RESUMO
PURPOSE: To systematically review and summarize the literature on minimal detectable change (MDC) and minimal clinically important difference (MCID) values for the Lower Extremity Functional Scale (LEFS). METHODS: The databases that were searched included PubMed, Embase, Medline, and CINAHL, from database inception to August 2023. The inclusion criteria were studies that examined the MDC or MCID of the LEFS in various patient populations and languages. The data extracted included information regarding test-retest reliability, MDC, MCID, and the intervals between assessments. RESULTS: Twenty-four studies defined MDC and five studies MCID values for the LEFS. They review reported a wide range of MDC values, spanning 11 language versions and a variety of diagnoses, with testing intervals ranging from 1 day to 12 months. MCID values were defined with corresponding area under curve, specificity, and sensitivity metrics for three language versions and a variety of diagnoses across timeframes from 4 weeks to 12 months. CONCLUSIONS: The review defined MDC and MCID values that can be applied in clinical practice for the LEFS across a variety of timeframes, diagnoses, and languages. The findings of this study allow clinicians use the identified MDC and MCID values of the LEFS when interpreting clinical outcome data.
The systematic review identified 24 studies on the minimal detectable change (MDC) and five on the minimal clinically important difference (MCID) of the Lower Extremity Functional Scale (LEFS) across different timeframes, diagnoses, and language versions that can be applied in clinical practice.Clinicians can use the MDC and MCID values of the LEFS to make decisions regarding changes in patient scores over time.Clinicians should be cautious about interpreting the MDC and MCID values contextually, considering factors such as language, timeframe, and specific diagnoses.
RESUMO
BACKGROUND: Computer-aided detection of cognitive impairment garnered increasing attention, offering older adults in the community access to more objective, ecologically valid, and convenient cognitive assessments using multimodal sensing technology on digital devices. METHODOLOGY: In this study, we aimed to develop an automated method for screening cognitive impairment, building on paper- and electronic TMTs. We proposed a novel deep representation learning approach named Semi-Supervised Vector Quantised-Variational AutoEncoder (S2VQ-VAE). Within S2VQ-VAE, we incorporated intra- and inter-class correlation losses to disentangle class-related factors. These factors were then combined with various real-time obtainable features (including demographic, time-related, pressure-related, and jerk-related features) to create a robust feature engineering block. Finally, we identified the light gradient boosting machine as the optimal classifier. The experiments were conducted on a dataset collected from older adults in the community. RESULTS: The experimental results showed that the proposed multi-type feature fusion method outperformed the conventional method used in paper-based TMTs and the existing VAE-based feature extraction in terms of screening performance. CONCLUSIONS: In conclusion, the proposed deep representation learning method significantly enhances the cognitive diagnosis capabilities of behavior-based TMTs and streamlines large-scale community-based cognitive impairment screening while reducing the workload of professional healthcare staff.