MyMedR

Displaying publications 21 - 31 of 31 in total

Abstract:

Sort:

Fulltext The classification of movement intention through machine learning models: the identification of significant time-domain EMG features

Mohd Khairuddin I, Sidek SN, P P Abdul Majeed A, Mohd Razman MA, Ahmad Puzi A, Md Yusof H

PeerJ Comput Sci, 2021;7:e379.
PMID: 33817026 DOI: 10.7717/peerj-cs.379

Electromyography (EMG) signal is one of the extensively utilised biological signals for predicting human motor intention, which is an essential element in human-robot collaboration platforms. Studies on motion intention prediction from EMG signals have often been concentrated on either classification and regression models of muscle activity. In this study, we leverage the information from the EMG signals, to detect the subject's intentions in generating motion commands for a robot-assisted upper limb rehabilitation platform. The EMG signals are recorded from ten healthy subjects' biceps muscle, and the movements of the upper limb evaluated are voluntary elbow flexion and extension along the sagittal plane. The signals are filtered through a fifth-order Butterworth filter. A number of features were extracted from the filtered signals namely waveform length (WL), mean absolute value (MAV), root mean square (RMS), standard deviation (SD), minimum (MIN) and maximum (MAX). Several different classifiers viz. Linear Discriminant Analysis (LDA), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and k-Nearest Neighbour (k-NN) were investigated on its efficacy to accurately classify the pre-intention and intention classes based on the significant features identified (MIN and MAX) via Extremely Randomised Tree feature selection technique. It was observed from the present investigation that the DT classifier yielded an excellent classification with a classification accuracy of 100%, 99% and 99% on training, testing and validation dataset, respectively based on the identified features. The findings of the present investigation are non-trivial towards facilitating the rehabilitation phase of patients based on their actual capability and hence, would eventually yield a more active participation from them.

Matched MeSH terms: Decision Trees
Machine Learning and Deep Learning Approaches in Breast Cancer Survival Prediction Using Clinical Data

Kalafi EY, Nor NAM, Taib NA, Ganggayah MD, Town C, Dhillon SK

Folia Biol. (Praha), 2019;65(5-6):212-220.
PMID: 32362304

Breast cancer survival prediction can have an extreme effect on selection of best treatment protocols. Many approaches such as statistical or machine learning models have been employed to predict the survival prospects of patients, but newer algorithms such as deep learning can be tested with the aim of improving the models and prediction accuracy. In this study, we used machine learning and deep learning approaches to predict breast cancer survival in 4,902 patient records from the University of Malaya Medical Centre Breast Cancer Registry. The results indicated that the multilayer perceptron (MLP), random forest (RF) and decision tree (DT) classifiers could predict survivorship, respectively, with 88.2 %, 83.3 % and 82.5 % accuracy in the tested samples. Support vector machine (SVM) came out to be lower with 80.5 %. In this study, tumour size turned out to be the most important feature for breast cancer survivability prediction. Both deep learning and machine learning methods produce desirable prediction accuracy, but other factors such as parameter configurations and data transformations affect the accuracy of the predictive model.

Matched MeSH terms: Decision Trees
Fulltext Economic Evaluation and Budget Impact Analysis of Vaccination against Haemophilus influenzae Type b Infection in Thailand

Kotirum S, Muangchana C, Techathawat S, Dilokthornsakul P, Wu DB, Chaiyakunapruk N

Front Public Health, 2017;5:289.
PMID: 29209602 DOI: 10.3389/fpubh.2017.00289

Current study aimed to estimate clinical and economic outcomes of providing the Haemophilus influenzae type b (Hib) vaccination as a national vaccine immunization program in Thailand. A decision tree combined with Markov model was developed to simulate relevant costs and health outcomes covering lifetime horizon in societal and health care payer perspectives. This analysis considered children aged under 5 years old whom preventive vaccine of Hib infection are indicated. Two combined Hib vaccination schedules were considered: three-dose series (3 + 0) and three-dose series plus a booster does (3 + 1) compared with no vaccination. Budget impact analysis was also performed under Thai government perspective. The outcomes were reported as Hib-infected cases averted and incremental cost-effectiveness ratios (ICERs) in 2014 Thai baht (THB) ($) per quality-adjusted life year (QALY) gained. In base-case scenario, the model estimates that 3,960 infected cases, 59 disability cases, and 97 deaths can be prevented by national Hib vaccination program. The ICER for 3 + 0 schedule was THB 1,099 ($34) per QALY gained under societal perspective. The model was sensitive to pneumonia incidence among aged under 5 years old and direct non-medical care cost per episode of Hib pneumonia. Hib vaccination is very cost-effective in the Thai context. The budget impact analysis showed that Thai government needed to invest an additional budget of 110 ($3.4) million to implement Hib vaccination program. Policy makers should consider our findings for adopting this vaccine into national immunization program.

Matched MeSH terms: Decision Trees
Fulltext Evaluation of risk factors for prolonged invasive mechanical ventilation in Paediatric Intensive Care Unit (PICU)

Ismail, I., Yap, B.W., Abidin, A.S.Z.

Pertanika Journal of Science & Technology, 2017;25(3):811-824.
MyJurnal

Prolonged mechanical ventilation (PMV) is associated with increase in mortality and resource utilisation as well as hospitalisation costs. This study evaluates the risk factors of PMV. A retrospective study was conducted involving 890 paediatric patients comprising 237 neonates, 306 infants, 223 of pre-school age and 124 who are of school going age. The data mining decision trees algorithms and logistic regression was employed to develop predictive models for each age category. The independent variables were classified into four categories, that is, demographic data, admission factors, medical factors and score factors. The dependent variable is the duration of ventilation where it is categorized 0 denoting non-PMV and 1 denoting PMV. The performances of three decision tree models (CHAID, CART and C5.0) and logistic regression were compared to determine the best model. The results indicated that the decision tree outperformed the logistic regression model for all age categories, given its good accuracy rate for testing dataset. Decision trees results identified length of stay and inotropes as significant risk factors in all age categories. PRISM 12 hours and principal diagnosis were identified as significant risk factors for infants.

Matched MeSH terms: Decision Trees
Cost-effectiveness analysis of HLA-B*15:02 screening before treatment of epilepsy in Indonesia

Tanoto E, Khosama H, Jehosua S, Sekeon SAS, Karema W, Mawuntu AHP, et al.

Epilepsy Behav, 2024 Jun;155:109787.
PMID: 38657484 DOI: 10.1016/j.yebeh.2024.109787

INTRODUCTION: Adverse skin reactions due to drugs such as Stevens Johnson Syndrome (SJS) and Toxic Epidermal Necrolysis (TEN) occur in 3% of people receiving anti epileptic drugs (AED). Although SJS/TEN has a low incidence, the mortality and morbidity rates are high. Indonesia has not adopted HLA-B*1502 screening prior to administration of carbamazepine (CBZ), although previous studies found a relationship between HLA-B*1502 and SJS/TEN.
METHODS: A hybrid decision tree and Markov model was developed to evaluate three strategies for treating newly diagnosed focal epilepsy: CBZ direct therapy, levetiracetam (LEV) direct therapy, and therapy based on HLA-B*15:02 test results. From a societal perspective, base case and sensitivity analyses were carried out over a lifetime.
RESULTS: Direct administration of CBZ appears to have a slightly lower average cost than the HLA-B*15:02 allele screening strategy. The increase in quality-adjusted life year (QALY) in HLA-B*15:02 screening before treatment related to the cost difference reached 0.519 with an incremental cost-effectiveness ratio (ICER) of around USD 984 per unit of QALY acquisition. Direct treatment of LEV increased treatment costs by almost USD 2000 on average compared to the standard CBZ strategy. The increase in QALY is 0.834 in direct levetiracetam treatment, with an ICER of around USD 2230 for each QALY processing.
CONCLUSION: Calculation of the cost-effectiveness of lifetime epilepsy therapy in this study found that the initial screening strategy with the HLA-B*15:02 test was the most cost-effective.

Matched MeSH terms: Decision Trees
A decision tree for differentiating multiple system atrophy from Parkinson's disease using 3-T MR imaging

Nair SR, Tan LK, Mohd Ramli N, Lim SY, Rahmat K, Mohd Nor H

Eur Radiol, 2013 Jun;23(6):1459-66.
PMID: 23300042 DOI: 10.1007/s00330-012-2759-9

OBJECTIVE: To develop a decision tree based on standard magnetic resonance imaging (MRI) and diffusion tensor imaging to differentiate multiple system atrophy (MSA) from Parkinson's disease (PD).
METHODS: 3-T brain MRI and DTI (diffusion tensor imaging) were performed on 26 PD and 13 MSA patients. Regions of interest (ROIs) were the putamen, substantia nigra, pons, middle cerebellar peduncles (MCP) and cerebellum. Linear, volumetry and DTI (fractional anisotropy and mean diffusivity) were measured. A three-node decision tree was formulated, with design goals being 100 % specificity at node 1, 100 % sensitivity at node 2 and highest combined sensitivity and specificity at node 3.
RESULTS: Nine parameters (mean width, fractional anisotropy (FA) and mean diffusivity (MD) of MCP; anteroposterior diameter of pons; cerebellar FA and volume; pons and mean putamen volume; mean FA substantia nigra compacta-rostral) showed statistically significant (P < 0.05) differences between MSA and PD with mean MCP width, anteroposterior diameter of pons and mean FA MCP chosen for the decision tree. Threshold values were 14.6 mm, 21.8 mm and 0.55, respectively. Overall performance of the decision tree was 92 % sensitivity, 96 % specificity, 92 % PPV and 96 % NPV. Twelve out of 13 MSA patients were accurately classified.
CONCLUSION: Formation of the decision tree using these parameters was both descriptive and predictive in differentiating between MSA and PD.
KEY POINTS: • Parkinson's disease and multiple system atrophy can be distinguished on MR imaging. • Combined conventional MRI and diffusion tensor imaging improves the accuracy of diagnosis. • A decision tree is descriptive and predictive in differentiating between clinical entities. • A decision tree can reliably differentiate Parkinson's disease from multiple system atrophy.

Matched MeSH terms: Decision Trees
Cost-utility analysis of an adjunctive recombinant activated factor VIIa for on-demand treatment of bleeding episodes in dengue haemorrhagic fever

Naing C, Poovorawan Y, Mak JW, Aung K, Kamolratankul P

Blood Coagul Fibrinolysis, 2015 Jun;26(4):403-7.
PMID: 25692521 DOI: 10.1097/MBC.0000000000000280

The present study aimed to assess the cost-utility analysis of using an adjunctive recombinant activated factor VIIa (rFVIIa) in children for controlling life-threatening bleeding in dengue haemorrhagic fever (DHF)/dengue shock syndrome (DSS). We constructed a decision-tree model, comparing a standard care and the use of an additional adjuvant rFVIIa for controlling life-threatening bleeding in children with DHF/DSS. Cost and utility benefit were estimated from the societal perspective. The outcome measure was cost per quality-adjusted life years (QALYs). Overall, treatment with adjuvant rFVIIa gained QALYs, but the total cost was higher. The incremental cost-utility ratio for the introduction of adjuvant rFVIIa was $4241.27 per additional QALY. Sensitivity analyses showed the utility value assigned for calculation of QALY was the most sensitive parameter. We concluded that despite high cost, there is a role for rFVIIa in the treatment of life-threatening bleeding in patients with DHF/DSS.

Matched MeSH terms: Decision Trees
Computational prediction of Mycoplasma hominis proteins targeting in nucleus of host cell and their implication in prostate cancer etiology

Khan S, Zakariah M, Palaniappan S

Tumour Biol., 2016 Aug;37(8):10805-13.
PMID: 26874727 DOI: 10.1007/s13277-016-4970-9

Cancer has long been assumed to be a genetic disease. However, recent evidence supports the enigmatic connection of bacterial infection with the growth and development of various types of cancers. The cause and mechanism of the growth and development of prostate cancer due to Mycoplasma hominis remain unclear. Prostate cancer cells are infected and colonized by enteroinvasive M. hominis, which controls several factors that can affect prostate cancer growth in susceptible persons. We investigated M. hominis proteins targeting the nucleus of host cells and their implications in prostate cancer etiology. Many vital processes are controlled in the nucleus, where the proteins targeting M. hominis may have various potential implications. A total of 29/563 M. hominis proteins were predicted to target the nucleus of host cells. These include numerous proteins with the capability to alter normal growth activities. In conclusion, our results emphasize that various proteins of M. hominis targeted the nucleus of host cells and were involved in prostate cancer etiology through different mechanisms and strategies.

Matched MeSH terms: Decision Trees
Fulltext Cost-effectiveness analysis of ultrasonography screening for nonalcoholic fatty liver disease in metabolic syndrome patients

Phisalprapa P, Supakankunti S, Charatcharoenwitthaya P, Apisarnthanarak P, Charoensak A, Washirasaksiri C, et al.

Medicine (Baltimore), 2017 Apr;96(17):e6585.
PMID: 28445256 DOI: 10.1097/MD.0000000000006585

BACKGROUND: Nonalcoholic fatty liver disease (NAFLD) can be diagnosed early by noninvasive ultrasonography; however, the cost-effectiveness of ultrasonography screening with intensive weight reduction program in metabolic syndrome patients is not clear. This study aims to estimate economic and clinical outcomes of ultrasonography in Thailand.
METHODS: Cost-effectiveness analysis used decision tree and Markov models to estimate lifetime costs and health benefits from societal perspective, based on a cohort of 509 metabolic syndrome patients in Thailand. Data were obtained from published literatures and Thai database. Results were reported as incremental cost-effectiveness ratios (ICERs) in 2014 US dollars (USD) per quality-adjusted life year (QALY) gained with discount rate of 3%. Sensitivity analyses were performed to assess the influence of parameter uncertainty on the results.
RESULTS: The ICER of ultrasonography screening of 50-year-old metabolic syndrome patients with intensive weight reduction program was 958 USD/QALY gained when compared with no screening. The probability of being cost-effective was 67% using willingness-to-pay threshold in Thailand (4848 USD/QALY gained). Screening before 45 years was cost saving while screening at 45 to 64 years was cost-effective.
CONCLUSIONS: For patients with metabolic syndromes, ultrasonography screening for NAFLD with intensive weight reduction program is a cost-effective program in Thailand. Study can be used as part of evidence-informed decision making.
TRANSLATIONAL IMPACTS: Findings could contribute to changes of NAFLD diagnosis practice in settings where economic evidence is used as part of decision-making process. Furthermore, study design, model structure, and input parameters could also be used for future research addressing similar questions.

Matched MeSH terms: Decision Trees
A cost-utility analysis of dabigatran, enoxaparin, and usual care for venous thromboprophylaxis after hip or knee replacement surgery in Thailand

Kotirum S, Chongmelaxme B, Chaiyakunapruk N

J Thromb Thrombolysis, 2017 Feb;43(2):252-262.
PMID: 27704332 DOI: 10.1007/s11239-016-1433-5

To analyze the cost-utility of oral dabigatran etexilate, enoxaparin sodium injection, and no intervention for venous thromboembolism (VTE) prophylaxis after total hip or knee replacement (THR/TKR) surgery among Thai patients. A cost-utility analysis using a decision tree model was conducted using societal and healthcare payers' perspectives to simulate relevant costs and health outcomes covering a 3-month time horizon. Costs were adjusted to year 2014. The willingness-to-pay threshold of THB 160,000 (USD 4926) was used. One-way sensitivity and probabilistic sensitivity analyses using a Monte Carlo simulation were performed. Compared with no VTE prophylaxis, dabigatran and enoxaparin after THR and TKR surgery incurred higher costs and increased quality adjusted life years (QALYs). However, their incremental cost-effectiveness ratios were high above the willingness to pay. Compared with enoxaparin, dabigatran for THR/TKR lowered VTE complications but increased bleeding cases; dabigatran was cost-saving by reducing the costs [by THB 3809.96 (USD 117.30) for THR] and producing more QALYs gained (by 0.00013 for THR). Dabigatran (vs. enoxaparin) had a 98 % likelihood of being cost effective. Dabigatran is cost-saving compared to enoxaparin for VTE prophylaxis after THR or TKR under the Thai context. However, both medications are not cost-effective compared to no thromboprophylaxis.

Matched MeSH terms: Decision Trees
Predicting the risk of exacerbation in patients with chronic obstructive pulmonary disease using home telehealth measurement data

Mohktar MS, Redmond SJ, Antoniades NC, Rochford PD, Pretto JJ, Basilakis J, et al.

Artif Intell Med, 2015 Jan;63(1):51-9.
PMID: 25704112 DOI: 10.1016/j.artmed.2014.12.003

BACKGROUND: The use of telehealth technologies to remotely monitor patients suffering chronic diseases may enable preemptive treatment of worsening health conditions before a significant deterioration in the subject's health status occurs, requiring hospital admission.
OBJECTIVE: The objective of this study was to develop and validate a classification algorithm for the early identification of patients, with a background of chronic obstructive pulmonary disease (COPD), who appear to be at high risk of an imminent exacerbation event. The algorithm attempts to predict the patient's condition one day in advance, based on a comparison of their current physiological measurements against the distribution of their measurements over the previous month.
METHOD: The proposed algorithm, which uses a classification and regression tree (CART), has been validated using telehealth measurement data recorded from patients with moderate/severe COPD living at home. The data were collected from February 2007 to January 2008, using a telehealth home monitoring unit.
RESULTS: The CART algorithm can classify home telehealth measurement data into either a 'low risk' or 'high risk' category with 71.8% accuracy, 80.4% specificity and 61.1% sensitivity. The algorithm was able to detect a 'high risk' condition one day prior to patients actually being observed as having a worsening in their COPD condition, as defined by symptom and medication records.
CONCLUSION: The CART analyses have shown that features extracted from three types of physiological measurements; forced expiratory volume in 1s (FEV1), arterial oxygen saturation (SPO2) and weight have the most predictive power in stratifying the patients condition. This CART algorithm for early detection could trigger the initiation of timely treatment, thereby potentially reducing exacerbation severity and recovery time and improving the patient's health. This study highlights the potential usefulness of automated analysis of home telehealth data in the early detection of exacerbation events among COPD patients.

Matched MeSH terms: Decision Trees

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links