Healthcare professionals' perceived problems in fast-track hip and knee arthroplasty: results of a qualitative interview study

Second opinion machine learning for fast-track pathway assignment in hip and knee replacement surgery: the use of patient-reported outcome measures

BACKGROUND

The frequency of hip and knee arthroplasty surgeries has been rising steadily in recent decades. This trend is attributed to an aging population, leading to increased demands on healthcare systems. Fast Track (FT) surgical protocols, perioperative procedures designed to expedite patient recovery and early mobilization, have demonstrated efficacy in reducing hospital stays, convalescence periods, and associated costs. However, the criteria for selecting patients for FT procedures have not fully capitalized on the available patient data, including patient-reported outcome measures (PROMs).

METHODS

Our study focused on developing machine learning (ML) models to support decision making in assigning patients to FT procedures, utilizing data from patients' self-reported health status. These models are specifically designed to predict the potential health status improvement in patients initially selected for FT. Our approach focused on techniques inspired by the concept of controllable AI. This includes eXplainable AI (XAI), which aims to make the model's recommendations comprehensible to clinicians, and cautious prediction, a method used to alert clinicians about potential control losses, thereby enhancing the models' trustworthiness and reliability.

RESULTS

Our models were trained and tested using a dataset comprising 899 records from individual patients admitted to the FT program at IRCCS Ospedale Galeazzi-Sant'Ambrogio. After training and selecting hyper-parameters, the models were assessed using a separate internal test set. The interpretable models demonstrated performance on par or even better than the most effective 'black-box' model (Random Forest). These models achieved sensitivity, specificity, and positive predictive value (PPV) exceeding 70%, with an area under the curve (AUC) greater than 80%. The cautious prediction models exhibited enhanced performance while maintaining satisfactory coverage (over 50%). Further, when externally validated on a separate cohort from the same hospital-comprising patients from a subsequent time period-the models showed no pragmatically notable decline in performance.

CONCLUSIONS

Our results demonstrate the effectiveness of utilizing PROMs as basis to develop ML models for planning assignments to FT procedures. Notably, the application of controllable AI techniques, particularly those based on XAI and cautious prediction, emerges as a promising approach. These techniques provide reliable and interpretable support, essential for informed decision-making in clinical processes.

Patient participation in orthopaedic care-a survey on hip surgery patients' preferences for and experiences of engagement in their health and healthcare

INTRODUCTION

Quality in health services is increasingly associated with enabling patients to participate in their own health and healthcare by recognising their resources and needs. Despite a growing recognition as to whether such participation is enabled, little is known regarding opportunities for preference-based patient participation in orthopaedic care.

AIMS

To investigate preference-based participation for patients in orthopaedic care due to hip surgery.

METHODS

Patients across 17 Swedish orthopaedic units who had had hip surgery, due to hip fracture or osteoarthritis, January-April 2021 were invited to complete the validated 4Ps questionnaire. Of 1514 patients, 458 patients returned the questionnaire with reports on their preferences for and experiences of participation. Each of the 4Ps' 12 items were analysed separately using descriptive and comparative statistics.

RESULTS

A complete match in preferences for, and experiences of, participation was achieved with variation between items for 41%-50% of the patients; if almost matches were included, this occurred for 57%-77% of the patients. Less participation than preferred was most common in terms of having had reciprocal communication, opportunities for partaking in planning, and in learning how to manage symptoms/issues. Hip fracture surgery was significantly associated with experiencing lower levels of participation than preferred.

CONCLUSION

Though standardised care promotes efficient hip surgery care, our study suggests a need for more person-centred opportunities to engage. A discrepancy was noted between patients' resources and preparation for their participation in and beyond the hip surgery process, particularly for self-care activities, calling for better use of nursing resources. ID: NCT04700969 with the U.S National Institutes of Health Clinical Registry.

Patients' perspective of fast-track total joint arthroplasty: a systematic review

The introduction of fast-track protocols decreased length of hospital stay and improved rehabilitation and outcomes in total joint arthroplasty. Despite improved clinical results published in many papers, the patient perspective of these protocols is less investigated. Purpose of this study was to explore the patient perspective of fast-track protocols in arthroplasty. A systematic search for articles of patient experiences in total hip, knee, and shoulder arthroplasty was conducted using EMBASE, MEDLINE, Cochrane, and Web-of-Science for articles published from inception to February 14, 2023. In total 12 studies were included involving 672 patients. Most patients were satisfied with short length of hospital stay and preferred rehabilitation at home with relatives for support. Various experiences were reported regarding pain and postoperative out of hospital physical therapy. Frequently, feelings of insecurity were reported because of lack of personalized information. Based on current qualitative literature, patients are satisfied with short length of hospital stay in fast-track total joint arthroplasty. Improvements in personalized information and physical therapy protocols is needed.

Patient-Reported Outcomes for Function and Pain in Total Knee Arthroplasty Patients

BACKGROUND

Some patients undergoing total knee arthroplasty successfully manage their condition postoperatively, while others encounter challenges in regaining function and controlling pain during recovery at home.

OBJECTIVE

To use traditional statistics and machine learning to develop prediction models that identify patients likely to have increased care needs related to managing function and pain following total knee arthroplasty.

METHODS

This study included 201 patients. Outcomes were changes between baseline and follow-up in the functional and pain subcomponents of the Oxford Knee Score. Both classification and regression modeling were applied. Twenty-one predictors were included. Tenfold cross-validation was used, and the regression models were evaluated based on root mean square error, mean absolute error, and coefficient of determination. Classification models were evaluated based on the area under the receiver operating curve, sensitivity, and specificity.

RESULTS

In classification modeling, random forest and stochastic gradient boosting provided the best overall metrics for model performance. A support vector machine and a stochastic gradient boosting machine in regression modeling provided the best predictive performance. The models performed better in predicting challenges related to function compared to challenges related to pain.

DISCUSSION

There is valuable predictive information in the data routinely collected for patients undergoing total knee arthroplasty. The developed models may predict patients who are likely to have enhanced care needs regarding function and pain management. Improvements are needed before the models can be implemented in routine clinical practice.

The potential of dividing the oxford knee score into subscales for predicting clinically meaningful improvements in pain and function of patients undergoing total knee arthroplasty

BACKGROUND

Subdividing the Oxford Knee Score (OKS) into a pain component scale (OKS-PCS) and a function component scale (OKS-FCS) for predicting clinically meaningful improvements may provide a basis for identifying patients in need of enhanced support from health care professionals to manage pain and functional challenges following total knee arthroplasty.

AIM

To assess the potential of dividing the OKS into subscales for predicting clinically meaningful improvements in pre- and postoperative pain and function by comparing two different versions of extracting pain and function derived from the OKS.

METHODS

This retrospective observational cohort study included 201 patients undergoing total knee arthroplasty. Multiple logistic regression analysis was applied for binary classification of whether patients achieved clinically meaningful improvements in pain and function.

RESULTS

The best overall version for predicting clinically meaningful improvements had an area under the receiver operating characteristic curve of 0.79 for both pain and function, whereas Nagelkerke's R² was 0.322 and 0.334, respectively.

CONCLUSION

The findings indicate that it is reasonable to subdivide the OKS into subscales for predicting clinically meaningful improvements in pain and function. However, more studies are needed to compare various types of classification algorithms in larger patient populations.

Effect of Observation of Shou Hui Tong Bian Capsule (Polygonum Multiflorum and Aloe-Based Herbal Capsule for Cathartic Effect) in Rapid Rehabilitation of Joint Surgery

OBJECTIVE

To observe the effect of Shou Hui Tong Bian capsule (polygonum multiflorum and aloe-based herbal capsule for cathartic effect) in rapid rehabilitation of joint surgery.

METHODS

A total of 98 patients undergoing perioperative joint surgery in our hospital from July 2019 to March 2020 were included in the study. According to the situation of arthroscopy and joint replacement therapy, the patients were randomly divided into a control group and an observation group, with 49 cases in each group. The control group was treated with conventional therapy. On the basis of the control group, the patients in the observation group were orally administrated with Shou Hui Tong Bian capsule, 2 capsules/time, 3 times/day. Both groups received continuous treatment for 14 days. The clinical effects, awakening time, postoperative exhaust time, and the number of patients with different degrees of abdominal distension in the four groups before and after treatment were observed and compared.

RESULTS

After treatment, the total effective rate of arthroscopy in the control group was 66.7%, which was significantly lower than 83.3% in the observation group (P < 0.05). The total effective rate of joint replacement in the control group was 64.0%, which was significantly lower than 84.0% in the observation group (P < 0.05). After arthroscopic treatment and joint replacement treatment, the recovery time and postoperative exhaust time of borborygmus in the observation group were significantly lower than those in the control group (both P < 0.05). After the treatment, the number of patients with different degrees of abdominal distension in the arthroscopic and joint replacement treatment group and the control group was significantly improved (P < 0.05), and the observation group was significantly better than the control group (P < 0.05).

CONCLUSION

The curative effect of Shou Hui Tong Bian capsule on patients undergoing arthroscopic joint surgery and joint replacement during perioperative period is obviously superior to that of conventional treatment. It can effectively improve the total effective rate, shorten the first exhaust time, and increase the number of patients without abdominal distension after treatment. It was safe and effective, and worthy of clinical promotion.

Association between preoperative frailty and outcomes among adults undergoing cardiac surgery: a prospective cohort study

BACKGROUND

The identification of frailty before complex and invasive procedures may have relevance for prognostic and recovery purposes, to optimally inform patients, caregivers and clinicians about perioperative risk and postoperative care needs. The aim of this study was to estimate the prevalence of frailty and describe the associated clinical course and outcomes of patients referred for nonemergent cardiac surgery.

METHODS

A prospective cohort of patients aged 50 years and older referred for nonemergent cardiac surgery in Alberta, Canada, from November 2011 to March 2014 were screened preoperatively for frailty, defined as a Clinical Frailty Scale (CFS) score of 5 or greater. Postoperatively, patients were followed by telephone to assess CFS score, health services use and vital status. The primary outcome was all-cause hospital mortality. Secondary outcomes included health services use, hospital discharge disposition, 1-year health-related quality of life and all-cause 5-year mortality.

RESULTS

The cohort (n = 529) had a mean age of 67 (standard deviation [SD] 9) years; 25.9% were female, and the prevalence of frailty was 9.6% (n = 51; 95% confidence interval [CI] 7.3%-12.5%). Frail patients were older (median age 75, interquartile range [IQR] 65-80 v. 67, IQR 60-73, yr; p < 0.001), were more likely to be female (51.0% v. 23.2%; p < 0.001), had a higher mean EuroSCORE II (8, SD 3 v. 5, SD 3; p < 0.001) and received combined coronary artery bypass grafting and valve procedures more frequently (29.4% v. 15.9%; p = 0.02) than nonfrail patients. Postoperatively, frail patients had a longer median duration of stay in the cardiovascular intensive care unit (median difference 2.2, 95% CI 1.60-2.79) and hospital (median difference 9.3, 95% CI 8.2-10.3). Hospital mortality was 9.8% among frail patients and 1.0% among nonfrail patients (adjusted hazard ratio 3.84, 95% CI 0.90-16.34).

INTERPRETATION

Preoperative frailty was present in 10% of patients and was associated with a higher risk of morbidity and greater health services use. Preoperative frailty has important implications for the postoperative clinical course and resource utilization of patients undergoing cardiac surgery.

Parental Experiences of the Pediatric Day Surgery Pathway and the Needs for a Digital Gaming Solution: Qualitative Study

BACKGROUND

The parents of hospitalized children are often dissatisfied with waiting times, fasting, discharge criteria, postoperative pain relief, and postoperative guidance. Parents' experiences help care providers to provide effective, family-centered care that responds to parents' needs throughout the day surgery pathway.

OBJECTIVE

The objective of our study was to describe parental experiences of the pediatric day surgery pathway and the needs for a digital gaming solution in order to facilitate the digitalization of these pathways.

METHODS

This was a descriptive qualitative study. The participants (N=31) were parents whose children were admitted to the hospital for the day surgical treatments or magnetic resonance imaging. The data were collected through an unstructured, open-ended questionnaire; an inductive content analysis was conducted to analyze the qualitative data. Reporting of the study findings adheres to the Consolidated Criteria for Reporting Qualitative Research (COREQ) checklist.

RESULTS

Parental experiences of the children's day surgery pathway included 3 main categories: (1) needs for parental guidance, (2) needs for support, and (3) child involved in his or her own pathway (eg, consideration of an individual child and preparation of child for treatment). The needs for a digital gaming solution were identified as 1 main category-the digital gaming solution for children and families to support care. This main category included 3 upper categories: (1) preparing children and families for the day surgery via the solution, (2) gamification in the solution, and (3) connecting people through the solution.

CONCLUSIONS

Parents need guidance and support for their children's day surgery care pathways. A digital gaming solution may be a relevant tool to support communication and to provide information on day surgeries. Families are ready for and are open to digital gaming solutions that provide support and guidance and engage children in the day surgery pathways.

Communication Preferences in Total Joint Arthroplasty: Exploring the Patient Experience Through Generative Research

BACKGROUND

Improving communication and information services for people receiving a total joint (knee or hip) arthroplasty (TJA) depends on the differences in patient communication needs and personal characteristics.

PURPOSE

The purpose of this study was to further examine individual differences in TJA patient preferences regarding communication and information provision.

METHODS

Nineteen patients participated in generative research, which meant they actively reflected on their TJA experiences and communication preferences through creative exercises (e.g., collage making). Audio transcripts of their shared reflections were qualitatively analyzed through an inductive approach.

RESULTS

Some participants wanted detailed health education, others did not. Participants also reported different support needs (e.g., at hospital discharge or during rehabilitation). Moreover, participant preferences for social connections with care providers differed.

CONCLUSIONS

An individual patient's mindset, his or her social support needs, physical condition, and medical history should guide the provision of tailored services.

Fast-track procedures after primary total knee arthroplasty reduce hospital stay by unselected patients: a prospective national multi-centre study

PURPOSE

The aim of this study was to evaluate the impact of fast-track procedures (FTPs) on length of hospital stay after primary total knee arthroplasty (TKA) in a prospective, national, multicentric analysis. The innovative point was that no patient selection was used. The hypothesis was that FTPs reduce hospital stay after primary TKA for non-traumatic conditions compared with the national database.

METHODS

An observational prospective study was conducted in ten centres throughout France. A total of 839 patients included in FTPs were followed up for three months. The average LOS, direct return home rate, unscheduled re-admission rate, and re-intervention rate were compared with those in the national database (93,329 TKAs). Knee society and Oxford score were collected.

RESULTS

The mean LOS was 4.4 ± 3.3 days, while the national base LOS was 6.4 ± 3.1 days (p < 0.001). A total of 560 patients (66.7%) were able to return home, compared with 47,617 (49.6%) in the national database (p < 0.001). Thirty-five patients (4.2%) were re-admitted within 90 days of the intervention, compared with 10,399 (10.8%) in the national database (p < 0.001). Seventeen patients (2.0%) were re-operated upon within 90 days after the TKA, compared with 529 (0.5%) in the national database (p < 0.05).

CONCLUSION

The FTPs used by unselected patients allowed a significant decrease in the mean LOS and in the rate of re-admission and a significant increase of the rate of direct home return after primary TKA compared with the national database. The significant increase in the re-operation rate warrants further investigation. However, FTP should become the standard of care after this intervention.

The digital patient journey solution for patients undergoing elective hip and knee arthroplasty: Protocol for a pragmatic randomized controlled trial

AIM

To describe a randomized controlled trial (RCT) protocol that will evaluate the effectiveness of a digital patient journey (DPJ) solution in improving the outcomes of patients undergoing total hip and knee arthroplasty.

BACKGROUND

There is an urgent need for novel technologies to ensure sustainability, improve patient experience, and empower patients in their own care by providing information, support, and control.

DESIGN

A pragmatic RCT with two parallel arms.

METHODS

The participants randomized assigned to the intervention arm (N = 33) will receive access to the DPJ solution. The participants in the control arm (N = 33) will receive conventional care, which is provided face to face by using paper-based methods. The group allocations will be blinded from the study nurse during the recruitment and baseline measures, as well as from the outcome assessors. Patients with total hip arthroplasty will be followed up for 8-12 weeks, whereas patients with total knee arthroplasty will be followed up for 6-8 weeks. The primary outcome is health-related quality of life, measured by the EuroQol EQ-5D-5L scale. Secondary outcomes include functional recovery, pain, patient experience, and self-efficacy. The first results are expected to be submitted for publication in 2020.

IMPACT

This study will provide information on the health effects and cost benefits of using the DPJ solution to support a patient's preparation for surgery and postdischarge surgical care. If the DPJ solution is found to be effective, its implementation into clinical practice could lead to further improvements in patient outcomes. If the DPJ solution is found to be cost effective for the hospital, it could be used to improve hospital resource efficiency.