostudies-literature
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.
| S-EPMC8784312 | biostudies-literature
Project description:BackgroundThe Centers for Medicare & Medicaid Services currently incentivizes hospitals to reduce postdischarge adverse events such as unplanned hospital readmissions for patients who underwent total joint arthroplasty (TJA). This study aimed to predict 90-day TJA readmissions from our comprehensive electronic health record data and routinely collected patient-reported outcome measures.MethodsWe retrospectively queried all TJA-related readmissions in our tertiary care center between 2016 and 2019. A total of 104-episode care characteristics and preoperative patient-reported outcome measures were used to develop several machine learning models for prediction performance evaluation and comparison. For interpretability, a logistic regression model was built to investigate the statistical significance, magnitudes, and directions of associations between risk factors and readmission.ResultsGiven the significant imbalanced outcome (5.8% of patients were readmitted), our models robustly predicted the outcome, yielding areas under the receiver operating characteristic curves over 0.8, recalls over 0.5, and precisions over 0.5. In addition, the logistic regression model identified risk factors predicting readmission: diabetes, preadmission medication prescriptions (ie, nonsteroidal anti-inflammatory drug, corticosteroid, and narcotic), discharge to a skilled nursing facility, and postdischarge care behaviors within 90 days. Notably, low self-reported confidence to carry out social activities accurately predicted readmission.ConclusionsA machine learning model can help identify patients who are at substantially increased risk of a readmission after TJA. This finding may allow for health-care providers to increase resources targeting these patients. In addition, a poor response to the "social activities" question may be a useful indicator that predicts a significant increased risk of readmission after TJA.
| S-EPMC10790030 | biostudies-literature
Project description:BackgroundDespite widely reported success associated with hip and knee replacements, some patients remain dissatisfied with their outcomes. Patient activation, an individual's propensity to engage in adaptive health behaviors, has been measured as a potentially important factor contributing to health outcomes, cost, and patient experience of care. However, to our knowledge, it has not been studied in patients undergoing total joint arthroplasties (TJAs).Questions/purposesWe wanted to determine whether patients with higher activation scores would experience (1) greater resolution of pain and improved activity, (2) greater improvements in postoperative physical and mental health, and (3) greater patient satisfaction after primary THA or TKA.MethodsWe approached 174 patients and enrolled 135 who were undergoing primary THA or TKA at one of two hospitals between January 2013 and May 2014. Patient Activation Measure (PAM) scores were obtained preoperatively and patient-reported outcomes were assessed and completed for 125 patients pre- and postoperatively at the 6- or 12-month visit. We assessed pain and activity with the Hip Disability and Osteoarthritis Outcome Score (HOOS), Knee Injury and Osteoarthritis Outcome Score (KOOS), and University of California Los Angeles (UCLA) activity scores. We measured physical and mental health by calculating SF12v2® scores and measured patient satisfaction with the Hip and Knee Satisfaction Scale (HKSS). Linear regression models were used to test the association between baseline PAM and postoperative patient-reported outcomes.ResultsOverall, patients with a higher baseline PAM score experienced better pain relief using the HOOS/KOOS pain scores (R2=0.311, p=0.048) and symptoms using the HOOS/KOOS symptom scores (R2=0.272, p=0.021). In addition, higher PAM scores were associated with better postoperative mental health using the SF12v2® (R2=0.057, p<0.001), but were not associated with higher physical health (R2=0.176, p=0.173). Finally, higher PAM scores were associated with having greater postoperative satisfaction after surgery using the HKSS questionnaire (R2=0.048, p=0.023).ConclusionsHigher preoperative patient activation was associated with better pain relief, decreased symptoms, improved mental health, and greater satisfaction after TJA. Future efforts should be aimed at studying if improving patient activation before surgery results in better patient-reported outcomes after elective THA or TKA.Level of evidenceLevel II, prognostic study.
| S-EPMC4488208 | biostudies-literature
Project description:BackgroundPatient satisfaction has become an important metric for total joint arthroplasty (TJA) used to reimburse hospitals. Despite ubiquitous narcotic use for post-TJA pain control, there is little understanding regarding patient factors associated with obtaining opioid refills and associations with patient satisfaction.MethodsUsing our state's mandatory opioid prescription monitoring program, we reviewed preoperative and postoperative narcotic prescriptions filled for 438 consecutive TJA patients. Subjects were divided into 3 groups based on the number of post-TJA narcotic refills obtained (0, 1, or >1), and logistic regression analysis was conducted comparing demographics, surgical factors, and satisfaction with pain control.ResultsOne hundred twenty-five patients (25.8%) did not consume preoperative opioids and received no postoperative refills. Total hip arthroplasty (THA) patients (P = .0004), subjects ≥65 years (P = .0057), and Medicare patients (P = .0058) had significantly higher rates of 0 postdischarge refills. THA recipients had 268% increased odds of not receiving a refill narcotic (adjusted odds ratio = 0.373; 95% confidence interval, 0.224- 0.622). Every 100-morphine milligram equivalent (MME) increase in presurgery use led to a 16% increase in odds of needing >1 opioid refill (adjusted odds ratio = 1.161; 95% confidence interval, 1.085-1.242). Subjects who noted higher satisfaction consumed less overall opioids when receiving a refill (436 vs 1119 MMEs, P = .021).ConclusionSubjects who received fewer narcotic prescriptions and overall MMEs demonstrated higher rates of satisfaction with early pain control. Our results are consistent with other studies in showing that increased preoperative narcotic use portends higher rates of postoperative refills. There appears to be a subset of THA patients >65 years of age who may be candidates for opioid-sparing analgesia.
| S-EPMC7855659 | biostudies-literature
Project description:BackgroundTotal joint arthroplasty (TJA) registries traditionally have focused on implant longevity and rates of revision surgery. Registries would benefit from the addition of standardized patient-reported outcomes (PROs) such as pain relief and improved physical function. However, PROs have not been routinely adopted, and their incorporation into TJA registries presents challenges.Questions/purposesWe review current PRO use by existing national registries, challenges to integrating PROs in national registries, lessons from national registries that have integrated PROs, and suggestions to guide future adoption of PROs.MethodsWe conducted a literature search of papers addressing PRO use in national knee and hip arthroplasty registries, resulting in 15 articles. These publications were supplemented by discussions with thought leaders from international registries. WHERE ARE WE NOW?: Some national TJA registries are collecting PROs and valuable research is emerging. However, challenges exist, such as selecting suitable PROs, selection bias in countries without government-mandated participation for all hospitals, and challenges with missing data. WHERE DO WE NEED TO GO?: The ideal system will incorporate PROs into TJA registries. In so doing, it will be important to choose suitable PROs and develop innovative methods to collect PROs to ensure complete data and sustainability. HOW DO WE GET THERE?: New methods are required to meet the challenges related to registry design, logistics of PRO collection, and registry cost and sustainability. Modifications to the traditional hospital- and implant-centric design and new procedures to collect complete data from both patients and clinicians may be necessary. For instance, England and Wales, New Zealand, and Sweden developed methods to collect PROs after TJA directly from patients and a US TJA registry collects PROs as the primary outcome. Finally, to assure long-term sustainability, PRO data must be valuable to multiple stakeholders, including patients, clinicians, researchers, and policy makers.
| S-EPMC3792256 | biostudies-literature
Project description:AimsThe use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments.MethodsBased on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data.ResultsWith an associated area under the receiver-operator curve ranging between 0.75 and 0.98, the optimized ML models resulted in good to excellent predictions. The best performing model used a random forest approach while considering both alignment and intra-articular load readings.ConclusionThe presented model has the potential to make experience available to surgeons adopting new technology, bringing expert opinion in their operating theatre, but also provides insight in the surgical decision process. More specifically, these promising outcomes indicated the relevance of considering the overall limb alignment in the coronal and sagittal plane to identify the appropriate surgical decision.
| S-EPMC7677727 | biostudies-literature
Project description:BackgroundThe purpose of this study was to determine the optimal window for collection of patient-reported outcome measures (PROMs) after total joint arthroplasty (TJA).MethodsOur prospectively collected institutional joint registry was queried for patients who underwent primary, unilateral TJAs. The primary outcomes were the net changes in WOMAC, SF-12 MCS, SF-12 PCS, OHS, KSCRS, and UCLA activity rating system at 6, 12, and 24 months postoperatively. Secondary outcomes were data acquisition costs and follow-up attrition rates.ResultsEight hundred sixty-six procedures (450 total hip arthroplasties, 416 TKAs) were analyzed. A consistent plateau in all PROMs was noted by 6 months postoperatively-except for SF-12 MCS which showed no significant changes at any time interval. For TKA, the percentage of overall improvement achieved by 6 months was 88.7%, 84.5%, 100%, and 90.5% for the WOMAC, SF-12 PCS, UCLA, and KSCRS, respectively. For total hip arthroplasty, these values were 92.7%, 83.5%, 88.0%, and 89.8% for WOMAC, SF-12 PCS, UCLA, and OHS, respectively. There were marginal improvements from 6 to 12 months and no improvement from 12 to 24 months. Follow-up rates at 6, 12, and 24 months were 85%, 69%, and 40%, respectively. Our institutional costs for collecting a complete data set per patient were $128, $158, and $272 for 6, 12, and 24 months, respectively.ConclusionsMost of the improvement in PROMs after primary TJA occurs within the first 6 months. In addition, limiting PROMs collection to 6 months appears to be cost-efficient owing to increased attrition rates beyond this time interval.
| S-EPMC7083724 | biostudies-literature