The potential of prediction models of functioning remains to be fully exploited: A scoping review in the field of spinal cord injury rehabilitation

Hodel, Jsabel; Stucki, Gerold; Prodinger, Birgit

doi:10.1016/j.jclinepi.2021.07.015

Cited by 11 publications

(7 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These outcome measures form the basis for documenting rehabilitation outcomes in terms of rehabilitation duration and can then be used to make informed decisions about appropriate service delivery. In addition, they are needed to calculate rehabilitation trajectories that can provide information about expected outcomes and lead to better rehabilitation planning ( 32 ).…”

Section: Discussionmentioning

confidence: 99%

Health care professionals’ experiences with goal setting during initial rehabilitation after newly acquired spinal cord injury/ disorder – a qualitative focus group study

Lampart

Schäppi²,

Langewitz³

et al. 2022

Front. Rehabilit. Sci.

View full text Add to dashboard Cite

IntroductionGoal setting (GS) is an important aspect of initial spinal cord injury/ disorder (SCI/D) rehabilitation. However, because expected outcomes are individual and often difficult to determine, GS is not straightforward. The aim of this study was to explore the health care professionals' (HCP's) experiences with and perspectives on the goal-setting process (GSP) during initial SCI/D rehabilitation.MethodFive semi-structured focus groups (FG) (22 purposively sampled HCP, mostly in leadership positions, six different professions). The FG were transcribed verbatim. We analyzed the transcripts for qualitative content analysis following Braun and Clarke (2013).ResultsHCP described GS-influencing aspects at the macro, meso and micro levels. At the macro level, participants spoke about restrictions imposed by health insurers or difficulties in planning the post-inpatient setting. Regarding the meso level, HCP spoke of institutional structures and culture that facilitated the GSP. At the micro level, knowledge of the diagnosis, expected outcomes, and individual patient characteristics were mentioned as important to the rehabilitation process. It was important for HCP to be patient and empathetic, to endure negative emotions, to accept that patients need time to adjust to their new situation, and to ensure that they do not lose hope. Open communication and interprofessional collaboration helped overcome barriers in the GSP.DiscussionThis paper shows the complex relationship between external (e.g., health insurers), emotional, and communication aspects. It calls for a comprehensive approach to optimizing the GSP, so that patients' experiences can be fully considered as a basis to identify the most appropriate care pathway.

show abstract

Section: Discussionmentioning

confidence: 99%

Health care professionals’ experiences with goal setting during initial rehabilitation after newly acquired spinal cord injury/ disorder – a qualitative focus group study

Lampart

Schäppi²,

Langewitz³

et al. 2022

Front. Rehabilit. Sci.

View full text Add to dashboard Cite

show abstract

“…In 2021, Hodel et al 22 explored databases such as EBSCOhost CINAHL Complete, PubMed, and IEEE Xplore, to find all publications that developed prediction models for spinal cord injury (SCI). The searches showed that twelve different predictive models were developed in seven unique studies to predict the following clinical outcomes in patients with SCI.…”

Section: Literature Reviewmentioning

confidence: 99%

Prognosis prediction in traumatic brain injury patients using machine learning algorithms

Khalili

Rismani

Nematollahi

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning (ML) algorithms to predict the outcomes of TBI treatment by evaluating demographic features, laboratory data, imaging indices, and clinical features. We used data from 3347 patients admitted to a tertiary trauma centre in Iran from 2016 to 2021. After the exclusion of incomplete data, 1653 patients remained. We used ML algorithms such as random forest (RF) and decision tree (DT) with ten-fold cross-validation to develop the best prediction model. Our findings reveal that among different variables included in this study, the motor component of the Glasgow coma scale, the condition of pupils, and the condition of cisterns were the most reliable features for predicting in-hospital mortality, while the patients’ age takes the place of cisterns condition when considering the long-term survival of TBI patients. Also, we found that the RF algorithm is the best model to predict the short-term mortality of TBI patients. However, the generalized linear model (GLM) algorithm showed the best performance (with an accuracy rate of 82.03 ± 2.34) in predicting the long-term survival of patients. Our results showed that using appropriate markers and with further development, ML has the potential to predict TBI patients’ survival in the short- and long-term.

show abstract

“…In 2021, Hodel et al 27 explored databases such as EBSCOhost CINAHL Complete, PubMed, and IEEE Xplore, to nd all publications that developed prediction models for spinal cord injury (SCI). The searches showed that twelve different predictive models were developed in seven unique studies to predict the following clinical outcomes in patients with SCI.…”

Section: Literature Reviewmentioning

confidence: 99%

Survival Prediction in Traumatic Brain Injury Patients Using Machine Learning Algorithms

Khalili

Rismani

Nematollahi

et al. 2022

Preprint

View full text Add to dashboard Cite

Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning algorithms to predict the outcomes of TBI treatment by evaluating demographic features, laboratory data, imaging indices, and clinical features. We used data from 3347 patients admitted to a tertiary trauma centre in Iran from 2016 to 2021. After the exclusion of incomplete data, 1653 patients remained. We used machine learning algorithms such as Random Forest (RF) and Decision Tree (DT) with ten-fold cross-validation to develop the best prediction model. Our findings reveal that among different variables included in this study, the motor component of the Glasgow Coma Scale, condition of pupils, and condition of cisterns were the most reliable features for predicting in-hospital mortality, while the patients’ age takes the place of cisterns condition when considering the long-term survival of TBI patients. Also, we found that the RF algorithm is the best model to predict the short-term mortality of TBI patients. However, the generalized linear model (GLM) algorithm had the best performance (with an accuracy rate of 82.03 ± 2.34) in predicting the long-term survival of patients. Our results showed that using appropriate markers, and machine learning algorithms can provide a reliable prediction of TBI patients’ survival in the short- and long-term with reliable and easily accessible features of patients.

show abstract

The potential of prediction models of functioning remains to be fully exploited: A scoping review in the field of spinal cord injury rehabilitation

Cited by 11 publications

References 69 publications

Health care professionals’ experiences with goal setting during initial rehabilitation after newly acquired spinal cord injury/ disorder – a qualitative focus group study

Health care professionals’ experiences with goal setting during initial rehabilitation after newly acquired spinal cord injury/ disorder – a qualitative focus group study

Prognosis prediction in traumatic brain injury patients using machine learning algorithms

Survival Prediction in Traumatic Brain Injury Patients Using Machine Learning Algorithms

Contact Info

Product

Resources

About