RESUMEN
BACKGROUND: The prosthetic alignment procedure considers biomechanical, anatomical and comfort characteristics of the amputee to achieve an acceptable gait. Prosthetic malalignment induces long-term disease. The assessment of alignment is highly variable and subjective to the experience of the prosthetist, so the use of machine learning could assist the prosthetist during the judgment of optimal alignment. RESEARCH OBJECTIVE: To assist the prosthetist during the assessment of prosthetic alignment using a new computational protocol based on machine learning. METHODS: Sixteen transfemoral amputees were recruited for training and validation of the alignment protocol. Four misalignments and one nominal alignment were performed. Eleven prosthetic limb ground reaction force parameters were recorded. A support vector machine with a Gaussian kernel radial basis function and a Bayesian regularization neural network were trained to predict the alignment condition, as well as the magnitude and angle of required to align the prosthesis correctly. The alignment protocol was validated by one junior and one senior prosthetist during the prosthetic alignment of two transfemoral amputees. RESULTS: The support vector machine-based model detected the nominal alignment 92.6 % of the time. The neural network recovered 94.11 % of the angles needed to correct the prosthetic misalignment with a fitting error of 0.51°. During the validation of the alignment protocol, the computational models and the prosthetists agreed on the alignment assessment. The gait quality evaluated by the prosthetists reached a satisfaction level of 8/10 for the first amputee and 9.6/10 for the second amputee. IMPORTANCE: The new computational prosthetic alignment protocol is a tool that helps the prosthetist during the prosthetic alignment procedure thereby decreasing the likelihood of gait deviations and musculoskeletal diseases associated with misalignments and consequently improving the amputees-prosthesis adherence.
Asunto(s)
Amputados , Miembros Artificiales , Humanos , Teorema de Bayes , Fenómenos Biomecánicos , Marcha , Extremidades , Diseño de PrótesisRESUMEN
BACKGROUND: Lower limb prosthetic alignment is a procedure mostly subjective. A prosthetic misaligned induces gait deviations and long-term joint diseases. The alignment effects for each lower limb and the stump stays uncertain. RESEARCH OBJECTIVE: To identify the effect of the transfemoral alignment prosthesis on ground reaction forces and thermal images of the residual limb. METHODS: The effect of misalignment and nominal alignment was evaluated in sixteen transfemoral amputees. The nominal alignment was considered as the optimal alignment for each subject. Misalignment included random variations in the anterior-posterior and medial-lateral translation of the prosthetic foot and the angle of flexion-extension, abduction-adduction, and internal-external rotation of the socket and prosthetic foot. The control group consisted of fifteen non-amputee individuals. The ground reaction force parameters and stump temperature were analyzed for each alignment condition. The statistical analysis included the one-way ANOVA, Kruskal-Wallis, and multiple comparison tests. RESULTS: The prosthesis did not produce statistically significant changes in the average temperature of residual limbs. However, the temperature distribution on the stump skin was different (P < 0.05). The transfemoral prosthesis misalignment produced an irregular heat diffusion on the anterior, posterior, and lateral sides of the stump contour compared to the nominal alignment (P < 0.05). The sound limb did not show differences between nominal alignments and misalignments for most ground reaction force parameters. For almost all GRF parameters, significant differences were observed for the prosthetic limb between misalignment and nominal alignment (P < 0.001). The symmetry indices of ground reaction force parameters of transfemoral amputees did not show any kind of significant improvements after aligning the prosthesis nominally. SIGNIFICANCE: The stump's temperature distribution and the ground reaction force findings for the prosthetic limb provide a better understanding of the alignment procedure of the transfemoral prosthesis and improve the amputees' compliance to the prosthesis.
Asunto(s)
Amputados , Miembros Artificiales , Fenómenos Biomecánicos , Marcha , Humanos , Extremidad Inferior , Diseño de Prótesis , TemperaturaRESUMEN
Resumen Objetivo: evaluar el efecto de un programa supervisado sobre el consumo de oxígeno, la función y la calidad de vida en pacientes con falla cardiaca. Diseño y métodos: ensayo clínico con doble enmascaramiento de grupos paralelos, en pacientes con falla cardiaca estado funcional II-IV por más de 6 meses con fracción de eyección < 40%. El desenlace primario fue el consumo de oxígeno pico a las 8 semanas. Resultados: veintitrés pacientes fueron asignados al grupo de intervención y 26 al grupo de control. Cinco fallecieron, 4 se negaron a completar todas las evaluaciones y 1 no realizó la prueba de ejercicio cardiopulmonar. Diecisiete fueron analizados en el grupo de intervención y 20 en el grupo de control. Respecto al VO2 pico, no se observaron cambios estadísticamente significativos al final del programa de intervención a las 8 semanas (-13,3 ± 3,9 ml/kg/min en el grupo de intervención frente a 14,8 ± 4,6 ml/kg/min en el grupo de control, p = 0,31). Las evaluaciones de funcionalidad y calidad de vida no difirieron entre los grupos a las 8 semanas o 6 meses. Sin embargo, hubo una mejoría en ambos grupos en los resultados de funcionalidad y calidad de vida. Conclusión: el uso de un programa de ejercicio protocolizado y supervisado en pacientes con falla cardiaca con una fracción de eyección < 40%, no produce cambios significativos en el VO2 pico en comparación con un programa comunitario.
Abstract Objective: To evaluate the effect of a supervised exercise program on oxygen consumption, function, and quality of life in patients with heart failure. Design and methods: A double-blind clinical trial, with parallel groups, conducted on patients with functional stage II-IV heart failure for more than 6 months and with an ejection fraction of < 40%. The primary outcome was the peak oxygen consumption at 8 weeks. Results: A total of 23 patients were assigned to the intervention group and 26 to the control group. Of those, 5 died, 4 failed to complete all the evaluations, and 1 did not perform the cardiopulmonary exercise test. Finally, 17 patients were analysed in the intervention group and 20 in the control group. As regards the peak VO2, no statistically significant changes were observed at the end of the intervention program at 8 weeks (-13.3 ± 3.9 ml/kg/min in the intervention group compared to 14.8 ± 4.6 ml/kg/min in the control group, P=.31). There were no differences between the groups in the functional evaluations and the quality of life at 8 weeks or 6 months. However, the results showed an improvement in the functionality and quality of life in both groups. Conclusion: The use of a standard and supervised exercise program by patients with heart failure with an ejection fraction < 40% does not lead to significant changes in the peak VO2, when compared to a community program.