Displaying publications 1 - 20 of 242 in total

Abstract:
Sort:
  1. Sha HL, Roslani AC, Poh KS
    Colorectal Dis, 2020 10;22(10):1379-1387.
    PMID: 32337794 DOI: 10.1111/codi.15091
    AIM: The Sodergren score was developed to objectively measure the severity of haemorrhoidal symptoms. This study aimed to determine if there was a difference in the Sodergren score between patients who were offered surgery and patients who underwent successful rubber band ligation of internal haemorrhoidal disease and to assess its performance in guiding management.

    METHOD: This is a prospective, observational study. The preintervention Sodergren scores of subjects with internal haemorrhoidal disease were recorded and blinded to the surgeon in charge. Sodergren scores of subjects in the two arms were unblinded and compared at the end of the study.

    RESULTS: The results for 290 patients were available for final analysis. The median scores of those offered surgery and those who underwent successful rubber band ligation differed significantly [4 (interquartile range 3-10) vs 0 (interquartile range 0-4), P = 0.001]. In predicting treatment, the Sodergren score had an area under the receiver operating characteristic curve of 0.735 (95% CI 0.675-0.795).

    CONCLUSION: There is a significant difference in scores between patients who were offered surgery and patients with successful rubber band ligation. Our study suggests that the Sodergren score has an acceptable discrimination in predicting the need for surgery in internal haemorrhoidal disease. We propose that patients with a Sodergren score of 6 or more be considered for upfront surgery. This score could potentially be used to standardize outcomes of future haemorrhoid trials.

    Matched MeSH terms: ROC Curve
  2. Yadav DP, Kumar D, Jalal AS, Kumar A, Singh KU, Shah MA
    Sci Rep, 2023 Oct 09;13(1):16988.
    PMID: 37813973 DOI: 10.1038/s41598-023-44210-7
    Leukemia is a cancer of white blood cells characterized by immature lymphocytes. Due to blood cancer, many people die every year. Hence, the early detection of these blast cells is necessary for avoiding blood cancer. A novel deep convolutional neural network (CNN) 3SNet that has depth-wise convolution blocks to reduce the computation costs has been developed to aid the diagnosis of leukemia cells. The proposed method includes three inputs to the deep CNN model. These inputs are grayscale and their corresponding histogram of gradient (HOG) and local binary pattern (LBP) images. The HOG image finds the local shape, and the LBP image describes the leukaemia cell's texture pattern. The suggested model was trained and tested with images from the AML-Cytomorphology_LMU dataset. The mean average precision (MAP) for the cell with less than 100 images in the dataset was 84%, whereas for cells with more than 100 images in the dataset was 93.83%. In addition, the ROC curve area for these cells is more than 98%. This confirmed proposed model could be an adjunct tool to provide a second opinion to a doctor.
    Matched MeSH terms: ROC Curve
  3. Moayedi H, Osouli A, Tien Bui D, Foong LK
    Sensors (Basel), 2019 Oct 29;19(21).
    PMID: 31671801 DOI: 10.3390/s19214698
    Regular optimization techniques have been widely used in landslide-related problems. This paper outlines two novel optimizations of artificial neural network (ANN) using grey wolf optimization (GWO) and biogeography-based optimization (BBO) metaheuristic algorithms in the Ardabil province, Iran. To this end, these algorithms are synthesized with a multi-layer perceptron (MLP) neural network for optimizing its computational parameters. The used spatial database consists of fourteen landslide conditioning factors, namely elevation, slope aspect, land use, plan curvature, profile curvature, soil type, distance to river, distance to road, distance to fault, rainfall, slope degree, stream power index (SPI), topographic wetness index (TWI) and lithology. 70% of the identified landslides are randomly selected to train the proposed models and the remaining 30% is used to evaluate the accuracy of them. Also, the frequency ratio theory is used to analyze the spatial interaction between the landslide and conditioning factors. Obtained values of area under the receiver operating characteristic curve, as well as mean square error and mean absolute error showed that both GWO and BBO hybrid algorithms could efficiently improve the learning capability of the MLP. Besides, the BBO-based ensemble surpasses other implemented models.
    Matched MeSH terms: ROC Curve
  4. Pszczolkowski S, Manzano-Patrón JP, Law ZK, Krishnan K, Ali A, Bath PM, et al.
    Eur Radiol, 2021 Oct;31(10):7945-7959.
    PMID: 33860831 DOI: 10.1007/s00330-021-07826-9
    OBJECTIVES: To test radiomics-based features extracted from noncontrast CT of patients with spontaneous intracerebral haemorrhage for prediction of haematoma expansion and poor functional outcome and compare them with radiological signs and clinical factors.

    MATERIALS AND METHODS: Seven hundred fifty-four radiomics-based features were extracted from 1732 scans derived from the TICH-2 multicentre clinical trial. Features were harmonised and a correlation-based feature selection was applied. Different elastic-net parameterisations were tested to assess the predictive performance of the selected radiomics-based features using grid optimisation. For comparison, the same procedure was run using radiological signs and clinical factors separately. Models trained with radiomics-based features combined with radiological signs or clinical factors were tested. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) score.

    RESULTS: The optimal radiomics-based model showed an AUC of 0.693 for haematoma expansion and an AUC of 0.783 for poor functional outcome. Models with radiological signs alone yielded substantial reductions in sensitivity. Combining radiomics-based features and radiological signs did not provide any improvement over radiomics-based features alone. Models with clinical factors had similar performance compared to using radiomics-based features, albeit with low sensitivity for haematoma expansion. Performance of radiomics-based features was boosted by incorporating clinical factors, with time from onset to scan and age being the most important contributors for haematoma expansion and poor functional outcome prediction, respectively.

    CONCLUSION: Radiomics-based features perform better than radiological signs and similarly to clinical factors on the prediction of haematoma expansion and poor functional outcome. Moreover, combining radiomics-based features with clinical factors improves their performance.

    KEY POINTS: • Linear models based on CT radiomics-based features perform better than radiological signs on the prediction of haematoma expansion and poor functional outcome in the context of intracerebral haemorrhage. • Linear models based on CT radiomics-based features perform similarly to clinical factors known to be good predictors. However, combining these clinical factors with radiomics-based features increases their predictive performance.

    Matched MeSH terms: ROC Curve
  5. Wang P, Jiang L, Soh KL, Ying Y, Liu Y, Huang X, et al.
    Nutr Cancer, 2023;75(1):61-72.
    PMID: 35903897 DOI: 10.1080/01635581.2022.2104877
    Early assessment of malnutrition in cancer patients is very important. The Mini Nutritional Assessment (MNA) is often used to assess malnutrition in adult cancer patients. However, the diagnostic values of MNA are controversial. We aimed to analyze the diagnostic values of MNA in assessing malnutrition in adult cancer patients. A systematic search was performed using Embase, Web of Science, PubMed, the Cochrane Library, China National Knowledge Infrastructure (CNKI), Wanfang Database, and China Science and Technology Journal Database (VIP). Studies comparing MNA with other tools or criteria in cancer patients were included. The quality of the included studies was assessed by the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The pooled sensitivity, specificity, the area under the receiver-operating characteristic curve (AUC), and the diagnostic odds ratio (DOR) were calculated using Stata 17.0 and Meta-DiSc1.4. In addition, sensitivity, subgroup, meta-regression, and publication bias analyses were conducted. In total, 11 studies involving 1367 patients involving MNA were included. The pooled sensitivity, specificity, ROC, and DOR were 0.84 (95% CI: 0.81-0.87), 0.66 (95% CI: 0.63-0.69), 0.84 (95% CI: 0.81-0.87), and 16.11 (95% CI: 7.16-36.27), respectively. In the assessment of malnutrition in adult cancer patients, MNA has high sensitivity and moderate specificity.
    Matched MeSH terms: ROC Curve
  6. Ong SQ, Isawasan P, Ngesom AMM, Shahar H, Lasim AM, Nair G
    Sci Rep, 2023 Nov 05;13(1):19129.
    PMID: 37926755 DOI: 10.1038/s41598-023-46342-2
    Machine learning algorithms (ML) are receiving a lot of attention in the development of predictive models for monitoring dengue transmission rates. Previous work has focused only on specific weather variables and algorithms, and there is still a need for a model that uses more variables and algorithms that have higher performance. In this study, we use vector indices and meteorological data as predictors to develop the ML models. We trained and validated seven ML algorithms, including an ensemble ML method, and compared their performance using the receiver operating characteristic (ROC) with the area under the curve (AUC), accuracy and F1 score. Our results show that an ensemble ML such as XG Boost, AdaBoost and Random Forest perform better than the logistics regression, Naïve Bayens, decision tree, and support vector machine (SVM), with XGBoost having the highest AUC, accuracy and F1 score. Analysis of the importance of the variables showed that the container index was the least important. By removing this variable, the ML models improved their performance by at least 6% in AUC and F1 score. Our result provides a framework for future studies on the use of predictive models in the development of an early warning system.
    Matched MeSH terms: ROC Curve
  7. Tai HK, Jusoh SA, Siu SWI
    J Cheminform, 2018 Dec 14;10(1):62.
    PMID: 30552524 DOI: 10.1186/s13321-018-0320-9
    BACKGROUND: Protein-ligand docking programs are routinely used in structure-based drug design to find the optimal binding pose of a ligand in the protein's active site. These programs are also used to identify potential drug candidates by ranking large sets of compounds. As more accurate and efficient docking programs are always desirable, constant efforts focus on developing better docking algorithms or improving the scoring function. Recently, chaotic maps have emerged as a promising approach to improve the search behavior of optimization algorithms in terms of search diversity and convergence speed. However, their effectiveness on docking applications has not been explored. Herein, we integrated five popular chaotic maps-logistic, Singer, sinusoidal, tent, and Zaslavskii maps-into PSOVina[Formula: see text], a recent variant of the popular AutoDock Vina program with enhanced global and local search capabilities, and evaluated their performances in ligand pose prediction and virtual screening using four docking benchmark datasets and two virtual screening datasets.

    RESULTS: Pose prediction experiments indicate that chaos-embedded algorithms outperform AutoDock Vina and PSOVina in ligand pose RMSD, success rate, and run time. In virtual screening experiments, Singer map-embedded PSOVina[Formula: see text] achieved a very significant five- to sixfold speedup with comparable screening performances to AutoDock Vina in terms of area under the receiver operating characteristic curve and enrichment factor. Therefore, our results suggest that chaos-embedded PSOVina methods might be a better option than AutoDock Vina for docking and virtual screening tasks. The success of chaotic maps in protein-ligand docking reveals their potential for improving optimization algorithms in other search problems, such as protein structure prediction and folding. The Singer map-embedded PSOVina[Formula: see text] which is named PSOVina-2.0 and all testing datasets are publicly available on https://cbbio.cis.umac.mo/software/psovina .

    Matched MeSH terms: ROC Curve
  8. Tan M, Al-Shabi M, Chan WY, Thomas L, Rahmat K, Ng KH
    Med Biol Eng Comput, 2021 Feb;59(2):355-367.
    PMID: 33447988 DOI: 10.1007/s11517-021-02313-1
    This study objectively evaluates the similarity between standard full-field digital mammograms and two-dimensional synthesized digital mammograms (2DSM) in a cohort of women undergoing mammography. Under an institutional review board-approved data collection protocol, we retrospectively analyzed 407 women with digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) examinations performed from September 1, 2014, through February 29, 2016. Both FFDM and 2DSM images were used for the analysis, and 3216 available craniocaudal (CC) and mediolateral oblique (MLO) view mammograms altogether were included in the dataset. We analyzed the mammograms using a fully automated algorithm that computes 152 structural similarity, texture, and mammographic density-based features. We trained and developed two different global mammographic image feature analysis-based breast cancer detection schemes for 2DSM and FFDM images, respectively. The highest structural similarity features were obtained on the coarse Weber Local Descriptor differential excitation texture feature component computed on the CC view images (0.8770) and MLO view images (0.8889). Although the coarse structures are similar, the global mammographic image feature-based cancer detection scheme trained on 2DSM images outperformed the corresponding scheme trained on FFDM images, with area under a receiver operating characteristic curve (AUC) = 0.878 ± 0.034 and 0.756 ± 0.052, respectively. Consequently, further investigation is required to examine whether DBT can replace FFDM as a standalone technique, especially for the development of automated objective-based methods.
    Matched MeSH terms: ROC Curve
  9. Fauziah Nordin, Quek Kia Fatt, Agus Salim M Banon
    MyJurnal
    This study aimed to validate the Malay Version of Copenhagen Psychosocial Questionnaire for Malaysian use and application for assessing psychosocial work environment factors. Validity and Reliability were studied in 50 staff nurses of Hospital Selayang. The validity of the questionnaire was evaluated by calculating the percentage of sensitivity and specificity at the different score level. Both percentage of sensitivity against specificity were plotted to produce a ROC (Receiver Operating Characteristics) curve, and score 52 has the highest both sensitivity and specificity was used as an overall index that expresses the probability that measure the psychosocial problems. For reliability purposes, a descriptive of Test-Retest Mean Scores and Paired Sample T-Test and the coefficient-correlation test were calculated. The Test-Retest Mean Scores and Paired Sample T-Test for all 26 scales were calculated and showed statistically not significant. The reliability of the questionnaire and its 26 scales was assessed by using Pearson (r) (overall questionnaire r within a range of 0.00 to 1.00). The COPSOQ appears to be a reliable and responsive measure of workers for Malaysian use and can be applied for assessing psychosocial work environment factors.
    Matched MeSH terms: ROC Curve
  10. Yuan CJ, Varathan KD, Suhaimi A, Ling LW
    J Rehabil Med, 2023 Jan 09;55:jrm00348.
    PMID: 36306152 DOI: 10.2340/jrm.v54.2432
    OBJECTIVE: To explore machine learning models for predicting return to work after cardiac rehabilitation.

    SUBJECTS: Patients who were admitted to the University of Malaya Medical Centre due to cardiac events.

    METHODS: Eight different machine learning models were evaluated. The models included 3 different sets of features: full features; significant features from multiple logistic regression; and features selected from recursive feature extraction technique. The performance of the prediction models with each set of features was compared.

    RESULTS: The AdaBoost model with the top 20 features obtained the highest performance score of 92.4% (area under the curve; AUC) compared with other prediction models.

    CONCLUSION: The findings showed the potential of using machine learning models to predict return to work after cardiac rehabilitation.

    Matched MeSH terms: ROC Curve
  11. Zhu CZ, Ting HN, Ng KH, Mun KS, Ong TA
    Phys Eng Sci Med, 2024 Mar;47(1):61-71.
    PMID: 37843766 DOI: 10.1007/s13246-023-01341-5
    Many studies have investigated the dielectric properties of human and animal tissues, particularly to differentiate between normal cells and tumors. However, these studies are invasive as tissue samples have to be excised to measure the properties. This study aims to investigate the dielectric properties of urine in relation to bladder cancer, which is safe and non-invasive to patients. 30 healthy subjects and 30 bladder cancer patients were recruited. Their urine samples were subjected to urinalysis and cytology assessment. A vector network analyzer was used to measure the dielectric constant (Ɛ') and loss factor (Ɛ″) at microwave frequencies of between 0.2 and 50 GHz at 25 °C, 30 °C and 37 °C. Significant differences in Ɛ' and Ɛ″ were observed between healthy subjects and patients, especially at frequencies of between 25 and 40 GHz at 25 °C. Bladder cancer patients had significant lower Ɛ' and higher Ɛ″ compared with healthy subjects. The Ɛ' was negatively correlated with urinary exfoliated urothelial cell number, and Ɛ″ was positively correlated. The study achieved a receiver operating characteristic area under curve (ROC-AUC) score of 0.69099 and an optimum accuracy of 75% with a sensitivity of 80% and a specificity of 70%. The number of exfoliated urothelial cell had significant effect on the dielectric properties, especially in bladder cancer patients. Urinary dielectric properties could potentially be used as a tool to detect bladder cancer.
    Matched MeSH terms: ROC Curve
  12. Ojha SC, Chen K, Yuan Y, Ahmed S, Malik AA, Nisha M, et al.
    PMID: 35967859 DOI: 10.3389/fcimb.2022.758833
    BACKGROUND: Efficient detection tools for determining staphylococcal pleural infection are critical for its eradication. The objective of this meta-analysis was to assess the diagnostic utility of nucleic acid amplification tests (NAAT) in suspected empyema cases to identify staphylococcal strains and avoid unnecessary empiric methicillin-resistant Staphylococcus aureus (MRSA) therapy.

    METHODS: From inception to July 24, 2021, relevant records were retrieved from PubMed, Embase, Scopus, Web of Science, and the Cochrane Library. The quality of studies was determined using the QUADAS-2 tool. The pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and hierarchical summary receiver operating characteristic (HSROC) curve for NAAT's diagnostic performance were evaluated using an HSROC model.

    RESULTS: Eight studies comprising 424 samples evaluated NAAT accuracy for Staphylococcus aureus (SA) identification, while four studies comprising 317 samples evaluated methicillin-resistant Staphylococcus aureus (MRSA) identification. The pooled NAAT summary estimates for detection of both SA (sensitivity: 0.35 (95% CI 0.19-0.55), specificity: 0.95 (95% CI 0.92-0.97), PLR: 7.92 (95% CI 4.98-12.59), NLR: 0.44 (95% CI 0.14-1.46), and DOR: 24.0 (95% CI 6.59-87.61) ) and MRSA (sensitivity: 0.45 (95% CI 0.15-0.78), specificity: 0.93 (95% CI 0.89-0.95), PLR: 10.06 (95% CI 1.49-67.69), NLR: 0.69 (95% CI 0.41-1.15), and DOR: 27.18 (95% CI 2.97-248.6) ) were comparable. The I2 statistical scores for MRSA and SA identification sensitivity were 13.7% and 74.9%, respectively, indicating mild to substantial heterogeneity. PCR was frequently used among NAA tests, and its diagnostic accuracy coincided well with the overall summary estimates. A meta-regression and subgroup analysis of country, setting, study design, patient selection, and sample condition could not explain the heterogeneity (meta-regression P = 0.66, P = 0.46, P = 0.98, P = 0.68, and P = 0.79, respectively) in diagnostic effectiveness.

    CONCLUSIONS: Our study suggested that the diagnostic accuracy of NAA tests is currently inadequate to substitute culture as a principal screening test. NAAT could be used in conjunction with microbiological culture due to the advantage of faster results and in situations where culture tests are not doable.

    Matched MeSH terms: ROC Curve
  13. Ng WL, Rahmat K, Fadzli F, Rozalli FI, Mohd-Shah MN, Chandran PA, et al.
    Medicine (Baltimore), 2016 Mar;95(12):e3146.
    PMID: 27015196 DOI: 10.1097/MD.0000000000003146
    The purpose of this study was to investigate the diagnostic efficacy of shearwave elastography (SWE) in differentiating between benign and malignant breast lesions.One hundred and fifty-nine lesions were assessed using B-mode ultrasound (US) and SWE parameters were recorded (Emax, Emean, Emin, Eratio, SD). SWE measurements were then correlated with histopathological diagnosis.The final sample contained 85 benign and 74 malignant lesions. The maximum stiffness (Emax) with a cutoff point of ≥ 56.0 kPa (based on ROC curves) provided sensitivity of 100.0%, specificity of 97.6%, positive predictive value (PPV) of 97.4%, and negative predictive value (NPV) of 100% in detecting malignant lesions. A cutoff of ≥80 kPa managed to downgrade 95.5% of the Breast Imaging-Reporting and Data System (BI-RADS) 4a lesions to BI-RADS 3, negating the need for biopsy. Using a combination of BI-RADS and SWE, the authors managed to improve the PPV from 2.3% to 50% in BI-RADS 4a lesions.SWE of the breast provides highly specific and sensitive quantitative values that are beneficial in the characterization of breast lesions. Our results showed that Emax is the most accurate value for differentiating benign from malignant lesions.
    Matched MeSH terms: ROC Curve
  14. Liu H, Tan T, van Zelst J, Mann R, Karssemeijer N, Platel B
    J Med Imaging (Bellingham), 2014 Jul;1(2):024501.
    PMID: 26158036 DOI: 10.1117/1.JMI.1.2.024501
    We investigated the benefits of incorporating texture features into an existing computer-aided diagnosis (CAD) system for classifying benign and malignant lesions in automated three-dimensional breast ultrasound images. The existing system takes into account 11 different features, describing different lesion properties; however, it does not include texture features. In this work, we expand the system by including texture features based on local binary patterns, gray level co-occurrence matrices, and Gabor filters computed from each lesion to be diagnosed. To deal with the resulting large number of features, we proposed a combination of feature-oriented classifiers combining each group of texture features into a single likelihood, resulting in three additional features used for the final classification. The classification was performed using support vector machine classifiers, and the evaluation was done with 10-fold cross validation on a dataset containing 424 lesions (239 benign and 185 malignant lesions). We compared the classification performance of the CAD system with and without texture features. The area under the receiver operating characteristic curve increased from 0.90 to 0.91 after adding texture features ([Formula: see text]).
    Matched MeSH terms: ROC Curve
  15. Wong VW, Irles M, Wong GL, Shili S, Chan AW, Merrouche W, et al.
    Gut, 2019 11;68(11):2057-2064.
    PMID: 30658997 DOI: 10.1136/gutjnl-2018-317334
    OBJECTIVE: The latest model of vibration-controlled transient elastography (VCTE) automatically selects M or XL probe according to patients' body built. We aim to test the application of a unified interpretation of VCTE results with probes appropriate for the body mass index (BMI) and hypothesise that this approach is not affected by hepatic steatosis.

    DESIGN: We prospectively recruited 496 patients with non-alcoholic fatty liver disease who underwent VCTE by both M and XL probes within 1 week before liver biopsy.

    RESULTS: 391 (78.8%) and 433 (87.3%) patients had reliable liver stiffness measurement (LSM) (10 successful acquisitions and IQR:median ratio ≤0.30) by M and XL probes, respectively (p<0.001). The area under the receiver operating characteristic curves was similar between the two probes (0.75-0.88 for F2-4, 0.83-0.91 for F4). When used in the same patient, LSM by XL probe was lower than that by M probe (mean difference 2.3 kPa). In contrast, patients with BMI ≥30 kg/m2 had higher LSM regardless of the probe used. When M and XL probes were used in patients with BMI <30 and ≥30 kg/m2, respectively, they yielded nearly identical median LSM at each fibrosis stage and similar diagnostic performance. Severe steatosis did not increase LSM or the rate of false-positive diagnosis by XL probe.

    CONCLUSION: High BMI but not severe steatosis increases LSM. The same LSM cut-offs can be used without further adjustment for steatosis when M and XL probes are used according to the appropriate BMI.

    Matched MeSH terms: ROC Curve
  16. Guo L, Wang Y, Xu X, Cheng KK, Long Y, Xu J, et al.
    J Proteome Res, 2021 01 01;20(1):346-356.
    PMID: 33241931 DOI: 10.1021/acs.jproteome.0c00431
    Identification of phosphorylation sites is an important step in the function study and drug design of proteins. In recent years, there have been increasing applications of the computational method in the identification of phosphorylation sites because of its low cost and high speed. Most of the currently available methods focus on using local information around potential phosphorylation sites for prediction and do not take the global information of the protein sequence into consideration. Here, we demonstrated that the global information of protein sequences may be also critical for phosphorylation site prediction. In this paper, a new deep neural network model, called DeepPSP, was proposed for the prediction of protein phosphorylation sites. In the DeepPSP model, two parallel modules were introduced to extract both local and global features from protein sequences. Two squeeze-and-excitation blocks and one bidirectional long short-term memory block were introduced into each module to capture effective representations of the sequences. Comparative studies were carried out to evaluate the performance of DeepPSP, and four other prediction methods using public data sets The F1-score, area under receiver operating characteristic curves (AUROC), and area under precision-recall curves (AUPRC) of DeepPSP were found to be 0.4819, 0.82, and 0.50, respectively, for S/T general site prediction and 0.4206, 0.73, and 0.39, respectively, for Y general site prediction. Compared with the MusiteDeep method, the F1-score, AUROC, and AUPRC of DeepPSP were found to increase by 8.6, 2.5, and 8.7%, respectively, for S/T general site prediction and by 20.6, 5.8, and 18.2%, respectively, for Y general site prediction. Among the tested methods, the developed DeepPSP method was also found to produce best results for different kinase-specific site predictions including CDK, mitogen-activated protein kinase, CAMK, AGC, and CMGC. Taken together, the developed DeepPSP method may offer a more accurate phosphorylation site prediction by including global information. It may serve as an alternative model with better performance and interpretability for protein phosphorylation site prediction.
    Matched MeSH terms: ROC Curve
  17. Ahmad Fuad Abdul Rahim, Mohd Jamil Yaacob, Muhamad Saiful Bahri Yusoff
    ASEAN Journal of Psychiatry, 2010;11(1):36-43.
    MyJurnal
    Objective: To determine the sensitivity, specificity and internal consistency of the Malay version GHQ-12 among medical student population. This study determined the appropriate GHQ-12 score to detect distressed medical students. Methods: The Malay version of GHQ-12 was derived based on two sources which were the original version GHQ-12 and the validated Malay version 30-items GHQ. The GHQ-12 and the Malay version Beck Depression Inventory-II (BDI-II) were administered to a total of 141 medical students. Distress diagnoses were made based on the Malay version BDI-II. ROC curve analysis was applied to determine the sensitivity and specificity of the GHQ-12 by testing against the BDI-II. Reliability analysis (Cronbach’s alpha and item total correlation) was applied to test internal consistency of the
    GHQ-12. The analysis was done using SPSS version 12.Results: The GHQ-12 sensitivity and specificity at cut-off point of 3/4 was 81.3% and 75.3% respectively with positive predictive value (PPV) of 62.9% as well as area under ROC curve more than 0.7. The Cronbach’s alpha value of the GHQ-12 was 0.85.Conclusion: This study showed the Malay version GHQ-12 is a valid and reliable screening tool in detecting distressed medical students. The
    GHQ-12 score equal to or more than 4 was considered as significant distress.
    Matched MeSH terms: ROC Curve
  18. Yusoff MSB
    MyJurnal
    Objective: To determine the sensitivity, specificity and internal consistency of the Malay version GHQ-30 among medical student population. This study also determined the level of agreement between GHQ-30 and M-BDI.
    Methods: The Malay version GHQ-30 and Malay version Beck Depression Inventory (M-BDI) were administered to 190 medical students. ROC curve analysis was applied to determine the sensitivity and specificity of the GHQ-30 by testing against the M-BDI diagnoses. Reliability and Kappa analysis were applied to test internal consistency of the GHQ and to determine the level of agreement between GHQ-30 and M-BDI respectively.
    Results: 141 (74.2%) medical students participated in this study. The GHQ-30 sensitivity and specificity at cut-off point of 5/6 was 87.5% and 80.6% respectively with positive predictive value (PPV) of 70% as well as area under ROC curve was 0.84. The Cronbach’s alpha value of the GHQ-30 was 0.93. The Kappa coefficient was 0.64 (p<0.001).
    Conclusion: This study showed the Malay version GHQ-30 is a valid and reliable screening tool in detecting distressed medical students. The GHQ-30 score equal to or more than 6 was considered as significant distress. The GHQ-30 showed a good level of agreement with M-BDI in detecting distressed medical students.
    Keywords: Kelantan; Malaysia; medical student
    Matched MeSH terms: ROC Curve
  19. Dheeb Albashish, Shahnorbanun Sahran, Azizi Abdullah, Nordashima Abd Shukor, Suria Hayati Md Pauzi
    MyJurnal
    The Gleason grading system assists in evaluating the prognosis of men with prostate cancer. Cancers with a higher score are more aggressive and have a worse prognosis. The pathologists observe the tissue components (e.g. lumen, nuclei) of the histopathological image to grade it. The differentiation between Grade 3 and Grade 4 is the most challenging, and receives the most consideration from scholars. However, since the grading is subjective and time-consuming, a reliable computer-aided prostate cancer diagnosing techniques are in high demand. This study proposed an ensemble computer-added system (CAD) consisting of two single classifiers: a) a specialist, trained specifically for texture features of the lumen and the other for nuclei tissue component; b) a fusion method to aggregate the decision of the single classifiers. Experimental results show promising results that the proposed ensemble system (area under the ROC curve (Az) of 88.9% for Grade 3 versus Grad 4 classification task) impressively outperforms the single classifier of nuclei (Az=87.7) and lumen (Az=86.6).
    Matched MeSH terms: ROC Curve
  20. Ow LL, Subramaniam N, Kamisan Atan I, Friedman T, Martin A, Dietz HP
    Female Pelvic Med Reconstr Surg, 2018 7 7;25(6):415-418.
    PMID: 29979358 DOI: 10.1097/SPV.0000000000000608
    OBJECTIVE: Genital hiatus (Gh) and perineal body (Pb) are part of the Pelvic Organ Prolapse Quantification assessment system, but it is unclear whether measurements should be taken at rest or on Valsalva. This study was designed to assess the predictive value of Gh and Pb measurements obtained at rest and on Valsalva for signs and symptoms of pelvic organ prolapse (POP).

    METHODS: This is a retrospective study involving 416 women who presented to a tertiary urogynecology unit with symptoms of pelvic floor dysfunction. Genital hiatus and Pb were measured at rest and on maximal Valsalva. The strength of association between binary markers of POP and measurements of Gh/Pb was estimated using logistic regression analysis. Receiver operator characteristic statistics were used to compare predictive values of Gh and Pb measurements obtained at rest and on Valsalva.

    RESULTS: A total of 451 women were seen during the study period. Thirty-five were excluded owing to missing data, leaving 416. Fifty-four percent (n = 223) complained of POP symptoms. On examination, 80% (n = 332) had significant POP (stage 2+ in anterior or posterior compartments or stage 1+ in the central compartment). On imaging, significant POP was diagnosed in 66% (n = 275). Mean hiatal area was 22 cm (SD, 7; range, 5-49 cm) at rest and 30 cm (SD, 10; range, 11-69 cm) on Valsalva. Genital hiatus and Pb measured on Valsalva were consistently stronger predictors of prolapse symptoms and objective prolapse (by clinician examination and by ultrasound) than at Gh and Pb measured at rest. The corresponding area under the curve values were significantly larger for Gh/Pb measures on Valsalva after adjusting for multiple confounders.

    CONCLUSIONS: Genital hiatus/Pb measured on maximal Valsalva is a superior predictor of symptoms and signs of POP compared with Gh/Pb at rest.

    Matched MeSH terms: ROC Curve
Filters
Contact Us

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

External Links