Clinical Prediction Rule for Declines in Activities of Daily Living at 6 Months After Surgery for Hip Fracture Repair

Tanaka, Ryo; Umehara, Takuya; Fujimura, Takafumi; Ozawa, Junya

doi:10.1016/j.apmr.2016.07.016

Cited by 22 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification and regression tree (CART) analysis was used to investigate the complex interaction of factors related to discharge destination in the previous analyses. Binary trees were used to split predictor variables recursively with yes/no questions about each variable [23]. The CART algorithm produced a tree from the root by selecting the best predictor variable, defined as that with the lowest Gini index value as an internal node [24].…”

Section: Discussionmentioning

confidence: 99%

Clinical Indicators and Thresholds for Determining Discharge Destination from Acute Stroke Ward

et al. 2019

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Clinical Indicators and Thresholds for Determining Discharge Destination from Acute Stroke Ward

et al. 2019

View full text Add to dashboard Cite

“…A previous study recommended the application of CPRs that combine individual factors and medical test scores as a tool for quantifying functional prognosis and treatment effects 15 ) . For example, there have been CPRs associated with pain [16][17][18] and ADL 19 ) in previous studies. However, there is no established CPR for individuals undergoing TKA to predict successful early recovery of knee ROM.…”

mentioning

confidence: 89%

Clinical prediction rule for early recovery of knee range of motion after total knee arthroplasty: A prospective cohort study

Amano

Tanaka

2020

Phys Ther Res

Self Cite

View full text Add to dashboard Cite

To derive a clinical prediction rule for early recovery of knee range of motion after total knee arthroplasty. Methods: This prospective cohort study evaluated the data of 273 individuals undergoing primary total knee arthroplasty. The individual factors, the physical and motor function data were assessed preoperatively upon admission as a baseline survey. The knee joint extension angle and knee joint flexion angle were re-evaluated on postoperative day 14 as a follow-up. The recovery group comprised individuals with a knee joint extension angle of more than-5 degrees and knee joint flexion angle of more than 110 degrees on postoperative day 14. The other patients constituted the non-recovery group. Multivariate logistic regression analysis was used for deriving a clinical prediction rule. Results: The results indicated that the use of a cane, knee joint extension and flexion angles, and Timed Up and Go test time were significant factors for predicting early recovery of knee range of motion after total knee arthroplasty. Furthermore, a clinical prediction rule was derived and included the use of a cane, knee joint extension angle !-15 degrees, knee joint flexion angle ! 125 degrees, and a Timed Up and Go test time < 11.2 s. A total clinical prediction rule score ! 8 indicated a positive likelihood ratio of more than 10 for a successful outcome and the post-test probability was approximately 95%. Conclusions: The derived clinical prediction rule might be a useful screening tool for proper postoperative goal setting and the establishment of individualized physical therapy programs.

show abstract

“…Many studies attempted to predict ADLs in a specific population, i.e., related to a disease or injury [13][14][15], while others are more general. In one study, machine learning (ML) methods were linked to biomedical ontologies to predict functional status [16], achieving predictive accuracy of 0.6.…”

Section: Introductionmentioning

confidence: 99%

Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients

Wojtusiak

Asadzadehzanjani

Levy³

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Assessment of functional ability, including activities of daily living (ADLs), is a manual process completed by skilled health professionals. In the presented research, an automated decision support tool, the Computational Barthel Index Tool (CBIT), was constructed that can automatically assess and predict probabilities of current and future ADLs based on patients’ medical history. Methods The data used to construct the tool include the demographic information, inpatient and outpatient diagnosis codes, and reported disabilities of 181,213 residents of the Department of Veterans Affairs’ (VA) Community Living Centers. Supervised machine learning methods were applied to construct the CBIT. Temporal information about times from the first and the most recent occurrence of diagnoses was encoded. Ten-fold cross-validation was used to tune hyperparameters, and independent test sets were used to evaluate models using AUC, accuracy, recall and precision. Random forest achieved the best model quality. Models were calibrated using isotonic regression. Results The unabridged version of CBIT uses 578 patient characteristics and achieved average AUC of 0.94 (0.93–0.95), accuracy of 0.90 (0.89–0.91), precision of 0.91 (0.89–0.92), and recall of 0.90 (0.84–0.95) when re-evaluating patients. CBIT is also capable of predicting ADLs up to one year ahead, with accuracy decreasing over time, giving average AUC of 0.77 (0.73–0.79), accuracy of 0.73 (0.69–0.80), precision of 0.74 (0.66–0.81), and recall of 0.69 (0.34–0.96). A simplified version of CBIT with 50 top patient characteristics reached performance that does not significantly differ from full CBIT. Conclusion Discharge planners, disability application reviewers and clinicians evaluating comparative effectiveness of treatments can use CBIT to assess and predict information on functional status of patients.

show abstract

Clinical Prediction Rule for Declines in Activities of Daily Living at 6 Months After Surgery for Hip Fracture Repair

Abstract: CPRs with moderate accuracy were developed to predict declines in ADL at 6 months after surgery for hip fracture repair.

Cited by 22 publications

References 30 publications

Clinical Indicators and Thresholds for Determining Discharge Destination from Acute Stroke Ward

Clinical Indicators and Thresholds for Determining Discharge Destination from Acute Stroke Ward

Clinical prediction rule for early recovery of knee range of motion after total knee arthroplasty: A prospective cohort study

Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients

Contact Info

Product

Resources

About