Machine Learning Model for Predicting Walking Ability in Lower Limb Amputees DOI Open Access
Aleksandar Knežević, Jovana Arsenovic, Enis Garipi

и другие.

Journal of Clinical Medicine, Год журнала: 2024, Номер 13(22), С. 6763 - 6763

Опубликована: Ноя. 10, 2024

Background/Objectives: The number of individuals with lower limb loss (LLL) is rising. Therefore, identifying the walking potential in LLL and prescribing adequate prosthetic systems are crucial. Various factors can influence participants’ ability, to different extents. aim present study was apply machine learning methods develop a predictive mode. This model assist rehabilitation care teams making informed decisions regarding prosthesis prescription predicting ability LLL. Methods: designed as prospective cross-sectional encompassing 104 consecutively recruited participants (average age 62.1 ± 10.9 years, 80 (76.9%) men) at Medical Rehabilitation Clinic. Demographic, physical, psychological, social status data patients were collected beginning program. At end treatment, K-level estimation functional Timed Up Go Test (TUG), Two-Minute Walking (TMWT) performed. Support vector machines (SVM) used prediction model. Results: Three decision trees created, one for each output, follows: K-level, TUG, TMWT. For all three outputs, there eight significant predictors (balance, body mass index, age, Beck depression inventory, amputation level, muscle strength residual extremity hip extensors, intact (IE) plantar flexors, IE extensors). ninth predictor Multidimensional Scale Perceived Social (MSPSS). Conclusions: Using SVM model, we predict TMWT high accuracy. These clinical assessments could be incorporated into routine practice guide clinicians inform their level ambulation.

Язык: Английский

Loneliness in the Context of Self-Harm Behaviors in Adolescence DOI Creative Commons
Linda Rajhvajn Bulat

IntechOpen eBooks, Год журнала: 2024, Номер unknown

Опубликована: Фев. 21, 2024

Loneliness could both precede and follow poor mental health of adolescents. Since the last decade, problems in adolescence have become widespread heavier; it is important to address what role loneliness has predicting maintaining problems. This chapter summarizes research data that connect with specific internalizing adolescence–non-suicidal self-injury, suicidal thoughts, attempts deliberate self-harm, or without intention. Findings different studies are discussed context interpersonal theory suicide, integrated motivational-volitional model behavior, Nock’s theoretical NSSI, as well evolutionary loneliness. COVID-19 pandemic resulting public measures had major impacts on health, including increased due social distancing isolation, practical implications for future crisis proposed order save adolescents’ health.

Язык: Английский

Процитировано

1
The mediating role of positive feelings in the association between adaptation to disability and positive emotional well-being in a sample of students with congenital physical disabilities DOI Creative Commons
Jean d'Amour MUZIKI,

Marie Paule Uwimbabazi,

Thaoussi Uwera

и другие.

Discover Mental Health, Год журнала: 2024, Номер 4(1)

Опубликована: Дек. 19, 2024

Язык: Английский

Процитировано

0
Machine Learning Model for Predicting Walking Ability in Lower Limb Amputees DOI Open Access
Aleksandar Knežević, Jovana Arsenovic, Enis Garipi

и другие.

Journal of Clinical Medicine, Год журнала: 2024, Номер 13(22), С. 6763 - 6763

Опубликована: Ноя. 10, 2024

Background/Objectives: The number of individuals with lower limb loss (LLL) is rising. Therefore, identifying the walking potential in LLL and prescribing adequate prosthetic systems are crucial. Various factors can influence participants’ ability, to different extents. aim present study was apply machine learning methods develop a predictive mode. This model assist rehabilitation care teams making informed decisions regarding prosthesis prescription predicting ability LLL. Methods: designed as prospective cross-sectional encompassing 104 consecutively recruited participants (average age 62.1 ± 10.9 years, 80 (76.9%) men) at Medical Rehabilitation Clinic. Demographic, physical, psychological, social status data patients were collected beginning program. At end treatment, K-level estimation functional Timed Up Go Test (TUG), Two-Minute Walking (TMWT) performed. Support vector machines (SVM) used prediction model. Results: Three decision trees created, one for each output, follows: K-level, TUG, TMWT. For all three outputs, there eight significant predictors (balance, body mass index, age, Beck depression inventory, amputation level, muscle strength residual extremity hip extensors, intact (IE) plantar flexors, IE extensors). ninth predictor Multidimensional Scale Perceived Social (MSPSS). Conclusions: Using SVM model, we predict TMWT high accuracy. These clinical assessments could be incorporated into routine practice guide clinicians inform their level ambulation.

Язык: Английский

Процитировано

0