Empirical Mode Decomposition and Decision Tree in Sarcopenia

Using Empirical Mode Decomposition and Decision Tree to Extract the Balance and Gait Features and Classification in Sarcopenia

Sarcopenia is quickly becoming a major global public health issue. Falls are the leading cause of mortality among the elderly, and they must be addressed. The investigators will use machine learning techniques such as empirical mode decomposition technology and decision tree algorithms to extract the characteristics and classification of sarcopenia in this retrospective study in order to offer clinically proven and effective interventional strategies to prevent, stabilize, and reverse sarcopenia.

Study Overview

• Status: Active, not recruiting
• Conditions: Sarcopenia; Fall; Gait, Unsteady; Balance; Distorted

Detailed Description

Sarcopenia is becoming a severe global public health concern as the world's elderly population grows. Sarcopenia is characterized by muscular mass and strength loss, as well as impaired physical performance, and it is frequently connected with negative health outcomes such as falls. Falls are a primary cause of death in older individuals and must be addressed. Sarcopenia is currently diagnosed clinically using three primary technologies: imaging technology, precision medicine, and machine learning. In this study, the investigators will use previously collected data from nearly 200 community-dwelling subjects, including medical history, biochemistry, body composition, balance and gait, electromyography, and functional performance, to extract the characteristics and classification of sarcopenia using machine learning techniques such as empirical mode decomposition technology and decision tree algorithms. The investigators intend to offer clinically proven and effective interventional strategies to prevent, stabilize, and reverse sarcopenia.

• Study Type: Observational
• Enrollment (Anticipated): 200

Contacts and Locations

Study Locations

• Taiwan
  • Changhua, Taiwan, 500
    • Changhua Christian Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 40 years to 90 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

The subject's data were collected from the e-medical chart system.

Description

Inclusion Criteria:

• aged from 40 - 90
• DXA test performed
• blood sample tests were performed

Exclusion Criteria:

• stroke history
• amputation
• cancer related disease

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Retrospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
observation; all subject data were retrieved from databank which is stored in the e-medical chart system.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
center of pressure (COP)	Use computerized dynography to measure the postural sway displacement, velocity (etc., mm, mm/sec)	baseline: subject was enrolled
walking speed	6m, patients can walk with foot orthosis and assistive devices	baseline: subject was enrolled
grip force	Use a grip force meter (kg) to test both hands for test 3 times	baseline: subject was enrolled
step time	Use computerized dynography to measure spatial gait parameter: step time (ms)	baseline: subject was enrolled
stance time	Use computerized dynography to measure spatial gait parameter: stance time (ms)	baseline: subject was enrolled
swing time	Use computerized dynography to measure spatial gait parameter: swing time (ms)	baseline: subject was enrolled
step / stance length	Use computerized dynography to measure spatial gait parameter: step / stance distance (mm)	baseline: subject was enrolled
muscle thickness	Use ultrasound to assess muscles morphological parameter: thickness (mm). Target muscles include quadriceps, hamstring, anterior tibialis, gastrocnemius.	baseline: subject was enrolled
international Quality of Life Assessment Short Form -36 (SF-36)	including 8 health concepts: (1) physical functioning, (2) role limitations because of physical health problems; (3) bodily pain, (4) social functioning, (5) general mental health (psychological distress and psychological wellbeing), (6) role limitations because of emotional problems, (7) vitality (energy/fatigue), (8) general health perceptions. Scoring: answers to each question are scored which are then summed and transformed to a 0 - 100 scale. The lower the score the more disability. The higher the score the less disability i.e., a score of zero is equivalent to maximum disability and a score of 100 is equivalent to no disability.	baseline: subject was enrolled
amplitude of Muscle activity	use electromyography to measure the muscles activity in microvolts (uv) included quadriceps, hamstrings, tibialis anterior, gastrocnemius during subject walking in self-selected speed in 6 meters.	baseline: subject was enrolled
Fear of fall scale	A 15-item self-report questionnaire for measuring fear of falling. Each item is rated on a Likert-type scale from 1 (strongly disagree) to 4 (strongly agree). The total possible score ranges from 15-60, with higher scores indicating greater fear of falling.	baseline: subject was enrolled
Bone density	A bone density test, DEXA, measures the mineral content of the bones in certain areas of the skeleton. A DEXA scan is a type of medical imaging test. It uses very low levels of x-rays to measure how dense participants' bones are. DEXA stands for "dual-energy X-ray absorptiometry." The bone density area includes: Hip and Spine	baseline: subject was enrolled
Body composition	Dual energy x-ray absorptiometry (DEXA) measures bone mineral content (BMC), fat-free mass (FFM).	baseline: subject was enrolled

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
concentration of CRP (C-Reactive Protein)	The concentration of CRP in the blood test. CRP is used mainly as a marker of inflammation.	baseline: subject was enrolled
concentration of ALB (Serum albumin)	The concentration of ALB in the blood test. Albumin is the most important contributor to the maintenance of plasma colloid oncotic pressure; deficiency results in edema.	baseline: subject was enrolled
concentration of Glomerular Filtration Rate (GFR)	The concentration of GFR in the blood test. The glomerular filtration rate is the best test to measure the patient's level of kidney function and determine the stage of kidney disease. It can calculate it from the results of the blood creatinine test.	baseline: subject was enrolled
concentration of Hemoglobin (Hb)	The concentration of Hb in the blood test.	baseline: subject was enrolled
concentration of Glucose SPOT	The concentration of Glucose SPOT in the blood test. TheSpot glucose measurement in epidermal interstitial fluid appears to be a promising alternative to capillary blood glucose estimation	baseline: subject was enrolled
concentration of Cholesterol	The concentration of Cholesterol in the blood test.	baseline: subject was enrolled
concentration of Triglyceride	The concentration of Triglyceride in the blood test.	baseline: subject was enrolled
concentration of Transferrin	The concentration of Transferrin in the blood test.	baseline: subject was enrolled
Berg balance test (BBS)	including 14 items which are scored on a 5 points scale (0-4). The degree of success in achieving each task is given a score of zero (unable) to four (independent), and the final measure is the sum of all of the scores. The item scores are summed, minimum score =0, maximum score = 56	baseline: subject was enrolled
Body Mass Index (BMI)	(body weight) kg/(height) m*(height)m	baseline: subject was enrolled
Mini-mental state examination (MMSE)	It is an 11-question measure that tests five areas of cognitive function: orientation, registration, attention and calculation, recall, and language. The maximum score is 30. A score of 23 or lower is indicative of cognitive impairment.	baseline: subject was enrolled
calf muscle circumference	Use ruler to measure the bilateral calf muscle circumference, It is an anthropometric parameter commonly used in clinical practice.	baseline: subject was enrolled
Timed up and go	To determine fall risk and measure the progress of balance, sit to stand and walking. Patients wear their regular footwear and can use a walking aid, if needed. The patient starts in a seated position. The patient stands up upon therapist's command: walks 3 meters, turns around, walks back to the chair and sits down. The time stops when the patient is seated. To document if the assistive device used. Stopwatch to record the whole task duration.	baseline: subject was enrolled

Collaborators and Investigators

• Sponsor: Changhua Christian Hospital
• Investigators: Principal Investigator: TASEN WEI, MD, Changhua Christian Hospital

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2022
• Primary Completion (Anticipated): January 31, 2024
• Study Completion (Anticipated): July 1, 2024

Study Registration Dates

• First Submitted: May 26, 2022
• First Submitted That Met QC Criteria: May 26, 2022
• First Posted (Actual): May 31, 2022

Study Record Updates

• Last Update Posted (Actual): September 8, 2022
• Last Update Submitted That Met QC Criteria: September 5, 2022
• Last Verified: February 1, 2022

More Information

Terms related to this study

• Keywords: machine learning; empirical mode decomposition; decision tree
• Additional Relevant MeSH Terms: Nervous System Diseases; Neurologic Manifestations; Neuromuscular Manifestations; Pathological Conditions, Anatomical; Muscular Atrophy; Atrophy; Sarcopenia; Gait Disorders, Neurologic
• Other Study ID Numbers: CCH IRB 211235

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No