MyMedR

Displaying all 9 publications

Abstract:

Sort:

Predictive modelling of colossal ATR-FTIR spectral data using PLS-DA: empirical differences between PLS1-DA and PLS2-DA algorithms

Lee LC, Jemain AA

Analyst, 2019 Apr 08;144(8):2670-2678.
PMID: 30849143 DOI: 10.1039/c8an02074d

In response to our review paper [L. C. Lee et al., Analyst, 2018, 143, 3526-3539], we present a study that compares empirical differences between PLS1-DA and PLS2-DA algorithms in modelling a colossal ATR-FTIR spectral dataset. Over the past two decades, partial least squares-discriminant analysis (PLS-DA) has gained wide acceptance and huge popularity in the field of applied research, partly due to its dimensionality reduction capability and ability to handle multicollinear and correlated variables. To solve a K-class problem (K > 2) using PLS-DA and high-dimensional data like infrared spectra, one can construct either K one-versus-all PLS1-DA models or only one PLS2-DA model. The aim of this work is to explore empirical differences between the two PLS-DA algorithms in modeling a colossal ATR-FTIR spectral dataset. The practical task is to build a prediction model using the imbalanced, high dimensional, colossal and multi-class ATR-FTIR spectra of blue gel pen inks. Four different sub-datasets were prepared from the principal dataset by considering the raw and asymmetric least squares (AsLS) preprocessed forms: (a) Raw-global region; (b) Raw-local region; (c) AsLS-global region; and (d) AsLS-local region. A series of 50 models which includes the first 50 PLS components incrementally was constructed repeatedly using the four sub-datasets. Each model was evaluated using six different variants of v-fold cross validation, autoprediction and external testing methods. As a result, each PLS-DA algorithm was represented by a number of figures of merit. The differences between PLS1-DA and PLS2-DA algorithms were assessed using hypothesis tests with respect to model accuracy, stability and fitting. On the other hand, confusion matrices of the two PLS-DA algorithms were inspected carefully for assessment of model parsimony. Overall, both the algorithms presented satisfactory model accuracy and stability. Nonetheless, PLS1-DA models showed significantly higher accuracy rates than PLS2-DA models, whereas PLS2-DA models seem to be much more stable compared to PLS1-DA models. Eventually, PLS2-DA also proved to be less prone to overfitting and is more parsimonious than PLS1-DA. In conclusion, the relatively high accuracy of the PLS1-DA algorithm is achieved at the cost of rather low parsimony and stability, and with an increased risk of overfitting.
Partial least squares-discriminant analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps

Lee LC, Liong CY, Jemain AA

Analyst, 2018 Jul 23;143(15):3526-3539.
PMID: 29947623 DOI: 10.1039/c8an00599k

Partial least squares-discriminant analysis (PLS-DA) is a versatile algorithm that can be used for predictive and descriptive modelling as well as for discriminative variable selection. However, versatility is both a blessing and a curse and the user needs to optimize a wealth of parameters before reaching reliable and valid outcomes. Over the past two decades, PLS-DA has demonstrated great success in modelling high-dimensional datasets for diverse purposes, e.g. product authentication in food analysis, diseases classification in medical diagnosis, and evidence analysis in forensic science. Despite that, in practice, many users have yet to grasp the essence of constructing a valid and reliable PLS-DA model. As the technology progresses, across every discipline, datasets are evolving into a more complex form, i.e. multi-class, imbalanced and colossal. Indeed, the community is welcoming a new era called big data. In this context, the aim of the article is two-fold: (a) to review, outline and describe the contemporary PLS-DA modelling practice strategies, and (b) to critically discuss the respective knowledge gaps that have emerged in response to the present big data era. This work could complement other available reviews or tutorials on PLS-DA, to provide a timely and user-friendly guide to researchers, especially those working in applied research.
Fulltext On the application of structural equation modeling for the construction of a health index

Yanuar F, Ibrahim K, Jemain AA

Environ Health Prev Med, 2010 Sep;15(5):285-91.
PMID: 21432557 DOI: 10.1007/s12199-010-0140-7

OBJECTIVE: The health of an individual is influenced by many factors. These could include factors that are related to the economy and the environment, as well as social and biological factors. Many studies have been carried out to study the effect of these factors on health, in terms of the individual factors or combined factors. The main purpose of this study was to demonstrate the value of structural equation modeling for the construction of an index to describe the health status of an individual.
METHODS: Structural equation modeling was applied to data obtained from 5035 respondents in a survey conducted in the district of Hulu Langat, Malaysia, in the year 2001 by the Department of Community Health, Medical Faculty, Universiti Kebangsaan Malaysia, Malaysia. The survey involved the gathering of information on the respondents' demography, lifestyles, mental health condition, and biomarkers.
RESULTS: Socio-demography and mental health condition were found to have a direct effect on the health index. However, lifestyle had an indirect effect on the health index, as mediated by the mental health. Based on the indicator of model fit, the proposed model fits the data well.
CONCLUSIONS: Structural equation modeling was found to be pertinent to be used for analyzing the health index of a particular individual.
Analysis of geometric moments as features for firearm identification

Md Ghani NA, Liong CY, Jemain AA

Forensic Sci Int, 2010 May 20;198(1-3):143-9.
PMID: 20211535 DOI: 10.1016/j.forsciint.2010.02.011

The task of identifying firearms from forensic ballistics specimens is exacting in crime investigation since the last two decades. Every firearm, regardless of its size, make and model, has its own unique 'fingerprint'. These fingerprints transfer when a firearm is fired to the fired bullet and cartridge case. The components that are involved in producing these unique characteristics are the firing chamber, breech face, firing pin, ejector, extractor and the rifling of the barrel. These unique characteristics are the critical features in identifying firearms. It allows investigators to decide on which particular firearm that has fired the bullet. Traditionally the comparison of ballistic evidence has been a tedious and time-consuming process requiring highly skilled examiners. Therefore, the main objective of this study is the extraction and identification of suitable features from firing pin impression of cartridge case images for firearm recognition. Some previous studies have shown that firing pin impression of cartridge case is one of the most important characteristics used for identifying an individual firearm. In this study, data are gathered using 747 cartridge case images captured from five different pistols of type 9mm Parabellum Vektor SP1, made in South Africa. All the images of the cartridge cases are then segmented into three regions, forming three different set of images, i.e. firing pin impression image, centre of firing pin impression image and ring of firing pin impression image. Then geometric moments up to the sixth order were generated from each part of the images to form a set of numerical features. These 48 features were found to be significantly different using the MANOVA test. This high dimension of features is then reduced into only 11 significant features using correlation analysis. Classification results using cross-validation under discriminant analysis show that 96.7% of the images were classified correctly. These results demonstrate the value of geometric moments technique for producing a set of numerical features, based on which the identification of firearms are made.
The Clinical Interview Schedule-Revised (CIS-R)-Malay Version, Clinical Validation

Subramaniam K, Krishnaswamy S, Jemain AA, Hamid A, Patel V

Malays J Med Sci, 2006 Jan;13(1):58-62.
PMID: 22589592

Use of instruments or questionnaires in different cultural settings without proper validation can result in inaccurate results. Issues like reliability, validity, feasibility and acceptability should be considered in the use of an instrument. The study aims to determine the usefulness of the CIS-R Malay version in detecting common mental health problems specifically to establish the validity. The CIS-R instrument (PROQSY* format) was translated through the back translation process into Malay. Inter rater reliability was established for raters who were medical students. Cases and controls for the study were psychiatric in patients, out patient and relatives or friends accompanying the patients to the clinic or visiting the inpatients. The Malay version of CIS-R was administered to all cases and controls. All cases and controls involved in the study were rated by psychiatrists for psychiatric morbidity using the SCID as a guideline. Specificity and sensitivity of the CIS-R to the assessment by the psychiatrist were determined. The Malay version of CIS-R showed 100% sensitivity and 96.15% specificity at a cut off score of 9. The CIS-R can be a useful instrument for clinical and research use in the Malaysian population for diagnosing common mental disorders like depression and anxiety.
Effect of ambient temperature on analytical and clinical performance of a blood glucose monitoring system: Omnitest Sensor glucose meter

Nawawi H, Sazali BS, Kamaruzaman BH, Yazid TN, Jemain AA, Ismail F, et al.

Ann. Clin. Biochem., 2001 Nov;38(Pt 6):676-83.
PMID: 11732650

The effect of ambient temperature on the analytical and clinical performance of a glucose meter was examined. A total of 114 venous whole blood samples were analysed for glucose by a reference method, and by a glucose meter at 21-22 degrees C, room temperatures, 26-27 degrees C and 33-34 degrees C. Glucose meter readings at each temperature were compared with the reference values and evaluated by analysis of variance, Spearman's correlation, the percentage of glucose meter readings within +/- 10% of the reference value and error grid analysis. Analysis of covariance was used to determine the effect of temperature on glucose meter readings. There were no significant differences in the glucose meter readings and in accuracy of the meter readings between different temperatures. Temperature was not a significant independent determinant of the glucose meter readings. For each glucose concentration, the precision of the meter and clinical performance were comparable between the different temperatures. In conclusion, ambient temperature does not affect the accuracy, precision and clinical performance of the Omnitest Sensor.
Trend and status of air quality at three different monitoring stations in the Klang Valley, Malaysia

Azmi SZ, Latif MT, Ismail AS, Juneng L, Jemain AA

Air Qual Atmos Health, 2010 Mar;3(1):53-64.
PMID: 20376168

Over the last decades, the development of the Klang Valley (Malaysia), as an urban commercial and industrial area, has elevated the risk of atmospheric pollutions. There are several significant sources of air pollutants which vary depending on the background of the location they originate from. The aim of this study is to determine the trend and status of air quality and their correlation with the meteorological factors at different air quality monitoring stations in the Klang Valley. The data of five major air pollutants (PM(10), CO, SO(2), O(3), NO(2)) were recorded at the Alam Sekitar Sdn Bhd (ASMA) monitoring stations in the Klang Valley, namely Petaling Jaya (S1), Shah Alam (S2) and Gombak (S3). The data from these three stations were compared with the data recorded at Jerantut, Pahang (B), a background station established by the Malaysian Department of Environment. Results show that the concentrations of CO, NO(2) and SO(2) are higher at Petaling Jaya (S1) which is due to influence of heavy traffic. The concentrations of PM(10) and O(3,) however, are predominantly related to regional tropical factors, such as the influence of biomass burning and of ultra violet radiation from sunlight. They can, though, also be influenced by local sources. There are relatively stronger inter-pollutant correlations at the stations of Gombak and Shah Alam, and the results also suggest that heavy traffic flow induces high concentrations of PM(10), CO, NO(2) and SO(2) at the three sampling stations. Additionally, meteorological factors, particularly the ambient temperature and wind speed, may influence the concentration of PM(10) in the atmosphere.
Enzyme activity profiles and ELISA analysis of biomarkers from human saliva and gingival crevicular fluid during orthodontic tooth movement using self-ligating brackets

Abdul Wahab RM, Abu Kasim N, Senafi S, Jemain AA, Zainol Abidin IZ, Shahidan MA, et al.

Oral Health Dent Manag, 2014 Jun;13(2):194-9.
PMID: 24984622

Profiles of orthodontic tooth movement biomarkers, i.e., Lactate Dehydrogenase (LDH), Aspartate Aminotransferase (AST), Tartrate-resistant Acid Phosphatase (TRAP) and Alkaline Phosphatase (ALP), using Self-ligating Brackets (SLBs) and possible relationships among their activities and total enzymes produced were determined.
Fulltext Crevicular Alkaline Phosphatase Activity and Rate of Tooth Movement of Female Orthodontic Subjects under Different Continuous Force Applications

Megat Abdul Wahab R, Md Dasor M, Senafi S, Abang Abdullah AA, Yamamoto Z, Jemain AA, et al.

Int J Dent, 2013;2013:245818.
PMID: 23737787 DOI: 10.1155/2013/245818

Purpose. This study is aimed to compare the effects of two different orthodontic forces on crevicular alkaline phosphatase activity, rate of tooth movement, and root resorption. Materials and Methods. Twelve female subjects of class II division 1 malocclusion participated. Maxillary canines with bonded fixed appliances acted as the tested teeth, while their antagonists with no appliances acted as the controls. Canine retraction was performed using nickel titanium coil spring that delivered forces of 100 gm or 150 gm to either side. Crevicular fluid was analyzed for ALP activity, and study models were casted to measure tooth movements. Root resorption was assessed using periapical radiographs before and after the force application. Results. ALP activity at the mesial sites peaked at week 1 for 150 gm group with significant differences when compared with the 100 gm group. Cumulative canine movements were significantly greater in the 150 gm force (2.10 ± 0.50 mm) than in the 100 gm force (1.57 ± 0.44 mm). No root resorption was in the maxillary canines after retraction. Conclusions. A force of 150 gm produced faster tooth movements and higher ALP activity compared with the 100 gm group and had no detrimental effects such as root resorption.