MyMedR

Displaying all 3 publications

Abstract:

Sort:

New real-time force monitoring device with enhanced accuracy for evaluation of applied force during the joint mobilization technique

Chia KP, Li OK, Yuong TS, Singh OP, Faudzi AABM, Sornambikai S, et al.

Technol Health Care, 2021;29(4):829-836.
PMID: 33492252 DOI: 10.3233/THC-202414

BACKGROUND: Force Monitoring Devices (FMDs) reported in the literature to monitor applied force during Joint Mobilization Technique (JMT) possess complex design/bulky which alters the execution of treatment, has poor accuracy and is unable to feel the resistance provided by soft tissues limits its usage in the clinical settings.
OBJECTIVES: This study aims to develop a highly accurate, portable FMD and to demonstrate real-time monitoring of force applied by health professionals during JMT without altering its execution.
METHODS: The FMD was constructed using the FlexiForce sensor, potential divider, ATmega 328 microcontroller, custom-written software, and liquid crystal display. The calibration, accuracy, and cyclic repeatability of the FMD were tested from 0 to 90 N applied load with a gold standard universal testing machine. For practical demonstration, the FMD was tested for monitoring applied force by a physiotherapist while performing Maitland's grade I to IV over the 6th cervical vertebra among 30 healthy subjects.
RESULTS: The obtained Bland-Altman plot limits agreement for accuracy, and cyclic repeatability was -1.57 N to 1.22 N, and -1.26 N to 1.26 N, respectively with standard deviation and standard error of the mean values of 3.77% and 0.73% and 2.15% and 0.23%, respectively. The test-retest reliability of the FMD tested by the same researcher at an interval of one week showed an excellent intra-class correlation coefficient of r= 1.00. The obtained force readings for grade I to IV among 30 subjects ranged from 10.33 N to 45.24 N.
CONCLUSIONS: Appreciable performance of the developed FMD suggested that it may be useful to monitor force applied by clinicians during JMT among neck pain subjects and is a useful educational tool for academicians to teach mobilization skills.
New Device for Intrinsic Hand Muscle Strength Measurement: An Alternative to Strain Gauge Handheld Dynamometer

Madhanagopal J, Singh OP, Mohan V, Sathasivam KV, Omar AH, Abdul Kadir MR

Eval Health Prof, 2019 03;42(1):103-113.
PMID: 28868907 DOI: 10.1177/0163278717727568

An accurate measurement of intrinsic hand muscle strength (IHMS) is required by clinicians for effective clinical decision-making, diagnosis of certain diseases, and evaluation of the outcome of treatment. In practice, the clinicians use Intrins-o-meter and Rotterdam Intrinsic Hand Myometer for IHMS measurement. These are quite bulky, expensive, and possess poor interobserver reliability (37-52%) and sensitivity. The purpose of this study was to develop an alternative lightweight, accurate, cost-effective force measurement device with a simple electronic circuit and test its suitability for IHMS measurement. The device was constructed with ketjenblack/deproteinized natural rubber sensor, 1-MΩ potential divider, and Arduino Uno through the custom-written software. Then, the device was calibrated and tested for accuracy and repeatability within the force range of finger muscles (100 N). The 95% limit of agreement in accuracy from -1.95 N to 2.06 N for 10 to 100 N applied load and repeatability coefficient of ±1.91 N or 6.2% was achieved. Furthermore, the expenditure for the device construction was around US$ 53. For a practical demonstration, the device was tested among 16 participants for isometric strength measurement of the ulnar abductor and dorsal interossei. The results revealed that the performance of the device was suitable for IHMS measurement.
Fulltext Classification of SARS-CoV-2 and non-SARS-CoV-2 using machine learning algorithms

Singh OP, Vallejo M, El-Badawy IM, Aysha A, Madhanagopal J, Mohd Faudzi AA

Comput Biol Med, 2021 Sep;136:104650.
PMID: 34329865 DOI: 10.1016/j.compbiomed.2021.104650

Due to the continued evolution of the SARS-CoV-2 pandemic, researchers worldwide are working to mitigate, suppress its spread, and better understand it by deploying digital signal processing (DSP) and machine learning approaches. This study presents an alignment-free approach to classify the SARS-CoV-2 using complementary DNA, which is DNA synthesized from the single-stranded RNA virus. Herein, a total of 1582 samples, with different lengths of genome sequences from different regions, were collected from various data sources and divided into a SARS-CoV-2 and a non-SARS-CoV-2 group. We extracted eight biomarkers based on three-base periodicity, using DSP techniques, and ranked those based on a filter-based feature selection. The ranked biomarkers were fed into k-nearest neighbor, support vector machines, decision trees, and random forest classifiers for the classification of SARS-CoV-2 from other coronaviruses. The training dataset was used to test the performance of the classifiers based on accuracy and F-measure via 10-fold cross-validation. Kappa-scores were estimated to check the influence of unbalanced data. Further, 10 × 10 cross-validation paired t-test was utilized to test the best model with unseen data. Random forest was elected as the best model, differentiating the SARS-CoV-2 coronavirus from other coronaviruses and a control a group with an accuracy of 97.4 %, sensitivity of 96.2 %, and specificity of 98.2 %, when tested with unseen samples. Moreover, the proposed algorithm was computationally efficient, taking only 0.31 s to compute the genome biomarkers, outperforming previous studies.

Filters

Please provide feedback to Administrator ([email protected])

External Links