Displaying all 4 publications

Abstract:
Sort:
  1. Farook TH, Jamayet NB, Abdullah JY, Alam MK
    Pain Res Manag, 2021;2021:6659133.
    PMID: 33986900 DOI: 10.1155/2021/6659133
    Purpose: The study explored the clinical influence, effectiveness, limitations, and human comparison outcomes of machine learning in diagnosing (1) dental diseases, (2) periodontal diseases, (3) trauma and neuralgias, (4) cysts and tumors, (5) glandular disorders, and (6) bone and temporomandibular joint as possible causes of dental and orofacial pain.

    Method: Scopus, PubMed, and Web of Science (all databases) were searched by 2 reviewers until 29th October 2020. Articles were screened and narratively synthesized according to PRISMA-DTA guidelines based on predefined eligibility criteria. Articles that made direct reference test comparisons to human clinicians were evaluated using the MI-CLAIM checklist. The risk of bias was assessed by JBI-DTA critical appraisal, and certainty of the evidence was evaluated using the GRADE approach. Information regarding the quantification method of dental pain and disease, the conditional characteristics of both training and test data cohort in the machine learning, diagnostic outcomes, and diagnostic test comparisons with clinicians, where applicable, were extracted.

    Results: 34 eligible articles were found for data synthesis, of which 8 articles made direct reference comparisons to human clinicians. 7 papers scored over 13 (out of the evaluated 15 points) in the MI-CLAIM approach with all papers scoring 5+ (out of 7) in JBI-DTA appraisals. GRADE approach revealed serious risks of bias and inconsistencies with most studies containing more positive cases than their true prevalence in order to facilitate machine learning. Patient-perceived symptoms and clinical history were generally found to be less reliable than radiographs or histology for training accurate machine learning models. A low agreement level between clinicians training the models was suggested to have a negative impact on the prediction accuracy. Reference comparisons found nonspecialized clinicians with less than 3 years of experience to be disadvantaged against trained models.

    Conclusion: Machine learning in dental and orofacial healthcare has shown respectable results in diagnosing diseases with symptomatic pain and with improved future iterations and can be used as a diagnostic aid in the clinics. The current review did not internally analyze the machine learning models and their respective algorithms, nor consider the confounding variables and factors responsible for shaping the orofacial disorders responsible for eliciting pain.

    Matched MeSH terms: Diagnostic Tests, Routine/instrumentation
  2. Kimura M, Teramoto I, Chan CW, Idris ZM, Kongere J, Kagaya W, et al.
    Malar J, 2018 Feb 07;17(1):72.
    PMID: 29415724 DOI: 10.1186/s12936-018-2214-8
    BACKGROUND: Rapid diagnosis of malaria using acridine orange (AO) staining and a light microscope with a halogen lamp and interference filter was deployed in some malaria-endemic countries. However, it has not been widely adopted because: (1) the lamp was weak as an excitation light and the set-up did not work well under unstable power supply; and, (2) the staining of samples was frequently inconsistent.

    METHODS: The halogen lamp was replaced by a low-cost, blue light-emitting diode (LED) lamp. Using a reformulated AO solution, the staining protocol was revised to make use of a concentration gradient instead of uniform staining. To evaluate this new AO diagnostic system, a pilot field study was conducted in the Lake Victoria basin in Kenya.

    RESULTS: Without staining failure, malaria infection status of about 100 samples was determined on-site per one microscopist per day, using the improved AO diagnostic system. The improved AO diagnosis had both higher overall sensitivity (46.1 vs 38.9%: p = 0.08) and specificity (99.0 vs 96.3%) than the Giemsa method (N = 1018), using PCR diagnosis as the standard.

    CONCLUSIONS: Consistent AO staining of thin blood films and rapid evaluation of malaria parasitaemia with the revised protocol produced superior results relative to the Giemsa method. This AO diagnostic system can be set up easily at low cost using an ordinary light microscope. It may supplement rapid diagnostic tests currently used in clinical settings in malaria-endemic countries, and may be considered as an inexpensive tool for case surveillance in malaria-eliminating countries.

    Matched MeSH terms: Diagnostic Tests, Routine/instrumentation*
  3. Mahendran P, Liew JWK, Amir A, Ching XT, Lau YL
    Malar J, 2020 Jul 10;19(1):241.
    PMID: 32650774 DOI: 10.1186/s12936-020-03314-5
    BACKGROUND: Plasmodium knowlesi and Plasmodium vivax are the predominant Plasmodium species that cause malaria in Malaysia and play a role in asymptomatic malaria disease transmission in Malaysia. The diagnostic tools available to diagnose malaria, such as microscopy and rapid diagnostic test (RDT), are less sensitive at detecting lower parasite density. Droplet digital polymerase chain reaction (ddPCR), which has been shown to have higher sensitivity at diagnosing malaria, allows direct quantification without the need for a standard curve. The aim of this study is to develop and use a duplex ddPCR assay for the detection of P. knowlesi and P. vivax, and compare this method to nested PCR and qPCR.

    METHODS: The concordance rate, sensitivity and specificity of the duplex ddPCR assay were determined and compared to nested PCR and duplex qPCR.

    RESULTS: The duplex ddPCR assay had higher analytical sensitivity (P. vivax = 10 copies/µL and P. knowlesi = 0.01 copies/µL) compared to qPCR (P. vivax = 100 copies/µL and P. knowlesi = 10 copies/µL). Moreover, the ddPCR assay had acceptable clinical sensitivity (P. vivax = 80% and P. knowlesi = 90%) and clinical specificity (P. vivax = 87.84% and P. knowlesi = 81.08%) when compared to nested PCR. Both ddPCR and qPCR detected more double infections in the samples.

    CONCLUSIONS: Overall, the ddPCR assay demonstrated acceptable efficiency in detection of P. knowlesi and P. vivax, and was more sensitive than nested PCR in detecting mixed infections. However, the duplex ddPCR assay still needs optimization to improve the assay's clinical sensitivity and specificity.

    Matched MeSH terms: Diagnostic Tests, Routine/instrumentation
  4. Amir A, Cheong FW, De Silva JR, Lau YL
    Parasit Vectors, 2018 01 23;11(1):53.
    PMID: 29361963 DOI: 10.1186/s13071-018-2617-y
    Every year, millions of people are burdened with malaria. An estimated 429,000 casualties were reported in 2015, with the majority made up of children under five years old. Early and accurate diagnosis of malaria is of paramount importance to ensure appropriate administration of treatment. This minimizes the risk of parasite resistance development, reduces drug wastage and unnecessary adverse reaction to antimalarial drugs. Malaria diagnostic tools have expanded beyond the conventional microscopic examination of Giemsa-stained blood films. Contemporary and innovative techniques have emerged, mainly the rapid diagnostic tests (RDT) and other molecular diagnostic methods such as PCR, qPCR and loop-mediated isothermal amplification (LAMP). Even microscopic diagnosis has gone through a paradigm shift with the development of new techniques such as the quantitative buffy coat (QBC) method and the Partec rapid malaria test. This review explores the different diagnostic tools available for childhood malaria, each with their characteristic strengths and limitations. These tools play an important role in making an accurate malaria diagnosis to ensure that the use of anti-malaria are rationalized and that presumptive diagnosis would only be a thing of the past.
    Matched MeSH terms: Diagnostic Tests, Routine/instrumentation*
Filters
Contact Us

Please provide feedback to Administrator ([email protected])

External Links