Model-based Prediction of Length of Stay for Rehabilitating Stroke Patients

Lin, Chien-Lin; Lin, Pao-Hsuan; Chou, Li‐Wei; Lan, Shou‐Jen; Meng, Nai‐Hsin; Lo, Sui-Foon; Wu, Hung‐Ming

doi:10.1016/s0929-6646(09)60386-7

Cited by 19 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The determinants investigated in those studies include the patient’s functional measures, demographic data, number of comorbidities, neurologic deficits, socioeconomic status, and family support. A retrospective study conducted by Lin et al showed that the modified Barthel Index and FIM were both significant tools in predicting the LOS, although they were limited by their reproducibility [ 8 ]. Additionally, Wee et al performed a prospective study and found that balance, aphasia, number of impairments, and family support at admission had significant contributory predictive effects on the LOS [ 12 ].…”

Section: Discussionmentioning

confidence: 99%

“…The length of hospital stay (LOS) is the principal predictive factor of medical expenses among variables that affect the total costs during hospitalization [ 7 , 8 ]. Accurate estimation of the LOS is important for patients and their family and healthcare providers because it facilitates rehabilitation planning, resource distribution, and healthcare system administration [ 7 , 8 ]. Various studies that aimed to identify the predictive factors of the LOS among stroke patients have been conducted.…”

Section: Introductionmentioning

confidence: 99%

“…Various studies that aimed to identify the predictive factors of the LOS among stroke patients have been conducted. Considering that functional status recovery is the primary goal of PAC, the prediction of the LOS in this stage using a functional evaluation tool is not surprising [ 8 , 9 ]. CARE-C has subtler grading and more comprehensive subscales than the other functional evaluation tools commonly used by previous studies, such as the Barthel Index and Functional Independence Measure (FIM).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting the length of hospital stay of post-acute care patients in Taiwan using the Chinese version of the continuity assessment record and evaluation item set

Hung

Chang

et al. 2017

PLoS ONE

View full text Add to dashboard Cite

BackgroundThe Chinese version of the Continuity Assessment Record and Evaluation (CARE-C) item set was developed to facilitate the assessment of post-acute care (PAC) patients in Taiwan. Considering that the length of hospital stay (LOS) has a significant effect on the total healthcare cost, determining whether the CARE-C scores could predict the LOS of PAC patients is of great interest to the PAC providers.MethodsThis prospective trial included PAC patients with stroke or central nervous system injuries. The demographic data and CARE-C scores were collected after admission and before discharge. A multivariable stepwise linear regression model was used to identify the predictors of the LOS using age, sex, tube placement status, CARE-C component scores at admission, and score differences between admission and discharge as independent variables.ResultsThis study included 178 patients (66 women and 112 men), with a mean age of 61.9 ± 15.6 years. Indwelling urinary catheter placement status at admission (β = 0.241, p = 0.002) was a positive predictor of the LOS, whereas age (β = −0.189, p = 0.010), core transfer subscale score at admission (β = −0.176, p = 0.020), and difference in continence subscale score (β = −0.203, p = 0.008) were negative predictors of the LOS. The model explained 14% of the total variance.ConclusionsIndwelling urinary catheter placement status at admission, age, core transfer subscale score at admission, and difference in the CARE-C continence subscale score were identified as predictors of the LOS. The explanatory power of these predictors might be limited due to the regulations of Taiwan’s National Health Insurance.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the length of hospital stay of post-acute care patients in Taiwan using the Chinese version of the continuity assessment record and evaluation item set

Hung

Chang

et al. 2017

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…They claimed that the back propagation algorithm had not previously been developed for this area. Lin et al [13] explored the prediction of hospital stays for first-time stroke patients in a rehabilitation department by a proportional hazard regression (HR) model. They proposed using the HR model to predict the mean LOS of stroke patients.…”

Section: Introductionmentioning

confidence: 99%

Use of Data Mining Techniques to Determine and Predict Length of Stay of Cardiac Patients

et al. 2013

View full text Add to dashboard Cite

ObjectivesPredicting the length of stay (LOS) of patients in a hospital is important in providing them with better services and higher satisfaction, as well as helping the hospital management plan and managing hospital resources as meticulously as possible. We propose applying data mining techniques to extract useful knowledge and draw an accurate model to predict the LOS of heart patients.MethodsData were collected from patients with coronary artery disease (CAD). The patient records of 4,948 patients who had suffered CAD were included in the analysis. The techniques used are classification with three algorithms, namely, decision tree, support vector machines (SVM), and artificial neural network (ANN). LOS is the target variable, and 36 input variables are used for prediction. A confusion matrix was obtained to calculate sensitivity, specificity, and accuracy.ResultsThe overall accuracy of SVM was 96.4% in the training set. Most single patients (64.3%) had an LOS ≤5 days, whereas 41.2% of married patients had an LOS >10 days. Moreover, the study showed that comorbidity states, such as lung disorders and hemorrhage with drug consumption have an impact on long LOS. The presence of comorbidities, an ejection fraction <2, being a current smoker, and having social security type insurance in coronary artery patients led to longer LOS than other subjects.ConclusionsAll three algorithms are able to predict LOS with various degrees of accuracy. The findings demonstrated that the SVM was the best fit. There was a significant tendency for LOS to be longer in patients with lung or respiratory disorders and high blood pressure.

show abstract

“…Repeating my search for prediction but excluding cancer retrieves nearly 25,000 papers. A very cursory look at the first 20 papers identifies a very wide variety of models: mortality after fungal infection(15); aerobic capacity(16); medication compliance(17); heart disease(18–19); Cesarean section(20), low birthweight(21); transfusion requirements after transplant(22); myodysplasia(23) and stroke rehabilitation(24). …”

Section: Prediction Models For Cancer Are Becoming Ubiquitousmentioning

confidence: 99%

Traditional Statistical Methods for Evaluating Prediction Models Are Uninformative as to Clinical Value: Towards a Decision Analytic Framework

Vickers

Cronin

2010

Seminars in Oncology

110

View full text Add to dashboard Cite

Cancer prediction models are becoming ubiquitous, yet we generally have no idea whether they do more good than harm. This is because current statistical methods for evaluating prediction models are uninformative as to their clinical value. Prediction models are typically evaluated in terms of discrimination or calibration. However, it is generally unclear how high discrimination needs to be before it is considered "high enough"; similarly, there are no rationale guidelines as to the degree of miscalibration that would discount clinical use of a model. Classification tables do present the results of models in more clinically relevant terms, but it is not always clear which of two models is preferable on the basis of a particular classification table, or even whether either model should be used at all. Recent years have seen the development of straightforward decision analytic techniques that evaluate prediction models in terms of their consequences. This depends on the simple approach of weighting true and false positives differently, to reflect that, for example, delaying the diagnosis of a cancer is more harmful than an unnecessary biopsy. Such decision analytic techniques hold the promise of determining whether clinical implementation of prediction models would do more good than harm.

show abstract

Model-based Prediction of Length of Stay for Rehabilitating Stroke Patients

Abstract: We recommend using the PH model for predicting mean LOS when the PH assumption for patients with different clinical characteristics is satisfied. However, the proposed method only applies to rehabilitating stroke patients.

Cited by 19 publications

References 20 publications

Predicting the length of hospital stay of post-acute care patients in Taiwan using the Chinese version of the continuity assessment record and evaluation item set

Predicting the length of hospital stay of post-acute care patients in Taiwan using the Chinese version of the continuity assessment record and evaluation item set

Use of Data Mining Techniques to Determine and Predict Length of Stay of Cardiac Patients

Traditional Statistical Methods for Evaluating Prediction Models Are Uninformative as to Clinical Value: Towards a Decision Analytic Framework

Contact Info

Product

Resources

About