Displaying publications 41 - 60 of 2008 in total

Abstract:
Sort:
  1. Fulltext A blood-based gene expression and signaling pathway analysis to differentiate between high and low grade gliomas
    Ponnampalam SN, Kamaluddin NR, Zakaria Z, Matheneswaran V, Ganesan D, Haspani MS, et al.
    Oncol Rep, 2017 Jan;37(1):10-22.
    PMID: 28004117 DOI: 10.3892/or.2016.5285
    The aims of the present study were to undertake gene expression profiling of the blood of glioma patients to determine key genetic components of signaling pathways and to develop a panel of genes that could be used as a potential blood-based biomarker to differentiate between high and low grade gliomas, non-gliomas and control samples. In this study, blood samples were obtained from glioma patients, non-glioma and control subjects. Ten samples each were obtained from patients with high and low grade tumours, respectively, ten samples from non-glioma patients and twenty samples from control subjects. Total RNA was isolated from each sample after which first and second strand synthesis was performed. The resulting cRNA was then hybridized with the Agilent Whole Human Genome (4x44K) microarray chip according to the manufacturer's instructions. Universal Human Reference RNA and samples were labeled with Cy3 CTP and Cy5 CTP, respectively. Microarray data were analyzed by the Agilent Gene Spring 12.1V software using stringent criteria which included at least a 2-fold difference in gene expression between samples. Statistical analysis was performed using the unpaired Student's t-test with a p<0.01. Pathway enrichment was also performed, with key genes selected for validation using droplet digital polymerase chain reaction (ddPCR). The gene expression profiling indicated that were a substantial number of genes that were differentially expressed with more than a 2-fold change (p<0.01) between each of the four different conditions. We selected key genes within significant pathways that were analyzed through pathway enrichment. These key genes included regulators of cell proliferation, transcription factors, cytokines and tumour suppressor genes. In the present study, we showed that key genes involved in significant and well established pathways, could possibly be used as a potential blood-based biomarker to differentiate between high and low grade gliomas, non-gliomas and control samples.
    Matched MeSH terms: Reproducibility of Results
  2. Fulltext A case-controlled validation study of a blood-based seven-gene biomarker panel for colorectal cancer in Malaysia
    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: Reproducibility of Results
  3. A cell-based potentiometric biosensor using the fungus Lentinus sajor-caju for permethrin determination in treated wood
    Arip MN, Heng LY, Ahmad M, Ujang S
    Talanta, 2013 Nov 15;116:776-81.
    PMID: 24148473 DOI: 10.1016/j.talanta.2013.07.065
    The characteristics of a potentiometric biosensor for the determination of permethrin in treated wood based on immobilised cells of the fungus Lentinus sajor-caju on a potentiometric transducer are reported this paper. The potentiometric biosensor was prepared by immobilisation of the fungus in alginate gel deposited on a pH-sensitive transducer employing a photocurable acrylic matrix. The biosensor gave a good response in detecting permethrin over the range of 1.0-100.0 µM. The slope of the calibration curve was 56.10 mV/decade with detection limit of 1.00 µM. The relative standard deviation for the sensor reproducibility was 4.86%. The response time of the sensor was 5 min at optimum pH 8.0 with 1.00 mg/electrode of fungus L. sajor-caju. The permethrin biosensor performance was compared with the conventional method for permethrin analysis using high performance liquid chromatography (HPLC), and the analytical results agreed well with the HPLC method (at 95% confidence limit). There was no interference from commonly used organophosphorus pesticides such as diazinon, parathion, paraoxon, and methyl parathion.
    Matched MeSH terms: Reproducibility of Results
  4. Fulltext A chaotic cryptosystem for images based on Henon and Arnold cat map
    Soleymani A, Nordin MJ, Sundararajan E
    ScientificWorldJournal, 2014;2014:536930.
    PMID: 25258724 DOI: 10.1155/2014/536930
    The rapid evolution of imaging and communication technologies has transformed images into a widespread data type. Different types of data, such as personal medical information, official correspondence, or governmental and military documents, are saved and transmitted in the form of images over public networks. Hence, a fast and secure cryptosystem is needed for high-resolution images. In this paper, a novel encryption scheme is presented for securing images based on Arnold cat and Henon chaotic maps. The scheme uses Arnold cat map for bit- and pixel-level permutations on plain and secret images, while Henon map creates secret images and specific parameters for the permutations. Both the encryption and decryption processes are explained, formulated, and graphically presented. The results of security analysis of five different images demonstrate the strength of the proposed cryptosystem against statistical, brute force and differential attacks. The evaluated running time for both encryption and decryption processes guarantee that the cryptosystem can work effectively in real-time applications.
    Matched MeSH terms: Reproducibility of Results
  5. A comparative study of count models: application to pedestrian-vehicle crashes along Malaysia federal roads
    Hosseinpour M, Pour MH, Prasetijo J, Yahaya AS, Ghadiri SM
    Traffic Inj Prev, 2013;14(6):630-8.
    PMID: 23859313 DOI: 10.1080/15389588.2012.736649
    The objective of this study was to examine the effects of various roadway characteristics on the incidence of pedestrian-vehicle crashes by developing a set of crash prediction models on 543 km of Malaysia federal roads over a 4-year time span between 2007 and 2010.
    Matched MeSH terms: Reproducibility of Results
  6. Fulltext A comparative study of machine learning techniques for suicide attempts predictive model
    Nordin N, Zainol Z, Mohd Noor MH, Lai Fong C
    Health Informatics J, 2021 3 23;27(1):1460458221989395.
    PMID: 33745355 DOI: 10.1177/1460458221989395
    Current suicide risk assessments for predicting suicide attempts are time consuming, of low predictive value and have inadequate reliability. This paper aims to develop a predictive model for suicide attempts among patients with depression using machine learning algorithms as well as presents a comparative study on single predictive models with ensemble predictive models for differentiating depressed patients with suicide attempts from non-suicide attempters. We applied and trained eight different machine learning algorithms using a dataset that consists of 75 patients diagnosed with a depressive disorder. A recursive feature elimination was used to reduce the features via three-fold cross validation. An ensemble predictive models outperformed the single predictive models. Voting and bagging revealed the highest accuracy of 92% compared to other machine learning algorithms. Our findings indicate that history of suicide attempt, religion, race, suicide ideation and severity of clinical depression are useful factors for prediction of suicide attempts.
    Matched MeSH terms: Reproducibility of Results
  7. Fulltext A comparative study on the accuracy of noninvasive thermometers
    Fadzil FM, Choon D, Arumugam K
    Aust Fam Physician, 2010 Apr;39(4):237-9.
    PMID: 20372685
    This study assessed the concordance of the temperatures of the digital, liquid crystal forehead and digital infrared tympanic thermometers with the mercury in glass thermometer.
    Matched MeSH terms: Reproducibility of Results
  8. Fulltext A comparative study on the inter-session and interexaminer reliability of corneal power measurement using various keratometry instruments
    Md. Muziman Syah, M. M., Mutalib, H. A., Sharanjeet Kaur, M. S., Khairidzan Khairidzan, M. K.
    International Medical Journal Malaysia, 2016;15(1):69-74.
    MyJurnal
    Introduction: The purpose of this study was to evaluate inter-session repeatability, inter-examiner
    reproducibility and inter-device agreement of corneal power measurements from manual keratometer,
    autokeratometer, topographer, Pentacam high resolution and IOLMaster. Methods: Two sets of mean
    corneal power measurements (n=40) were compared for inter-session repeatability and inter-examiner
    reproducibility in each instrument. Repeatability and reproducibility were evaluated by within-subject
    standard deviation (Sw), coefficient of variation (COV) and intraclass correlation coefficient (ICC). A oneway
    repeated measures analysis of variance was conducted to compare differences in the corneal power
    between each instrument pair. The Bland and Altman analysis and Pearson’s correlation were employed to
    assess agreement and determine strength of relationship between measurements. Results: There were no
    significant differences in mean corneal power measurements between 2 different visits (p > 0.05). The Sw
    and COV values between 2 visits were lower than 0.09 D and 0.20 % respectively. The ICCs were stronger
    than 0.99 in all instruments. For reproducibility of each instrument, differences of the measurements
    between 2 different examiners were also insignificant (p > 0.05). The Sw and COV values between 2
    examiners were lower than 0.11 D and 0.23 % respectively. The ICCs were 0.99 and above in all instruments.
    The 95% limit of agreement between instruments ranged from -0.29 to 1.13 D and the r-values were stronger
    than 0.84. Conclusion: The corneal power measurements using these 5 instruments were repeatable and
    reproducible. These instruments can also be used interchangeably, however the topographer should be used
    with caution.
    Matched MeSH terms: Reproducibility of Results
  9. A comparison of autorefraction and subjective refraction with and without cycloplegia in primary school children
    Choong YF, Chen AH, Goh PP
    Am J Ophthalmol, 2006 Jul;142(1):68-74.
    PMID: 16815252 DOI: 10.1016/j.ajo.2006.01.084
    To evaluate the accuracy of autorefraction using three autorefractors comparing to subjective refraction in diagnosing refractive error in children.
    Matched MeSH terms: Reproducibility of Results
  10. A comparison of brain phantom relative permittivity with CST simulation library and existing research
    Chew KM, Seman N, Sudirman R, Yong CY
    Biomed Mater Eng, 2014;24(6):2161-7.
    PMID: 25226914 DOI: 10.3233/BME-141027
    The development of human-like brain phantom is important for data acquisition in microwave imaging. The characteristics of the phantom should be based on the real human body dielectric properties such as relative permittivity. The development of phantom includes the greymatter and whitematter regions, each with a relative permittivity of 38 and 28 respectively at 10 GHz frequency. Results were compared with the value obtained from the standard library of Computer Simulation Technology (CST) simulation application and the existing research by Fernandez and Gabriel. Our experimental results show a positive outcome, in which the proposed mixture was adequate to represent real human brain for data acquisition.
    Matched MeSH terms: Reproducibility of Results
  11. Fulltext A comparison of central composite design and Taguchi method for optimizing Fenton process
    Asghar A, Abdul Raman AA, Daud WM
    ScientificWorldJournal, 2014;2014:869120.
    PMID: 25258741 DOI: 10.1155/2014/869120
    In the present study, a comparison of central composite design (CCD) and Taguchi method was established for Fenton oxidation. [Dye]ini, Dye:Fe(+2), H2O2:Fe(+2), and pH were identified control variables while COD and decolorization efficiency were selected responses. L 9 orthogonal array and face-centered CCD were used for the experimental design. Maximum 99% decolorization and 80% COD removal efficiency were obtained under optimum conditions. R squared values of 0.97 and 0.95 for CCD and Taguchi method, respectively, indicate that both models are statistically significant and are in well agreement with each other. Furthermore, Prob > F less than 0.0500 and ANOVA results indicate the good fitting of selected model with experimental results. Nevertheless, possibility of ranking of input variables in terms of percent contribution to the response value has made Taguchi method a suitable approach for scrutinizing the operating parameters. For present case, pH with percent contribution of 87.62% and 66.2% was ranked as the most contributing and significant factor. This finding of Taguchi method was also verified by 3D contour plots of CCD. Therefore, from this comparative study, it is concluded that Taguchi method with 9 experimental runs and simple interaction plots is a suitable alternative to CCD for several chemical engineering applications.
    Matched MeSH terms: Reproducibility of Results
  12. A comparison of different standard-setting methods for professional qualifying dental examination
    Abd-Rahman ANA, Baharuddin IH, Abu-Hassan MI, Davies SJ
    J Dent Educ, 2021 Jul;85(7):1210-1216.
    PMID: 33792052 DOI: 10.1002/jdd.12600
    BACKGROUND: The outcome of assessments is determined by the standard-setting method used. Standard setting is the process of deciding what is good enough. A cutoff score of 50% was commonly used in dental schools in Malaysia. This study aims to compare the conventional, norm-referenced, and modified-Angoff standard-setting methods.

    METHODS: The norm-referenced method of standard setting was applied to the real scores of 40 final-year dental students on a multiple-choice question (MCQ), a short answer question (SAQ), and an objective structured clinical examination (OSCE). A panel of 10 judges set the standard using the modified-Angoff method for the same paper in one sitting. One judge set the passing score of 10 OSCE questions after 2 weeks. A comparison of the grades and pass/fail rates derived from the absolute standard, norm-referenced, and modified-Angoff methods was made. The intra-rater and inter-rater reliabilities of the modified-Angoff method were assessed.

    RESULTS: The passing rate for the absolute standard was 100% (40/40), for the norm-referenced method it was 62.5% (25/40), and for the modified-Angoff method it was 80% (32/40). The modified-Angoff method had good inter-rater reliability of 0.876 and excellent test-retest reliability of 0.941.

    CONCLUSION: There were significant differences in the outcomes of these three standard-setting methods, as shown by the difference in the proportion of candidates who passed and failed the assessment. The modified-Angoff method was found to have good reliability for use with a professional qualifying dental examination.

    Matched MeSH terms: Reproducibility of Results
  13. A comparison of human elements and nonhuman elements in private health care settings: customers' perceptions and expectations
    Mohd Suki N, Chwee Lian JC, Suki NM
    J Hosp Mark Public Relations, 2009;19(2):113-28.
    PMID: 19827322 DOI: 10.1080/15390940903041567
    In today's highly competitive health care environment, many private health care settings are now looking into customer service indicators to learn customers' perceptions and determine whether they are meeting customers' expectations in order to ensure that their customers are satisfied with the services. This research paper aims to investigate whether the human elements were more important than the nonhuman elements in private health care settings. We used the internationally renowned SERVQUAL five-dimension model plus three additional dimensions-courtesy, communication, and understanding of customers of the human element-when evaluating health care services. A total of 191 respondents from three private health care settings in the Klang Valley region of Malaysia were investigated. Descriptive statistics were calculated by the Statistical Package for Social Sciences (SPSS) computer program, version 15. Interestingly, the results suggested that customers nowadays have very high expectations especially when it comes to the treatment they are receiving. Overall, the research indicated that the human elements were more important than the nonhuman element in private health care settings. Hospital management should look further to improve on areas that have been highlighted. Implications for management practice and directions for future research are discussed.
    Matched MeSH terms: Reproducibility of Results
  14. Fulltext A comparison of physiological and transcriptome responses to water deprivation and salt loading in the rat supraoptic nucleus
    Greenwood MP, Mecawi AS, Hoe SZ, Mustafa MR, Johnson KR, Al-Mahmoud GA, et al.
    Am J Physiol Regul Integr Comp Physiol, 2015 Apr 01;308(7):R559-68.
    PMID: 25632023 DOI: 10.1152/ajpregu.00444.2014
    Salt loading (SL) and water deprivation (WD) are experimental challenges that are often used to study the osmotic circuitry of the brain. Central to this circuit is the supraoptic nucleus (SON) of the hypothalamus, which is responsible for the biosynthesis of the hormones, arginine vasopressin (AVP) and oxytocin (OXT), and their transport to terminals that reside in the posterior lobe of the pituitary. On osmotic challenge evoked by a change in blood volume or osmolality, the SON undergoes a function-related plasticity that creates an environment that allows for an appropriate hormone response. Here, we have described the impact of SL and WD compared with euhydrated (EU) controls in terms of drinking and eating behavior, body weight, and recorded physiological data including circulating hormone data and plasma and urine osmolality. We have also used microarrays to profile the transcriptome of the SON following SL and remined data from the SON that describes the transcriptome response to WD. From a list of 2,783 commonly regulated transcripts, we selected 20 genes for validation by qPCR. All of the 9 genes that have already been described as expressed or regulated in the SON by osmotic stimuli were confirmed in our models. Of the 11 novel genes, 5 were successfully validated while 6 were false discoveries.
    Matched MeSH terms: Reproducibility of Results
  15. A comparison of two global positioning system devices for team-sport running protocols
    Willmott AGB, James CA, Bliss A, Leftwich RA, Maxwell NS
    J Biomech, 2019 01 23;83:324-328.
    PMID: 30563764 DOI: 10.1016/j.jbiomech.2018.11.044
    The comparability and reliability of global positioning system (GPS) devices during running protocols associated with team-sports was investigated. Fourteen moderately-trained males completed 690 m of straight-line movements, a 570 m change of direction (COD) course and a 642.5 m team-sport simulated circuit (TSSC); on two occasions. Participants wore a FieldWiz GPS device and a Catapult MinimaxX S4 10-Hz GPS device. Typical error of measurement (TE) and coefficient of variation (CV%) were calculated between GPS devices, for the variables of total distance and peak speed. Reliability comparisons were made within FieldWiz GPS devices, between sessions. Small TE were observed between FieldWiz and Catapult GPS devices for total distance and peak speed during straight-line (16.9 m [2%], 1.2 km·h-1 [4%]), COD (31.8 m [6%], 0.4 km·h-1 [2%]) and TSSC protocols (12.9 m [2%], 0.5 km·h-1 [2%]), respectively, with no significant mean bias (p > 0.05). Small TE were also observed for the FieldWiz GPS device between sessions (p > 0.05) for straight-line (9.6 m [1%], 0.2 km·h-1 [1%]), COD (12.8 m [2%], 0.2 km·h-1 [1%]) and TSSC protocols (6.9 m [1%], 0.6 km·h-1 [2%]), respectively. Data from the FieldWiz GPS device appears comparable to established devices and reliable across a range of movement patterns associated with team-sports.
    Matched MeSH terms: Reproducibility of Results
  16. Fulltext A comprehensive review of demand side management in distributed grids based on real estate perspectives
    Dahiru AT, Daud D, Tan CW, Jagun ZT, Samsudin S, Dobi AM
    Environ Sci Pollut Res Int, 2023 Jul;30(34):81984-82013.
    PMID: 36652076 DOI: 10.1007/s11356-023-25146-x
    A major challenge in renewable energy planning and integration with existing systems is the management of intermittence of the resources and customer demand uncertainties that are attributed to climates. In emerging distributed grids, state-of-the-art optimization techniques were used for cost and reliability objectives. In the existing literature, power dispatch and demand side management schemes were implemented for various techno-economic objectives. In renewable energy-based distributed grids, power dispatch is strategic to system operations. However, demand side management is preferred, as it allows more options for customer participation and active management of energy in buildings. Moreover, the demand side management can simply follow supplies. This paper investigates the implications of demand side management as it affects planning and operations in renewable energy-based distributed grids. Integration of demand side management in customer-oriented plans such as the time-of-use and real-time-pricing on residential and commercial demands is conceptualised to ensure effective customer participation which maintains the valued comforts. Moreover, the optimised tariff integrated demand side management implementations based on the utility-initiated demand response programmes are envisaged to offset conflicting objectives of the economy and customer comforts within residential and commercial demands and are also viewed as a step towards efficient management of energy in buildings.
    Matched MeSH terms: Reproducibility of Results
  17. Fulltext A confirmatory factor analysis study on the medical student stressor questionnaire among Malaysian medical students
    Muhamad Saiful Bahri Yusoff
    Education in Medicine Journal, 2011;3(1):44-53.
    MyJurnal
    Objective: To determine the construct validity, convergent validity, construct reliability and internal consistency of the Medical Student Stressor Questionnaire (MSSQ) among first-year medical students in Malaysia. Methods: A multicenter cross-sectional study was done on 375 medical students of four medical schools in Malaysia. The confirmatory factor analysis and reliability analysis were applied to measure construct validity, construct reliability and internal consistency of the MSSQ. These analyses were done using Predictive Analytics SoftWare (PASW) version 18 and Analysis of Moment Structure (AMOS) version 19. The Composite Reliability and Average Variance Extracted of the final constructs were calculated manually to determine construct reliability and convergent validity. Results: A total of 359 (95.7%) medical students responded to this study. The confirmatory factor analysis showed the six factor model with 20 items had a good fit with the latent constructs (X2 (df) = 258.02 (155), p < 0.001, RMR = 0.055, GFI = 0.933, AGFI = 0.910, NFI = 0.931, RFI = 0.916, IFI = 0.971, TLI = 0.965, CFI = 0.971, RMSEA = 0.043). The Cronbach’s alpha value of the MSSQ was 0.92. The Cronbach’s alpha values of the six constructs were more than 0.7. Composite Reliability and Average Variance Extracted values of the six constructs were more than 0.6 and 0.5 respectively indicating good construct reliability and adequate convergent validity. Conclusion: This study suggested that the six factor model with 20 items of the MSSQ had a good fit and shown good psychometric values. It is a valid and reliability measurement to identify stressors among medical students across institutions in Malaysia.
    Matched MeSH terms: Reproducibility of Results
  18. Fulltext A coumarin-based fluorescent probe as a central nervous system disease biomarker
    Yap AC, Mahamad UA, Lim SY, Kim HJ, Choo YM
    Sensors (Basel), 2014 Nov 10;14(11):21140-50.
    PMID: 25390405 DOI: 10.3390/s141121140
    Homocysteine and methylmalonic acid are important biomarkers for diseases associated with an impaired central nervous system (CNS). A new chemoassay utilizing coumarin-based fluorescent probe 1 to detect the levels of homocysteine is successfully implemented using Parkinson's disease (PD) patients' blood serum. In addition, a rapid identification of homocysteine and methylmalonic acid levels in blood serum of PD patients was also performed using the liquid chromatography-mass spectrometry (LC-MS). The results obtained from both analyses were in agreement. The new chemoassay utilizing coumarin-based fluorescent probe 1 offers a cost- and time-effective method to identify the biomarkers in CNS patients.
    Matched MeSH terms: Reproducibility of Results
  19. 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: Reproducibility of Results
  20. A deep neural network-based approach for prediction of mutagenicity of compounds
    Kumar R, Khan FU, Sharma A, Siddiqui MH, Aziz IB, Kamal MA, et al.
    Environ Sci Pollut Res Int, 2021 Sep;28(34):47641-47650.
    PMID: 33895950 DOI: 10.1007/s11356-021-14028-9
    We are exposed to various chemical compounds present in the environment, cosmetics, and drugs almost every day. Mutagenicity is a valuable property that plays a significant role in establishing a chemical compound's safety. Exposure and handling of mutagenic chemicals in the environment pose a high health risk; therefore, identification and screening of these chemicals are essential. Considering the time constraints and the pressure to avoid laboratory animals' use, the shift to alternative methodologies that can establish a rapid and cost-effective detection without undue over-conservation seems critical. In this regard, computational detection and identification of the mutagens in environmental samples like drugs, pesticides, dyes, reagents, wastewater, cosmetics, and other substances is vital. From the last two decades, there have been numerous efforts to develop the prediction models for mutagenicity, and by far, machine learning methods have demonstrated some noteworthy performance and reliability. However, the accuracy of such prediction models has always been one of the major concerns for the researchers working in this area. The mutagenicity prediction models were developed using deep neural network (DNN), support vector machine, k-nearest neighbor, and random forest. The developed classifiers were based on 3039 compounds and validated on 1014 compounds; each of them encoded with 1597 molecular feature vectors. DNN-based prediction model yielded highest prediction accuracy of 92.95% and 83.81% with the training and test data, respectively. The area under the receiver's operating curve and precision-recall curve values were found to be 0.894 and 0.838, respectively. The DNN-based classifier not only fits the data with better performance as compared to traditional machine learning algorithms, viz., support vector machine, k-nearest neighbor, and random forest (with and without feature reduction) but also yields better performance metrics. In current work, we propose a DNN-based model to predict mutagenicity of compounds.
    Matched MeSH terms: Reproducibility of Results
Related Terms
Filters
Contact Us

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

External Links