The reliability of the functional independence measure: A quantitative review

Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat-Turkey)

A 66-year-old man was suddenly unable to speak, follow directions, or move his right arm and leg. He received tissue plasminogen activator within 90 minutes. Four days later, his speech was limited to effortful answers of yes or no. He could not walk or use his right arm, and self-care tasks required maximal assistance. What advice would you offer him and his family regarding rehabilitation for his disabilities?

https://www.nejm.org/doi/pdf/10.1056/NEJMcp043511

Rehabilitation after Stroke

Neural networks are being used in areas of prediction and classification, the areas where statistical methods have traditionally been used. Both the traditional statistical methods and neural networks are looked upon as competing model-building techniques in literature. This paper carries out a comprehensive review of articles that involve a comparative study of feed forward neural networks and statistical techniques used for prediction and classification problems in various areas of applications. Tabular presentations highlighting the important features of these articles are also provided. This study aims to give useful insight into the capabilities of neural networks and statistical methods used in different kinds of applications.

Review: Neural networks and statistical techniques: A review of applications

Landslide susceptibility mapping : A comparison of logistic regression and neural networks methods in a medium scale study, Hendek Region (Turkey)

ContextChanges in reimbursement have reduced length of stay (LOS) for patients
receiving inpatient medical rehabilitation. The impact of decreased LOS on
functional status, living setting, and mortality is not known.ObjectiveTo examine changes in LOS, functional status, living setting, and mortality
in patients completing inpatient rehabilitation.DesignRetrospective cohort study from 1994 through 2001 using information
submitted to the Uniform Data System for Medical Rehabilitation.Setting and ParticipantsData were analyzed from 744 inpatient medical rehabilitation hospitals
and centers located in 48 US states. A total of 148 807 patient records
from 5 impairment groups (stroke, brain dysfunction, spinal cord dysfunction,
other neurologic conditions, and orthopedic conditions) were examined. Patients’
mean age was 67.8 (SD, 15.8) years; the sample was 59% female and 81% non-Hispanic
white.Main Outcome MeasuresDischarge setting, follow-up living setting, change in functional status,
and mortality.ResultsMedian LOS decreased from 20 to 12 days (P<.001)
from 1994 to 2001. The proportional decrease in median LOS was greatest (42%)
for patients with orthopedic conditions. Mean days to follow-up remained constant
from 89 in 1994 to 90 in 2001. Functional status was clinically stable, while
efficiency (functional status change divided by LOS) increased significantly
(P<.001). Rates of discharge to home and living
at home at follow-up remained stable, ranging from 81% to 93%. However, mortality
at 80- to 180-day follow-up increased from less than 1% in 1994 to 4.7% in
2001.ConclusionsLength of stay for inpatient rehabilitation decreased substantially
from 1994 to 2001. Effectiveness as measured by change in functional status
did not change clinically, and living setting did not change. Efficiency for
functional outcomes improved but mortality at follow-up increased.

https://jamanetwork.com/journals/jama/articlepdf/199580/JOC32252.pdf

Trends in length of stay, living setting, functional outcome, and mortality following medical rehabilitation.

https://www.archives-pmr.org/article/S0003-9993(96)90029-5/pdf

Intermodal agreement of follow-up telephone functional assessment using the functional independence measure in patients with stroke

Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke

Objective: To examine the reliability of the Positive and Negative Affect Schedule (PANAS) in patients 90 and 100 days after discharge from inpatient medical rehabilitation.Design: A prospective study.Subjects: A convenience sample of 31 medical rehabilitation patients.Main measures: The PANAS.Results: The average age was 74 years, 80.7% were female and the average length of stay was 13 days. The test-retest intraclass correlation (ICC) values for the positive and negative affect scales (at the 90 and 100 day follow-up assessment) were 0.79 and 0.93, respectively.Conclusions: Our results show that the PANAS has excellent reliability among a sample of patients who received inpatient medical rehabilitation.

Pamela M. Smith

Papers

Trends in length of stay, living setting, functional outcome, and mortality following medical rehabilitation.

Intermodal agreement of follow-up telephone functional assessment using the functional independence measure in patients with stroke

Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke

Reliability of the Positive and Negative Affect Schedule (PANAS) in medical rehabilitation

Comparison of logistic regression and neural network analysis applied to predicting living setting after hip fracture