MyMedR

Displaying publications 1 - 20 of 30 in total

Abstract:

Sort:

Fulltext Personality prediction based on social media using decision tree algorithm

Tan Lee CY, Ngatirin NR, Zainol Z

Pertanika Journal of Science & Technology, 2017;25(104):237-248.
MyJurnal

Personality represents the mixture of features and qualities that built an individual’s distinctive characters including thinking, feeling and behaving. Traditionally, self-assessment method via questionnaire is the most common means to identify personality. Since recommender systems and advertisement
campaigns have evolved rapidly, personality computing has become a popular research field to provide personalisation to users. Currently, researchers have utilised social media data for automatically predicting personality. However, it is complex to mine the social media data as they are noisy, free-format, and
of varying length and multimedia. This paper proposes a decision tree C4.5 algorithm to automatically predict personality based on Big Five model. The Big Five Inventory and ZeroR algorithm were included to be served as the baseline for performance evaluation. Experimental evaluation demonstrated that C4.5
performs better than ZeroR in terms of accuracy.
Keywords: Big Five, decision tree, personality, social media

Matched MeSH terms: Decision Trees
Fulltext Proposal of a Clinical Decision Tree Algorithm Using Factors Associated with Severe Dengue Infection

Tamibmaniam J, Hussin N, Cheah WK, Ng KS, Muninathan P

PLoS One, 2016;11(8):e0161696.
PMID: 27551776 DOI: 10.1371/journal.pone.0161696

BACKGROUND: WHO's new classification in 2009: dengue with or without warning signs and severe dengue, has necessitated large numbers of admissions to hospitals of dengue patients which in turn has been imposing a huge economical and physical burden on many hospitals around the globe, particularly South East Asia and Malaysia where the disease has seen a rapid surge in numbers in recent years. Lack of a simple tool to differentiate mild from life threatening infection has led to unnecessary hospitalization of dengue patients.

METHODS: We conducted a single-centre, retrospective study involving serologically confirmed dengue fever patients, admitted in a single ward, in Hospital Kuala Lumpur, Malaysia. Data was collected for 4 months from February to May 2014. Socio demography, co-morbidity, days of illness before admission, symptoms, warning signs, vital signs and laboratory result were all recorded. Descriptive statistics was tabulated and simple and multiple logistic regression analysis was done to determine significant risk factors associated with severe dengue.

RESULTS: 657 patients with confirmed dengue were analysed, of which 59 (9.0%) had severe dengue. Overall, the commonest warning sign were vomiting (36.1%) and abdominal pain (32.1%). Previous co-morbid, vomiting, diarrhoea, pleural effusion, low systolic blood pressure, high haematocrit, low albumin and high urea were found as significant risk factors for severe dengue using simple logistic regression. However the significant risk factors for severe dengue with multiple logistic regressions were only vomiting, pleural effusion, and low systolic blood pressure. Using those 3 risk factors, we plotted an algorithm for predicting severe dengue. When compared to the classification of severe dengue based on the WHO criteria, the decision tree algorithm had a sensitivity of 0.81, specificity of 0.54, positive predictive value of 0.16 and negative predictive of 0.96.

CONCLUSION: The decision tree algorithm proposed in this study showed high sensitivity and NPV in predicting patients with severe dengue that may warrant admission. This tool upon further validation study can be used to help clinicians decide on further managing a patient upon first encounter. It also will have a substantial impact on health resources as low risk patients can be managed as outpatients hence reserving the scarce hospital beds and medical resources for other patients in need.

Study site: single ward, in Hospital Kuala Lumpur, Malaysia

Matched MeSH terms: Decision Trees*
Fulltext Cost-Effectiveness Analysis of Spending on Research and Development to Address the Needs for Innovative Therapeutic Products in Indonesia

Suwantika AA, Kautsar AP, Zakiyah N, Abdulah R, Boersma C, Postma MJ

Ther Clin Risk Manag, 2020;16:969-977.
PMID: 33116546 DOI: 10.2147/TCRM.S260377

Background: The annual gross domestic expenditure on research and development (GERD) per capita of Indonesia ($24) remains relatively lower than the annual GERD per capita of neighboring countries, such as Vietnam ($36), Singapore ($1804), Malaysia ($361), and Thailand ($111).
Objective: The aim of this study was to conduct a cost-effectiveness analysis of spending on healthcare R&D to address the needs of developing innovative therapeutic products in Indonesia.
Methods: A decision tree model was developed by taking into account four stages of R&D: stage 1 from raw concept to feasibility, stage 2 from feasibility to development, stage 3 from development to early commercialization, and stage 4 from early to full commercialization. Considering a 3-year time horizon, a stage-dependent success rate was applied and analyses were conducted from a business perspective. Two scenarios were compared by assuming the government of Indonesia would increase GERD in health and medical sciences up to 2- and 3-times higher than the baseline (current situation) for the first and second scenario, respectively. Cost per number of innovative products in health and medical sciences was considered as the incremental cost-effectiveness ratio (ICER). Univariate sensitivity analysis was conducted to investigate the effects of different input parameters on the ICER.
Results: There was a statistically significant association (P-value<0.05) between countries' GERD in medical and health sciences with the number of innovative products. We estimated the ICER would be $8.50 million and $2.04 million per innovative product for the first and second scenario, respectively. The sensitivity analysis showed that the success rates in all stages and total GERD were the most influential parameters impacting the ICER.
Conclusion: The result showed that there was an association between GERD in medical and health sciences with the number of innovative products. In addition, the second scenario would be more cost-effective than the first scenario.

Matched MeSH terms: Decision Trees
A decision tree model for the prediction of homodimer folding mechanism

Suresh A, Karthikraja V, Lulu S, Kangueane U, Kangueane P

Bioinformation, 2009 Nov 17;4(5):197-205.
PMID: 20461159

The formation of protein homodimer complexes for molecular catalysis and regulation is fascinating. The homodimer formation through 2S (2 state), 3SMI (3 state with monomer intermediate) and 3SDI (3 state with dimer intermediate) folding mechanism is known for 47 homodimer structures. Our dataset of forty-seven homodimers consists of twenty-eight 2S, twelve 3SMI and seven 3SDI. The dataset is characterized using monomer length, interface area and interface/total (I/T) residue ratio. It is found that 2S are often small in size with large I/T ratio and 3SDI are frequently large in size with small I/T ratio. Nonetheless, 3SMI have a mixture of these features. Hence, we used these parameters to develop a decision tree model. The decision tree model produced positive predictive values (PPV) of 72% for 2S, 58% for 3SMI and 57% for 3SDI in cross validation. Thus, the method finds application in assigning homodimers with folding mechanism.

Matched MeSH terms: Decision Trees
Utilizing decision tree machine model to map dental students' preferred learning styles with suitable instructional strategies

Shoaib LA, Safii SH, Idris N, Hussin R, Sazali MAH

BMC Med Educ, 2024 Jan 11;24(1):58.
PMID: 38212703 DOI: 10.1186/s12909-023-05022-5

BACKGROUND: Growing demand for student-centered learning (SCL) has been observed in higher education settings including dentistry. However, application of SCL in dental education is limited. Hence, this study aimed to facilitate SCL application in dentistry utilising a decision tree machine learning (ML) technique to map dental students' preferred learning styles (LS) with suitable instructional strategies (IS) as a promising approach to develop an IS recommender tool for dental students.
METHODS: A total of 255 dental students in Universiti Malaya completed the modified Index of Learning Styles (m-ILS) questionnaire containing 44 items which classified them into their respective LS. The collected data, referred to as dataset, was used in a decision tree supervised learning to automate the mapping of students' learning styles with the most suitable IS. The accuracy of the ML-empowered IS recommender tool was then evaluated.
RESULTS: The application of a decision tree model in the automation process of the mapping between LS (input) and IS (target output) was able to instantly generate the list of suitable instructional strategies for each dental student. The IS recommender tool demonstrated perfect precision and recall for overall model accuracy, suggesting a good sensitivity and specificity in mapping LS with IS.
CONCLUSION: The decision tree ML empowered IS recommender tool was proven to be accurate at matching dental students' learning styles with the relevant instructional strategies. This tool provides a workable path to planning student-centered lessons or modules that potentially will enhance the learning experience of the students.

Matched MeSH terms: Decision Trees
Fulltext Forecasting shear stress parameters in rectangular channels using new soft computing methods

Sheikh Khozani Z, Sheikhi S, Mohtar WHMW, Mosavi A

PLoS One, 2020;15(4):e0229731.
PMID: 32271780 DOI: 10.1371/journal.pone.0229731

Shear stress comprises basic information for predicting the average depth velocity and discharge in channels. With knowledge of the percentage of shear force carried by walls (%SFw) it is possible to more accurately estimate shear stress values. The %SFw, non-dimension wall shear stress ([Formula: see text]) and non-dimension bed shear stress ([Formula: see text]) in smooth rectangular channels were predicted by a three methods, the Bayesian Regularized Neural Network (BRNN), the Radial Basis Function (RBF), and the Modified Structure-Radial Basis Function (MS-RBF). For this aim, eight data series of research experimental results in smooth rectangular channels were used. The results of the new method of MS-RBF were compared with those of a simple RBF and BRNN methods and the best model was selected for modeling each predicted parameters. The MS-RBF model with RMSE of 3.073, 0.0366 and 0.0354 for %SFw, [Formula: see text] and [Formula: see text] respectively, demonstrated better performance than those of the RBF and BRNN models. The results of MS-RBF model were compared with three other proposed equations by researchers for trapezoidal channels and rectangular ducts. The results showed that the MS-RBF model performance in estimating %SFw, [Formula: see text] and [Formula: see text] is superior than those of presented equations by researchers.

Matched MeSH terms: Decision Trees
Crash severity along rural mountainous highways in Malaysia: An application of a combined decision tree and logistic regression model

Rusli R, Haque MM, Saifuzzaman M, King M

Traffic Inj Prev, 2018;19(7):741-748.
PMID: 29932734 DOI: 10.1080/15389588.2018.1482537

OBJECTIVE: Traffic crashes along mountainous highways may lead to injuries and fatalities more often than along highways on plain topography; however, research focusing on the injury outcome of such crashes is relatively scant. The objective of this study was to investigate the factors affecting the likelihood that traffic crashes along rural mountainous highways result in injuries.
METHOD: This study proposes a combination of decision tree and logistic regression techniques to model crash severity (injury vs. noninjury), because the combined approach allows the specification of nonlinearities and interactions in addition to main effects. Both a scobit model and a random parameters logit model, respectively accounting for an imbalance response variable and unobserved heterogeneities, are tested and compared. The study data set contains a total of 5 years of crash data (2008-2012) on selected mountainous highways in Malaysia. To enrich the data quality, an extensive field survey was conducted to collect detailed information on horizontal alignment, longitudinal grades, cross-section elements, and roadside features. In addition, weather condition data from the meteorology department were merged using the time stamp and proximity measures in AutoCAD-Geolocation.
RESULTS: The random parameters logit model is found to outperform both the standard logit and scobit models, suggesting the importance of accounting for unobserved heterogeneity in crash severity models. Results suggest that proportion of segment lengths with simple curves, presence of horizontal curves along steep gradients, highway segments with unsealed shoulders, and highway segments with cliffs along both sides are positively associated with injury-producing crashes along rural mountainous highways. Interestingly, crashes during rainy conditions are associated with crashes that are less likely to involve injury. It is also found that the likelihood of injury-producing crashes decreases for rear-end collisions but increases for head-on collisions and crashes involving heavy vehicles. A higher order interaction suggests that single-vehicle crashes involving light and medium-sized vehicles are less severe along straight sections compared to road sections with horizontal curves. One the other hand, crash severity is higher when heavy vehicles are involved in crashes as single vehicles traveling along straight segments of rural mountainous highways.
CONCLUSION: In addition to unobserved heterogeneity, it is important to account for higher order interactions to have a better understanding of factors that influence crash severity. A proper understanding of these factors will help develop targeted countermeasures to improve road safety along rural mountainous highways.

Matched MeSH terms: Decision Trees
A Review of Machine Learning Methods of Feature Selection and Classification for Autism Spectrum Disorder

Rahman MM, Usman OL, Muniyandi RC, Sahran S, Mohamed S, Razak RA

Brain Sci, 2020 Dec 07;10(12).
PMID: 33297436 DOI: 10.3390/brainsci10120949

Autism Spectrum Disorder (ASD), according to DSM-5 in the American Psychiatric Association, is a neurodevelopmental disorder that includes deficits of social communication and social interaction with the presence of restricted and repetitive behaviors. Children with ASD have difficulties in joint attention and social reciprocity, using non-verbal and verbal behavior for communication. Due to these deficits, children with autism are often socially isolated. Researchers have emphasized the importance of early identification and early intervention to improve the level of functioning in language, communication, and well-being of children with autism. However, due to limited local assessment tools to diagnose these children, limited speech-language therapy services in rural areas, etc., these children do not get the rehabilitation they need until they get into compulsory schooling at the age of seven years old. Hence, efficient approaches towards early identification and intervention through speedy diagnostic procedures for ASD are required. In recent years, advanced technologies like machine learning have been used to analyze and investigate ASD to improve diagnostic accuracy, time, and quality without complexity. These machine learning methods include artificial neural networks, support vector machines, a priori algorithms, and decision trees, most of which have been applied to datasets connected with autism to construct predictive models. Meanwhile, the selection of features remains an essential task before developing a predictive model for ASD classification. This review mainly investigates and analyzes up-to-date studies on machine learning methods for feature selection and classification of ASD. We recommend methods to enhance machine learning's speedy execution for processing complex data for conceptualization and implementation in ASD diagnostic research. This study can significantly benefit future research in autism using a machine learning approach for feature selection, classification, and processing imbalanced data.

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 hybrid method for classifying cognitive states from fMRI data

Parida S, Dehuri S, Cho SB, Cacha LA, Poznanski RR

J Integr Neurosci, 2015 Sep;14(3):355-68.
PMID: 26455882 DOI: 10.1142/S0219635215500223

Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.

Matched MeSH terms: Decision Trees
Fulltext A predictive method for hepatitis disease diagnosis using ensembles of neuro-fuzzy technique

Nilashi M, Ahmadi H, Shahmoradi L, Ibrahim O, Akbari E

J Infect Public Health, 2018 10 04;12(1):13-20.
PMID: 30293875 DOI: 10.1016/j.jiph.2018.09.009

BACKGROUND: Hepatitis is an inflammation of the liver, most commonly caused by a viral infection. Supervised data mining techniques have been successful in hepatitis disease diagnosis through a set of datasets. Many methods have been developed by the aids of data mining techniques for hepatitis disease diagnosis. The majority of these methods are developed by single learning techniques. In addition, these methods do not support the ensemble learning of the data. Combining the outputs of several predictors can result in improved accuracy in classification problems. This study aims to propose an accurate method for the hepatitis disease diagnosis by taking the advantages of ensemble learning.
METHODS: We use Non-linear Iterative Partial Least Squares to perform the data dimensionality reduction, Self-Organizing Map technique for clustering task and ensembles of Neuro-Fuzzy Inference System for predicting the hepatitis disease. We also use decision trees for the selection of most important features in the experimental dataset. We test our method on a real-world dataset and present our results in comparison with the latest results of previous studies.
RESULTS: The results of our analyses on the dataset demonstrated that our method performance is superior to the Neural Network, ANFIS, K-Nearest Neighbors and Support Vector Machine.
CONCLUSIONS: The method has potential to be used as an intelligent learning system for hepatitis disease diagnosis in the healthcare.

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
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
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
Fulltext ECG-based prediction algorithm for imminent malignant ventricular arrhythmias using decision tree

Mandala S, Cai Di T, Sunar MS, Adiwijaya

PLoS One, 2020;15(5):e0231635.
PMID: 32407335 DOI: 10.1371/journal.pone.0231635

Spontaneous prediction of malignant ventricular arrhythmia (MVA) is useful to avoid delay in rescue operations. Recently, researchers have developed several algorithms to predict MVA using various features derived from electrocardiogram (ECG). However, there are several unresolved issues regarding MVA prediction such as the effect of number of ECG features on a prediction remaining unclear, possibility that an alert for occurring MVA may arrive very late and uncertainty in the performance of the algorithm predicting MVA minutes before onset. To overcome the aforementioned problems, this research conducts an in-depth study on the number and types of ECG features that are implemented in a decision tree classifier. In addition, this research also investigates an algorithm's execution time before the occurrence of MVA to minimize delays in warnings for MVA. Lastly, this research aims to study both the sensitivity and specificity of an algorithm to reveal the performance of MVA prediction algorithms from time to time. To strengthen the results of analysis, several classifiers such as support vector machine and naive Bayes are also examined for the purpose of comparison study. There are three phases required to achieve the objectives. The first phase is literature review on existing relevant studies. The second phase deals with design and development of four modules for predicting MVA. Rigorous experiments are performed in the feature selection and classification modules. The results show that eight ECG features with decision tree classifier achieved good prediction performance in terms of execution time and sensitivity. In addition, the results show that the highest percentage for sensitivity and specificity is 95% and 90% respectively, in the fourth 5-minute interval (15.1 minutes-20 minutes) that preceded the onset of an arrhythmia event. Such results imply that the fourth 5-minute interval would be the best time to perform prediction.

Matched MeSH terms: Decision Trees
Fulltext Risk prediction analysis for classifying type 2 diabetes occurrence using local dataset

M. Hafiz Fazren Abd Rahman, Wan Wardatul Amani Wan Salim, M. Firdaus Abd-Wahab

Biological and Natural Resources Engineering Journal, 2020;3(1):48-61.
MyJurnal

The steep rise of cases pertaining to Diabetes Mellitus (DM) condition among global population has encouraged extensive researches on DM, which led to exhaustive accumulation of data related to DM. In this case, data mining and machine learning applications prove to be a powerful tool in transforming data into meaningful deductions. Several machine learning tools have shown great promise in diabetes classification. However, challenges remain in obtaining an accurate model suitable for real world application. Most disease risk-prediction modelling are found to be specific to a local population. Moreover, real-world data are likely to be complex, incomplete and unorganized, thus, convoluting efforts to develop models around it. This research aims to develop a robust prediction model for classification of type 2 diabetes mellitus (T2DM), with the interest of a Malaysian population, using three different machine learning algorithms; Decision Tree, Support Vector Machine and Naïve Bayes. Data pre-processing methods are utilised to the raw data to improve model performance. This study uses datasets obtained from the IIUM Medical Centre for classification and modelling. Ultimately, the performance of each model is validated, evaluated and compared based on several statistical metrics that measures accuracy, precision, sensitivity and efficiency. This study shows that the random forest model provides the best overall prediction performance in terms of accuracy (0.87), sensitivity (0.9), specificity (0.8), precision (0.9), F1-score (0.9) and AUC value (0.93) (Normal).

Matched MeSH terms: Decision Trees
Fulltext A hybrid interpretable deep structure based on adaptive neuro-fuzzy inference system, decision tree, and K-means for intrusion detection

Liu J, Yinchai W, Siong TC, Li X, Zhao L, Wei F

Sci Rep, 2022 Dec 01;12(1):20770.
PMID: 36456582 DOI: 10.1038/s41598-022-23765-x

For generating an interpretable deep architecture for identifying deep intrusion patterns, this study proposes an approach that combines ANFIS (Adaptive Network-based Fuzzy Inference System) and DT (Decision Tree) for interpreting the deep pattern of intrusion detection. Meanwhile, for improving the efficiency of training and predicting, Pearson Correlation analysis, standard deviation, and a new adaptive K-means are used to select attributes and make fuzzy interval decisions. The proposed algorithm was trained, validated, and tested on the NSL-KDD (National security lab-knowledge discovery and data mining) dataset. Using 22 attributes that highly related to the target, the performance of the proposed method achieves a 99.86% detection rate and 0.14% false alarm rate on the KDDTrain+ dataset, a 77.46% detection rate on the KDDTest+ dataset, which is better than many classifiers. Besides, the interpretable model can help us demonstrate the complex and overlapped pattern of intrusions and analyze the pattern of various intrusions.

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
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

Filters

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

External Links