Displaying publications 1 - 20 of 360 in total

Abstract:
Sort:
  1. Fathinul Fikri AS, Dharmendran R, Vikneswaran P, Nordin AJ
    Abdom Imaging, 2015 Aug;40(6):1457-64.
    PMID: 25576048 DOI: 10.1007/s00261-014-0343-2
    A study was undertaken to investigate the value of pretreatment PET-CT in predicting survival in patients with oesophageal cancer (OC).
    Matched MeSH terms: Predictive Value of Tests
  2. Fathinul F, Nordin AJ, Lau WF
    Cell Biochem Biophys, 2013 May;66(1):37-43.
    PMID: 22790883 DOI: 10.1007/s12013-012-9395-5
    Molecular imaging employing (18)[F]FDG-PET/CT enables in-vivo visualization, characterisation and measurement of biological process in tumour at the molecular and cellular level. In oncology, this approach can be directly applied as translational biomarkers of disease progression. In this article, the improved roles of FDG as an in-vivo glycolytic marker which reflect biological changes across in-vitro cellular environment are discussed. New understanding in how altered metabolism via glycolytic downstream drivers of malignant transformation as reviewed below offers unique promise as to monitor tumour aggressiveness and hence optimize the therapeutic management.
    Matched MeSH terms: Predictive Value of Tests
  3. Yip KT, Das PK, Suria D, Lim CR, Ng GH, Liew CC
    J Exp Clin Cancer Res, 2010;29:128.
    PMID: 20846378 DOI: 10.1186/1756-9966-29-128
    BACKGROUND: Colorectal cancer (CRC) screening is key to CRC prevention and mortality reduction, but patient compliance with CRC screening is low. We previously reported a blood-based test for CRC that utilizes a seven-gene panel of biomarkers. The test is currently utilized clinically in North America for CRC risk stratification in the average-risk North American population in order to improve screening compliance and to enhance clinical decision making.
    METHODS: In this study, conducted in Malaysia, we evaluated the seven-gene biomarker panel validated in a North American population using blood samples collected from local patients. The panel employs quantitative RT-PCR (qRT-PCR) to analyze gene expression of the seven biomarkers (ANXA3, CLEC4D, TNFAIP6, LMNB1, PRRG4, VNN1 and IL2RB) that are differentially expressed in CRC patients as compared with controls. Blood samples from 210 patients (99 CRC and 111 controls) were collected, and total blood RNA was isolated and subjected to quantitative RT-PCR and data analysis.
    RESULTS: The logistic regression analysis of seven-gene panel has an area under the curve (AUC) of 0.76 (95% confidence interval: 0.70 to 0.82), 77% specificity, 61% sensitivity and 70% accuracy, comparable to the data obtained from the North American investigation of the same biomarker panel.
    CONCLUSIONS: Our results independently confirm the results of the study conducted in North America and demonstrate the ability of the seven biomarker panel to discriminate CRC from controls in blood samples drawn from a Malaysian population.
    Matched MeSH terms: Predictive Value of Tests
  4. Chong E, Shen L, Tan HC, Poh KK
    Med J Malaysia, 2011 Aug;66(3):249-52.
    PMID: 22111450
    Thrombolysis in Myocardial Infarction (TIMI) score has been used to predict outcomes in patients presenting with unstable angina (UA) and non-ST elevation myocardial infarction (NSTEMI). Our study assessed other clinical predictors for patients with UA/NSTEMI undergoing early percutaneous coronary intervention (PCI).
    Matched MeSH terms: Predictive Value of Tests
  5. Toh TH, Abdul-Aziz NA, Yahya MA, Goh KJ, Loh EC, Capelle DP, et al.
    Clin Neurophysiol, 2021 10;132(10):2722-2728.
    PMID: 34312065 DOI: 10.1016/j.clinph.2021.05.034
    OBJECTIVE: We aimed to develop a model to predict amyotrophic lateral sclerosis (ALS) disease progression based on clinical and neuromuscular ultrasound (NMUS) parameters.

    METHODS: ALS patients were prospectively recruited. Muscle fasciculation (≥2 over 30-seconds, examined in biceps brachii-brachialis (BB), brachioradialis, tibialis anterior and vastus medialis) and nerve cross-sectional area (CSA) (median, ulnar, tibial, fibular nerve) were evaluated through NMUS. Ultrasound parameters were correlated with clinical data, including revised ALS Functional Rating Scale (ALSFRS-R) progression at one year. A predictive model was constructed to differentiate fast progressors (ALSFRS-R decline ≥ 1/month) from non-fast progressors.

    RESULTS: 40 ALS patients were recruited. Three parameters emerged as strong predictors of fast progressors: (i) ALSFRS-R slope at time of NMUS (p = 0.041), (ii) BB fasciculation count (p = 0.027) and (iii) proximal to distal median nerve CSA ratio 

    Matched MeSH terms: Predictive Value of Tests
  6. Diez Benavente E, Campos M, Phelan J, Nolder D, Dombrowski JG, Marinho CRF, et al.
    PLoS Genet, 2020 02;16(2):e1008576.
    PMID: 32053607 DOI: 10.1371/journal.pgen.1008576
    Although Plasmodium vivax parasites are the predominant cause of malaria outside of sub-Saharan Africa, they not always prioritised by elimination programmes. P. vivax is resilient and poses challenges through its ability to re-emerge from dormancy in the human liver. With observed growing drug-resistance and the increasing reports of life-threatening infections, new tools to inform elimination efforts are needed. In order to halt transmission, we need to better understand the dynamics of transmission, the movement of parasites, and the reservoirs of infection in order to design targeted interventions. The use of molecular genetics and epidemiology for tracking and studying malaria parasite populations has been applied successfully in P. falciparum species and here we sought to develop a molecular genetic tool for P. vivax. By assembling the largest set of P. vivax whole genome sequences (n = 433) spanning 17 countries, and applying a machine learning approach, we created a 71 SNP barcode with high predictive ability to identify geographic origin (91.4%). Further, due to the inclusion of markers for within population variability, the barcode may also distinguish local transmission networks. By using P. vivax data from a low-transmission setting in Malaysia, we demonstrate the potential ability to infer outbreak events. By characterising the barcoding SNP genotypes in P. vivax DNA sourced from UK travellers (n = 132) to ten malaria endemic countries predominantly not used in the barcode construction, we correctly predicted the geographic region of infection origin. Overall, the 71 SNP barcode outperforms previously published genotyping methods and when rolled-out within new portable platforms, is likely to be an invaluable tool for informing targeted interventions towards elimination of this resilient human malaria.
    Matched MeSH terms: Predictive Value of Tests
  7. Chan WK, Nik Mustapha NR, Mahadeva S
    Hepatol Int, 2015 Oct;9(4):594-602.
    PMID: 25788185 DOI: 10.1007/s12072-014-9596-7
    BACKGROUND: The non-alcoholic fatty liver disease (NAFLD) fibrosis score (NFS) is indeterminate in a proportion of NAFLD patients. Combining the NFS with liver stiffness measurement (LSM) may improve prediction of advanced fibrosis. We aim to evaluate the NFS and LSM in predicting advanced fibrosis in NAFLD patients.

    METHODS: The NFS was calculated and LSM obtained for consecutive adult NAFLD patients scheduled for liver biopsy. The accuracy of predicting advanced fibrosis using either modality and in combination were assessed. An algorithm combining the NFS and LSM was developed from a training cohort and subsequently tested in a validation cohort.

    RESULTS: There were 101 and 46 patients in the training and validation cohort, respectively. In the training cohort, the percentages of misclassifications using the NFS alone, LSM alone, LSM alone (with grey zone), both tests for all patients and a 2-step approach using LSM only for patients with indeterminate and high NFS were 5.0, 28.7, 2.0, 2.0 and 4.0 %, respectively. The percentages of patients requiring liver biopsy were 30.7, 0, 36.6, 36.6 and 18.8 %, respectively. In the validation cohort, the percentages of misclassifications were 8.7, 28.3, 2.2, 2.2 and 8.7 %, respectively. The percentages of patients requiring liver biopsy were 28.3, 0, 41.3, 43.5 and 19.6 %, respectively.

    CONCLUSIONS: The novel 2-step approach further reduced the number of patients requiring a liver biopsy whilst maintaining the accuracy to predict advanced fibrosis. The combination of NFS and LSM for all patients provided no apparent advantage over using either of the tests alone.

    Matched MeSH terms: Predictive Value of Tests
  8. Kamarul T, Ahmad TS, Loh WY
    Med J Malaysia, 2006 Dec;61 Suppl B:37-44.
    PMID: 17600991
    Hand grip strength measurement is a recognized part of hand function assessment. The standard measurement using the Jamar dynamometer and comparing these results to the recommended normal values suggested by the manufacturers of the Jamar was questioned as these values were based on Western population. A study comparing a novel method of predicting grip strength using our software was conducted on 25 normal subjects using the LIDO kinetic workset (Group A and B ). These results were then compared against our predictive software (Group A) and the expected values supplied together with the Jamar Dynamometer (Group B). In another group, 22 normal subjects were tested using the Jamar (Group C and D) and then matched against the predicted values using their recommended chart (Group C). The last group (Group D) was tested using the Jamar but the values attained were compared to the results from our software. In group A, the predictability of our predictive method was 100% (both R & L) as compared to (R = 64%, L = 68%) in group B, (R = 27.3%, L = 59.1%) in group C and (R = 81.8%, L = 86.4%) in group D. The differences between the predictability of both methods were statistically significant. The data collected using both the Jamar and the LIDO kinetic workset correlated well to the data from our software but not to the values suggested by the manufacturers of Jamar. We conclude that our method of predicting hand grip values are superior to that suggested by the manufacturers of dynamometers. The standard reference for hand grip strength provided by the manufacturers is less accurate in predicting the grip strength of our local population.
    Matched MeSH terms: Predictive Value of Tests
  9. Warrener L, Slibinskas R, Chua KB, Nigatu W, Brown KE, Sasnauskas K, et al.
    Bull World Health Organ, 2011 Sep 01;89(9):675-82.
    PMID: 21897488 DOI: 10.2471/BLT.11.088427
    OBJECTIVE: To evaluate the performance of a newly developed point-of-care test (POCT) for the detection of measles-specific IgM antibodies in serum and oral fluid specimens and to assess if measles virus nucleic acid could be recovered from used POCT strips.

    METHODS: The POCT was used to test 170 serum specimens collected through measles surveillance or vaccination programmes in Ethiopia, Malaysia and the Russian Federation: 69 were positive for measles immunoglobulin M (IgM) antibodies, 74 were positive for rubella IgM antibodies and 7 were positive for both. Also tested were 282 oral fluid specimens from the measles, mumps and rubella (MMR) surveillance programme of the United Kingdom of Great Britain and Northern Ireland. The Microimmune measles IgM capture enzyme immunoassay was the gold standard for comparison. A panel of 24 oral fluids was used to investigate if measles virus haemagglutinin (H) and nucleocapsid (N) genes could be amplified by polymerase chain reaction directly from used POCT strips.

    FINDINGS: With serum POCT showed a sensitivity and specificity of 90.8% (69/76) and 93.6% (88/94), respectively; with oral fluids, sensitivity and specificity were 90.0% (63/70) and 96.2% (200/208), respectively. Both H and N genes were reliably detected in POCT strips and the N genes could be sequenced for genotyping. Measles virus genes could be recovered from POCT strips after storage for 5 weeks at 20-25 °C.

    CONCLUSION: The POCT has the sensitivity and specificity required of a field-based test for measles diagnosis. However, its role in global measles control programmes requires further evaluation.

    Matched MeSH terms: Predictive Value of Tests
  10. Lee M, Harrison BA, Lewis GE
    Am J Trop Med Hyg, 1990 Apr;42(4):314-9.
    PMID: 2184690 DOI: 10.4269/ajtmh.1990.42.314
    A modified version of the standard 2-site sporozoite enzyme-linked immunosorbent assay (ELISA) using 3,3',5,5'-tetramethylbenzidine (TMB) as the substrate chromogen solution was adapted for rapid detection and identification of Plasmodium falciparum and P. vivax circumsporozoite (CS) proteins. The TMB-ELISA was evaluated using sporozoites from experimentally infected mosquitoes and laboratory colonized uninfected mosquitoes. Our data indicate comparable sensitivity levels between the TMB-ELISA and the standard ELISA, i.e., 50 P. falciparum or P. vivax sporozoites/50 microliters of test solution. Reactions inherent to the method were specific and background reactivity was minimal. The TMB-ELISA is rapid (1 hr), simple, uses a minimal amount of monoclonal antibodies, and is suitable for use in a wide range of laboratories.
    Matched MeSH terms: Predictive Value of Tests
  11. Pipanmekaporn T, Bunchungmongkol N, Punjasawadwong Y, Lapisatepun W, Tantraworasin A, Saokaew S
    Asian Cardiovasc Thorac Ann, 2019 May;27(4):278-287.
    PMID: 30857395 DOI: 10.1177/0218492319835994
    BACKGROUND: Respiratory complications are some of the most common complications following thoracic surgery and can lead to higher perioperative morbidity and mortality. The purpose of this study was to develop a simple clinical score for prediction of respiratory complications after thoracic surgery, and determine the internal validity.

    METHODS: In this retrospective cohort study, all consecutive patients were aged 18 years and over and undergoing non-cardiac thoracic surgery at a tertiary-care university hospital. Respiratory complications included bronchospasm, atelectasis, pneumonia, respiratory failure, and adult respiratory distress syndrome within 30 days of surgery or before discharge.

    RESULTS: A total of 1488 patients were included over a 7-year period, and 15.8% (235 of 1488 patients) developed respiratory complications. The significant predictors of respiratory complications were chronic obstructive pulmonary disease, American Society of Anesthesiologist physical status ≥ 3, right-sided surgery, duration of surgery longer than 180 min, preoperative arterial oxygen saturation on room air 

    Matched MeSH terms: Predictive Value of Tests
  12. Ch'ng SS, Roddy J, Keen HI
    Int J Rheum Dis, 2013 Jun;16(3):264-72.
    PMID: 23981746 DOI: 10.1111/1756-185X.12106
    The modified Rodnan skin score is widely accepted as a validated tool to assess skin involvement in systemic sclerosis, which is a hallmark of this heterogeneous disease. Ultrasonography is increasingly being utilized in the study of other rheumatic diseases. The utility of ultrasonography to measure skin thickness in systemic sclerosis has been explored since three decades ago. The aim of this review was to examine the validity of ultrasonography as an outcome measure of skin involvement in systemic sclerosis. Original articles in English, published before December 2010, pertaining to the use of B mode ultrasound assessing skin involvement in systemic sclerosis were reviewed. Data were extracted with a focus on criterion and construct validity, reproducibility and responsiveness to change. Seventeen papers were analyzed. Skin thickness was most commonly studied, although skin echogenicity has also been examined. There was heterogeneity with regards to subjects, definitions used and sites imaged. Although there was limited information regarding reliability, when reported, the results showed excellent reproducibility. There was also a lack of construct and criterion validity and evidence for sensitivity to change. Ultrasound has potential as an outcome measure in systemic sclerosis. However, more work needs to be done in order to prove that it is a feasible outcome measure with proven validity.
    Matched MeSH terms: Predictive Value of Tests
  13. Kasmini K, Kyaw O
    Singapore Med J, 1988 Feb;29(1):48-52.
    PMID: 3406767
    The Middlesex Hospital Questionnaire (MHQ) with its subscales on anxiety, phobia, somatic symptoms, depression and hysteria was devised by Crown and Crisp(1). it has been used to differentiate between neurotic and normal population. The MHQ has been translated into the Malay language and this paper shows the results of an attempt to validate this translated questionnaire in the Malaysian population. The translated questionnaire is found to have useful validity as a whole and also for subscales on anxiety, somatic symptoms and depression.
    Matched MeSH terms: Predictive Value of Tests
  14. Mumtaz W, Xia L, Mohd Yasin MA, Azhar Ali SS, Malik AS
    PLoS One, 2017;12(2):e0171409.
    PMID: 28152063 DOI: 10.1371/journal.pone.0171409
    Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant's treatment outcome may help during antidepressant's selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant's treatment outcome for the MDD patients.
    Matched MeSH terms: Predictive Value of Tests
  15. Karunamuni RA, Huynh-Le MP, Fan CC, Thompson W, Eeles RA, Kote-Jarai Z, et al.
    Prostate Cancer Prostatic Dis, 2021 Jun;24(2):532-541.
    PMID: 33420416 DOI: 10.1038/s41391-020-00311-2
    BACKGROUND: Polygenic hazard scores (PHS) can identify individuals with increased risk of prostate cancer. We estimated the benefit of additional SNPs on performance of a previously validated PHS (PHS46).

    MATERIALS AND METHOD: 180 SNPs, shown to be previously associated with prostate cancer, were used to develop a PHS model in men with European ancestry. A machine-learning approach, LASSO-regularized Cox regression, was used to select SNPs and to estimate their coefficients in the training set (75,596 men). Performance of the resulting model was evaluated in the testing/validation set (6,411 men) with two metrics: (1) hazard ratios (HRs) and (2) positive predictive value (PPV) of prostate-specific antigen (PSA) testing. HRs were estimated between individuals with PHS in the top 5% to those in the middle 40% (HR95/50), top 20% to bottom 20% (HR80/20), and bottom 20% to middle 40% (HR20/50). PPV was calculated for the top 20% (PPV80) and top 5% (PPV95) of PHS as the fraction of individuals with elevated PSA that were diagnosed with clinically significant prostate cancer on biopsy.

    RESULTS: 166 SNPs had non-zero coefficients in the Cox model (PHS166). All HR metrics showed significant improvements for PHS166 compared to PHS46: HR95/50 increased from 3.72 to 5.09, HR80/20 increased from 6.12 to 9.45, and HR20/50 decreased from 0.41 to 0.34. By contrast, no significant differences were observed in PPV of PSA testing for clinically significant prostate cancer.

    CONCLUSIONS: Incorporating 120 additional SNPs (PHS166 vs PHS46) significantly improved HRs for prostate cancer, while PPV of PSA testing remained the same.

    Matched MeSH terms: Predictive Value of Tests
  16. Chen BC, McGown IN, Thong MK, Pitt J, Yunus ZM, Khoo TB, et al.
    J Inherit Metab Dis, 2010 Dec;33 Suppl 3:S159-62.
    PMID: 20177786 DOI: 10.1007/s10545-010-9056-z
    Most cases of adenylosuccinate lyase (ADSL OMIM 103050) deficiency reported to date are confined to the various European ethnic groups. We report on the first Malaysian case of ADSL deficiency, which appears also to be the first reported Asian case. The case was diagnosed among a cohort of 450 patients with clinical features of psychomotor retardation, global developmental delay, seizures, microcephaly and/or autistic behaviour. The patient presented with frequent convulsions and severe myoclonic jerk within the first few days of life and severe psychomotor retardation. The high performance liquid chromatography (HPLC) profile of the urine revealed the characteristic biochemical markers of succinyladenosine (S-Ado) and succinyl-aminoimidazole carboximide riboside (SAICAr). The urinary S-Ado/SAICAr ratio was found to be 1.02 (type I ADSL deficiency). The patient was compound heterozygous for two novel mutations, c.445C > G (p.R149G) and c.774_778insG (p.A260GfsX24).
    Matched MeSH terms: Predictive Value of Tests
  17. Ng SM, Lin HP, Ariffin WA, Zainab AK, Lam SK, Chan LL
    J Trop Pediatr, 2000 Dec;46(6):338-43.
    PMID: 11191144
    The presenting features and treatment outcome for 575 Malaysian children (< or = 12 years of age) with newly diagnosed acute lymphoblastic leukemia (ALL), admitted to the University Hospital, Kuala Lumpur, Malaysia between 1 January 1980 and 30 May 1995 were evaluated to determine their prognostic significance. Two-year overall survival was achieved in 67 per cent of all patients and 55 per cent of patients were relapse-free at 2 years. All except 10 patients, with identified French-American-British L3 morphology were treated with the modified Berlin-Frankfurt-Munster 78 treatment protocol. Univariate analyses of failure rate conferred age, sex, white cell count and hemoglobin level as potentially significant prognostic factors. All four presenting features retained their prognostic strength in a multivariate analysis. Race, platelet count, morphological subtype, liver/spleen size, lymphadenopathy, central nervous system and mediastinal mass involvement did not show any significant effect on treatment outcome. The 2-year survival rate was significantly different with regard to age, white cell count and hemoglobin level. However, sex was not significantly related to overall survival. These prognostic factors may have implications on future stratification of risk-adjusted initial treatment in the management of childhood ALL. Our analysis of Malaysian children is similar to what could be predicted based on previous studies in other populations.
    Matched MeSH terms: Predictive Value of Tests
  18. Hamizan AW, Loftus PA, Alvarado R, Ho J, Kalish L, Sacks R, et al.
    Laryngoscope, 2018 09;128(9):2015-2021.
    PMID: 29602169 DOI: 10.1002/lary.27180
    OBJECTIVES/HYPOTHESIS: Polypoid edema of the middle turbinate is a marker of inhalant allergy. Extensive edematous changes may result in limited central nasal and sinus disease, which has been called central compartment atopic disease (CCAD). Radiologically, this is seen as soft tissue thickening in the central portion of the sinonasal cavity with or without paranasal sinus involvement. When the sinuses are involved, the soft tissue thickening spares the sinus roof or lateral wall (centrally limited). This centrally limited radiological pattern was assessed among chronic rhinosinusitis (CRS) patients and compared to allergy status.

    STUDY DESIGN: Diagnostic cross-sectional study.

    METHODS: This study included consecutive CRS patients without prior sinus surgery. Computed tomography (CT) scans of the paranasal sinuses were blindly assessed and allergy status was confirmed by serum or skin testing. Individual sinus cavities were defined as either centrally limited or diffuse disease. The radiological pattern that may predict allergy was determined, and its diagnostic accuracy was calculated.

    RESULTS: One hundred twelve patients diagnosed to have CRS, representing 224 sides, were assessed (age 46.31 ± 13.57 years, 38.39% female, 41.07% asthma, Lund-Mackay CT score 15.88 ± 4.35, 56.25% atopic). The radiological pattern defined by centrally limited changes in all of the paranasal sinuses was associated with allergy status (73.53% vs. 53.16%, P = .03). This predicted atopy with 90.82% specificity, 73.53% positive predictive value, likelihood positive ratios of 2.16, and diagnostic odds ratio of 4.59.

    CONCLUSIONS: A central radiological pattern of mucosal disease is associated with inhalant allergen sensitization. This group may represent a CCAD subgroup of patients with mainly allergic etiology.

    LEVEL OF EVIDENCE: 3b Laryngoscope, 128:2015-2021, 2018.

    Matched MeSH terms: Predictive Value of Tests
  19. Mumtaz W, Saad MNBM, Kamel N, Ali SSA, Malik AS
    Artif Intell Med, 2018 01;84:79-89.
    PMID: 29169647 DOI: 10.1016/j.artmed.2017.11.002
    BACKGROUND: The abnormal alcohol consumption could cause toxicity and could alter the human brain's structure and function, termed as alcohol used disorder (AUD). Unfortunately, the conventional screening methods for AUD patients are subjective and manual. Hence, to perform automatic screening of AUD patients, objective methods are needed. The electroencephalographic (EEG) data have been utilized to study the differences of brain signals between alcoholics and healthy controls that could further developed as an automatic screening tool for alcoholics.

    METHOD: In this work, resting-state EEG-derived features were utilized as input data to the proposed feature selection and classification method. The aim was to perform automatic classification of AUD patients and healthy controls. The validation of the proposed method involved real-EEG data acquired from 30 AUD patients and 30 age-matched healthy controls. The resting-state EEG-derived features such as synchronization likelihood (SL) were computed involving 19 scalp locations resulted into 513 features. Furthermore, the features were rank-ordered to select the most discriminant features involving a rank-based feature selection method according to a criterion, i.e., receiver operating characteristics (ROC). Consequently, a reduced set of most discriminant features was identified and utilized further during classification of AUD patients and healthy controls. In this study, three different classification models such as Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were used.

    RESULTS: The study resulted into SVM classification accuracy=98%, sensitivity=99.9%, specificity=95%, and f-measure=0.97; LR classification accuracy=91.7%, sensitivity=86.66%, specificity=96.6%, and f-measure=0.90; NB classification accuracy=93.6%, sensitivity=100%, specificity=87.9%, and f-measure=0.95.

    CONCLUSION: The SL features could be utilized as objective markers to screen the AUD patients and healthy controls.

    Matched MeSH terms: Predictive Value of Tests
Filters
Contact Us

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

External Links