Displaying publications 41 - 60 of 909 in total

Abstract:
Sort:
  1. Kang CC, Lee TY, Lim WF, Yeo WWY
    Clin Transl Sci, 2023 Nov;16(11):2078-2094.
    PMID: 37702288 DOI: 10.1111/cts.13640
    Moving away from traditional "one-size-fits-all" treatment to precision-based medicine has tremendously improved disease prognosis, accuracy of diagnosis, disease progression prediction, and targeted-treatment. The current cutting-edge of 5G network technology is enabling a growing trend in precision medicine to extend its utility and value to the smart healthcare system. The 5G network technology will bring together big data, artificial intelligence, and machine learning to provide essential levels of connectivity to enable a new health ecosystem toward precision medicine. In the 5G-enabled health ecosystem, its applications involve predictive and preventative measurements which enable advances in patient personalization. This review aims to discuss the opportunities, challenges, and prospects posed to 5G network technology in moving forward to deliver personalized treatments and patient-centric care via a precision medicine approach.
    Matched MeSH terms: Machine Learning
  2. Mansor N, Awang H, Amuthavalli Thiyagarajan J, Mikton C, Diaz T
    Age Ageing, 2023 Oct 28;52(Suppl 4):iv118-iv132.
    PMID: 37902520 DOI: 10.1093/ageing/afad101
    OBJECTIVE: this study aims to conduct a systematic review on available instruments for measuring older persons' ability to learn, grow and make decisions and to critically review the measurement properties of the identified instruments.

    METHODS: we searched six electronic databases, which include PubMed, Embase, PsycINFO, SciELO, ERIC and AgeLine, between January 2000 and April 2022. Reference lists of the included papers were also manually searched. The COSMIN (CONsensus-based Standards for the selection of health Measurement Instruments) guidelines were used to evaluate the measurement properties and the quality of evidence for each instrument.

    RESULTS: 13 instruments from 29 studies were included for evaluation of their measurement properties. Of the 13 reviewed, 6 were on the ability to learn, 3 were on the ability to grow and 4 were on the ability to make decisions. The review found no single instrument that measured all three constructs in unidimensional or multidimensional scales. Many of the instruments were found to have sufficient overall rating on content validity, structural validity, internal consistency and cross-cultural validity. The quality of evidence was rated as low due to a limited number of related validation studies.

    CONCLUSION: a few existing instruments to assess the ability to learn, grow and make decisions of older people can be identified in the literature. Further research is needed in validating them against functional, real-world outcomes.

    Matched MeSH terms: Learning*
  3. Jeppu AK, Kumar KA, Sethi A
    BMC Med Educ, 2023 Oct 06;23(1):734.
    PMID: 37803418 DOI: 10.1186/s12909-023-04734-y
    BACKGROUND: Modern clinical practice increasingly relies on collaborative, cooperative and team-based approaches for effective patient care. Recently, Jigsaw cooperative learning has gained attention in medical education. There is a need for studies in Southeast Asian context to establish its effectives in developing various core competencies expected of health professionals such as interpersonal, communication, collaborative, and teamwork skills. This current study explores the impact of using Jigsaw Cooperative Learning on undergraduate medical students.

    METHOD: An explanatory mixed method research design was carried out on first year medical students at a private university in Malaysia. In Phase I, a survey was conducted to explore the effectiveness of jigsaw learning. Descriptive and inferential statistics were calculated using SPSS. In Phase II, a focus group interview was conducted to explore their in-depth experiences. Qualitative data were thematically analysed.

    RESULTS: Fifty-seven students participated in the survey and seven students took part in the focus group interview. Quantitative data analysis showed a statistically significant improvement in the student's individual accountability, promotive interaction, positive interdependence, interpersonal skill, communication skill, teamwork skill, critical thinking and consensus building after jigsaw learning sessions. Qualitative data explained their experiences in-depth.

    CONCLUSION: Jigsaw cooperative learning improves collaboration, communication, cooperation and critical thinking among the undergraduate medical students. Educators should use jigsaw learning methods to encourage effective collaboration and team working. Future studies should explore the effectiveness of the jigsaw cooperative learning technique in promoting interprofessional collaboration in the workplace.

    Matched MeSH terms: Learning
  4. Lin GSS, Foo JY, Foong CC
    BMC Med Educ, 2023 Oct 02;23(1):716.
    PMID: 37784112 DOI: 10.1186/s12909-023-04717-z
    BACKGROUND: Dental materials science is an important subject, but research on curriculum mapping in preclinical dental materials science courses is still scarce. The present study aimed to conduct a curriculum mapping in analysing elements and suggesting recommendations for an institutional dental materials science course.

    METHODS: Curriculum mapping was conducted for the Year 2 undergraduate dental materials science course (Bachelor of Dental Surgery programme) in a Malaysian dental school. Based on Harden's framework, the following steps were used to map the curriculum of the institutional dental materials science course: (1) scoping the task; (2) deciding the mapping format; (3) populating the windows, and (4) establishing the links. Two analysts reviewed the curriculum independently. Their respective analyses were compared, and discrepancies were discussed until reaching a consensus. A SWOT analysis was also conducted to evaluate the strengths, weaknesses, opportunities, and threats associated with the curriculum.

    RESULTS: Course learning outcomes, course contents, levels of cognitive and psychomotor competencies, learning opportunities, learning resources, learning locations, assessments, timetable, staff, curriculum management and students' information were successfully scoped from the institutional dental materials science course. The present curriculum's strengths included comprehensiveness, alignment with standards, adequate learning opportunities, well-defined assessment methods, and sufficient learning resources. However, the identified weaknesses were repetition in curriculum content, limited emphasis on the psychomotor domain, dependency on a single academic staff, and limited integration of technology. The SWOT analysis highlighted the opportunities for curriculum improvement, such as revising repetitive content, emphasising the psychomotor domain, and incorporating advanced teaching strategies and technology.

    CONCLUSIONS: The present dental materials science curriculum demonstrated several strengths with some areas for improvement. The findings suggested the need to revise and optimise the course content to address gaps and enhance student learning outcomes. Ongoing monitoring and evaluation are necessary to ensure the curriculum remains aligned with emerging trends and advancements in dental materials science.

    Matched MeSH terms: Learning
  5. Ravindiran G, Hayder G, Kanagarathinam K, Alagumalai A, Sonne C
    Chemosphere, 2023 Oct;338:139518.
    PMID: 37454985 DOI: 10.1016/j.chemosphere.2023.139518
    Clean air is critical component for health and survival of human and wildlife, as atmospheric pollution is associated with a number of significant diseases including cancer. However, due to rapid industrialization and population growth, activities such as transportation, household, agricultural, and industrial processes contribute to air pollution. As a result, air pollution has become a significant problem in many cities, especially in emerging countries like India. To maintain ambient air quality, regular monitoring and forecasting of air pollution is necessary. For that purpose, machine learning has emerged as a promising technique for predicting the Air Quality Index (AQI) compared to conventional methods. Here we apply the AQI to the city of Visakhapatnam, Andhra Pradesh, India, focusing on 12 contaminants and 10 meteorological parameters from July 2017 to September 2022. For this purpose, we employed several machine learning models, including LightGBM, Random Forest, Catboost, Adaboost, and XGBoost. The results show that the Catboost model outperformed other models with an R2 correlation coefficient of 0.9998, a mean absolute error (MAE) of 0.60, a mean square error (MSE) of 0.58, and a root mean square error (RMSE) of 0.76. The Adaboost model had the least effective prediction with an R2 correlation coefficient of 0.9753. In summary, machine learning is a promising technique for predicting AQI with Catboost being the best-performing model for AQI prediction. Moreover, by leveraging historical data and machine learning algorithms enables accurate predictions of future urban air quality levels on a global scale.
    Matched MeSH terms: Machine Learning
  6. Mohd Faizal AS, Hon WY, Thevarajah TM, Khor SM, Chang SW
    Med Biol Eng Comput, 2023 Oct;61(10):2527-2541.
    PMID: 37199891 DOI: 10.1007/s11517-023-02841-y
    Acute myocardial infarction (AMI) or heart attack is a significant global health threat and one of the leading causes of death. The evolution of machine learning has greatly revamped the risk stratification and death prediction of AMI. In this study, an integrated feature selection and machine learning approach was used to identify potential biomarkers for early detection and treatment of AMI. First, feature selection was conducted and evaluated before all classification tasks with machine learning. Full classification models (using all 62 features) and reduced classification models (using various feature selection methods ranging from 5 to 30 features) were built and evaluated using six machine learning classification algorithms. The results showed that the reduced models performed generally better (mean AUPRC via random forest (RF) algorithm for recursive feature elimination (RFE) method ranges from 0.8048 to 0.8260, while for random forest importance (RFI) method, it ranges from 0.8301 to 0.8505) than the full models (mean AUPRC via RF: 0.8044). The most notable finding of this study was the identification of a five-feature model that included cardiac troponin I, HDL cholesterol, HbA1c, anion gap, and albumin, which had achieved comparable results (mean AUPRC via RF: 0.8462) as to the models that containing more features. These five features were proven by the previous studies as significant risk factors for AMI or cardiovascular disease and could be used as potential biomarkers to predict the prognosis of AMI patients. From the medical point of view, fewer features for diagnosis or prognosis could reduce the cost and time of a patient as lesser clinical and pathological tests are needed.
    Matched MeSH terms: Machine Learning
  7. Kim YJ
    Medicine (Baltimore), 2023 Sep 29;102(39):e35143.
    PMID: 37773837 DOI: 10.1097/MD.0000000000035143
    The objective of this study was to investigate the impact of the problem-based learning (PBL) method on Neurology education for Traditional Chinese Medicine (TCM) undergraduate students. This observational study was conducted during the 2020/02 and 2020/04 intakes of the third year TCM undergraduate students at School of Traditional Chinese Medicine, Xiamen University Malaysia. A total of 86 students were enrolled in the study and randomly assigned to either conventional learning groups or PBL groups. Students who missed more than 1 session of the course or did not complete the questionnaires during the evaluation periods were excluded from the study (n = 0). An independent sample t test was used to compare the results between the 2 groups, with a significance level set as P 
    Matched MeSH terms: Learning; Problem-Based Learning/methods
  8. Za'im NAN, Al-Dhief FT, Azman M, Alsemawi MRM, Abdul Latiff NMA, Mat Baki M
    J Otolaryngol Head Neck Surg, 2023 Sep 20;52(1):62.
    PMID: 37730624 DOI: 10.1186/s40463-023-00661-6
    BACKGROUND: A multidimensional voice quality assessment is recommended for all patients with dysphonia, which requires a patient visit to the otolaryngology clinic. The aim of this study was to determine the accuracy of an online artificial intelligence classifier, the Online Sequential Extreme Learning Machine (OSELM), in detecting voice pathology. In this study, a Malaysian Voice Pathology Database (MVPD), which is the first Malaysian voice database, was created and tested.

    METHODS: The study included 382 participants (252 normal voices and 130 dysphonic voices) in the proposed database MVPD. Complete data were obtained for both groups, including voice samples, laryngostroboscopy videos, and acoustic analysis. The diagnoses of patients with dysphonia were obtained. Each voice sample was anonymized using a code that was specific to each individual and stored in the MVPD. These voice samples were used to train and test the proposed OSELM algorithm. The performance of OSELM was evaluated and compared with other classifiers in terms of the accuracy, sensitivity, and specificity of detecting and differentiating dysphonic voices.

    RESULTS: The accuracy, sensitivity, and specificity of OSELM in detecting normal and dysphonic voices were 90%, 98%, and 73%, respectively. The classifier differentiated between structural and non-structural vocal fold pathology with accuracy, sensitivity, and specificity of 84%, 89%, and 88%, respectively, while it differentiated between malignant and benign lesions with an accuracy, sensitivity, and specificity of 92%, 100%, and 58%, respectively. Compared to other classifiers, OSELM showed superior accuracy and sensitivity in detecting dysphonic voices, differentiating structural versus non-structural vocal fold pathology, and between malignant and benign voice pathology.

    CONCLUSION: The OSELM algorithm exhibited the highest accuracy and sensitivity compared to other classifiers in detecting voice pathology, classifying between malignant and benign lesions, and differentiating between structural and non-structural vocal pathology. Hence, it is a promising artificial intelligence that supports an online application to be used as a screening tool to encourage people to seek medical consultation early for a definitive diagnosis of voice pathology.

    Matched MeSH terms: Machine Learning*
  9. Sheikh Khozani Z, Ehteram M, Mohtar WHMW, Achite M, Chau KW
    Environ Sci Pollut Res Int, 2023 Sep;30(44):99362-99379.
    PMID: 37610542 DOI: 10.1007/s11356-023-29406-8
    A wastewater treatment plant (WWTP) is an essential part of the urban water cycle, which reduces concentration of pollutants in the river. For monitoring and control of WWTPs, researchers develop different models and systems. This study introduces a new deep learning model for predicting effluent quality parameters (EQPs) of a WWTP. A method that couples a convolutional neural network (CNN) with a novel version of radial basis function neural network (RBFNN) is proposed to simultaneously predict and estimate uncertainty of data. The multi-kernel RBFNN (MKRBFNN) uses two activation functions to improve the efficiency of the RBFNN model. The salp swarm algorithm is utilized to set the MKRBFNN and CNN parameters. The main advantage of the CNN-MKRBFNN-salp swarm algorithm (SSA) is to automatically extract features from data points. In this study, influent parameters (if) are used as inputs. Biological oxygen demand (BODif), chemical oxygen demand (CODif), total suspended solids (TSSif), volatile suspended solids (VSSif), and sediment (SEDef) are used to predict EQPs, including CODef, BODef, and TSSef. At the testing level, the Nash-Sutcliffe efficiencies of CNN-MKRBFNN-SSA are 0.98, 0.97, and 0.98 for predicting CODef, BODef, and TSSef. Results indicate that the CNN-MKRBFNN-SSA is a robust model for simulating complex phenomena.
    Matched MeSH terms: Machine Learning
  10. McEllistrem B, Owens M, Whitford DL
    Int J Med Educ, 2023 Aug 31;14:117-122.
    PMID: 37661729 DOI: 10.5116/ijme.64e3.740e
    OBJECTIVES: This study explores a method of transferring a post graduate medical education curriculum internationally and contextualising it to the local environment. This paper also explores the experiences of those local medical educationalists involved in the process.

    METHODS: Several methods were implemented. Firstly, a modified Delphi process for the contextualisation of learning outcomes was implemented with a purposefully sampled expert group of Malaysian Family Medicine Specialists. Secondly a small group review for supporting materials was undertaken. Finally, qualitative data in relation to the family medicine specialists' experiences of the processes was collected via online questionnaire and analysed via template analysis. Descriptive statistics were used.

    RESULTS: Learning outcomes were reviewed over three rounds; 95.9% (1691/1763) of the learning outcomes were accepted without modification, with the remainder requiring additions, modifications, or deletions. Supporting materials were extensively altered by the expert group. Template analysis showed that Family Medicine Specialists related positively to their involvement in the process, commenting on the amount of similarity in the medical curriculum whilst recognising differences in disease profiles and cultural approaches.

    CONCLUSIONS: Learning outcomes and associated material were transferable between "home" and "host" institution. Where differences were discovered this novel approach places "host" practitioners' experiences and knowledge central to the adaptation process, thereby rendering a fit for purpose curriculum. Host satisfaction with the outcome of the processes, as well as ancillary benefits were clearly identified.

    Matched MeSH terms: Learning
  11. Ting JSK, Tan YL, Veasuvalingam B, Yap AYM, Ghui SM, Yong JL, et al.
    Clin Exp Dermatol, 2023 Aug 25;48(9):998-1006.
    PMID: 37097177 DOI: 10.1093/ced/llad149
    BACKGROUND: To date, to our knowledge, there has not been a study on dermatological teaching in the preclinical years (usually the first 2 years of medical school), where the majority of learning takes place in the form of lectures and seminars. Near-peer teaching (NPT) involves students who are at least one academic year more senior imparting knowledge to junior students. The principles behind scaffolding are having a more experienced teacher to guide learning, breaking down learning into smaller tasks and helping to build interest in learning.

    OBJECTIVES: To investigate the feasibility and effectiveness of NPT in scaffolding dermatological learning among preclinical-year medical students.

    METHODS: Near-peer teachers who are content experts in dermatology taught alongside conventional teaching with lecturers. We employed five quiz questions before and after the case launch lecture, where students were first exposed to dermatology. We also invited students to provide feedback using a questionnaire on NPT in dermatology at the end of the case 8 teaching week.

    RESULTS: In total, 74 students participated in the pre- and post-lecture quiz questions, and 47 completed feedback. There was overwhelmingly positive feedback towards NPT, and various learning theories can help explain the success of this project.

    CONCLUSIONS: Preclinical students enjoy dermatological teaching with the involvement of suitable near-peers. With the professional barrier removed, students can better relate to near-peers (and vice versa). Helping students understand the relevance of dermatology in the clinical setting at an early stage and adopting learning tools such as mnemonics, summary tables, comparison tables and mapping teaching with the learning curriculum clearly helped students learn about dermatology.

    Matched MeSH terms: Learning
  12. Lin GSS, Tan WW, Foong CC
    BMC Oral Health, 2023 Aug 13;23(1):571.
    PMID: 37574553 DOI: 10.1186/s12903-023-03293-4
    BACKGROUND: Effective teaching of dental materials science is crucial for dental students to develop a comprehensive understanding of materials used in clinical practice. However, literature on educators' views on teaching this subject is still scarce. This qualitative study aimed to explore the lived experiences of dental educators in teaching dental materials science subjects, thereby addressing potential gaps and enhancing teaching practices.

    METHODS: Thirteen dental educators from East and Southeast Asian countries (Malaysia, China, Indonesia, Thailand, South Korea, and Japan) participated in the present study. The present study adopted a transcendental phenomenological approach. One-to-one semi-structured online interviews were conducted. Interviews were recorded and transcribed verbatim. Thematic analysis was employed to identify patterns in the educators' experiences.

    RESULTS: Three themes emerged from the present study. First, perceptions of the importance of dental materials science, highlighting its relevance in clinical practice, patient care, and lifelong learning. Second, the challenges faced in teaching dental materials science include limited instructional time, complex content, and insufficient resources. Third, specific strategies, such as applying interactive teaching methods, integrating clinical scenarios, and promoting critical thinking skills have been suggested to enhance teaching and learning.

    CONCLUSION: Understanding dental educators' experiences can improve dental materials science education, curriculum development, teaching methods, and faculty training programmes, ultimately enhancing the knowledge and skills of dental students in this field.

    Matched MeSH terms: Learning
  13. Thagaard J, Broeckx G, Page DB, Jahangir CA, Verbandt S, Kos Z, et al.
    J Pathol, 2023 Aug;260(5):498-513.
    PMID: 37608772 DOI: 10.1002/path.6155
    The clinical significance of the tumor-immune interaction in breast cancer is now established, and tumor-infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple-negative (estrogen receptor, progesterone receptor, and HER2-negative) breast cancer and HER2-positive breast cancer. How computational assessments of TILs might complement manual TIL assessment in trial and daily practices is currently debated. Recent efforts to use machine learning (ML) to automatically evaluate TILs have shown promising results. We review state-of-the-art approaches and identify pitfalls and challenges of automated TIL evaluation by studying the root cause of ML discordances in comparison to manual TIL quantification. We categorize our findings into four main topics: (1) technical slide issues, (2) ML and image analysis aspects, (3) data challenges, and (4) validation issues. The main reason for discordant assessments is the inclusion of false-positive areas or cells identified by performance on certain tissue patterns or design choices in the computational implementation. To aid the adoption of ML for TIL assessment, we provide an in-depth discussion of ML and image analysis, including validation issues that need to be considered before reliable computational reporting of TILs can be incorporated into the trial and routine clinical management of patients with triple-negative breast cancer. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
    Matched MeSH terms: Machine Learning
  14. Ahad MA, Chear NJ, Keat LG, Has ATC, Murugaiyah V, Hassan Z
    Ageing Res Rev, 2023 Aug;89:101990.
    PMID: 37343678 DOI: 10.1016/j.arr.2023.101990
    Research employing a bio-enhanced fraction of Clitoria ternatea (CT) to treat cognitive decline in the animal model has not yet been found. This study aimed to determine the neuroprotective effect of CT root bioactive fraction (CTRF) in chronic cerebral hypoperfusion (CCH) rat model. CTRF and its major compound, clitorienolactones A (CLA), were obtained using column chromatography. A validated HPLC-UV method was employed for the standardization of CTRF. CCH rats were given orally either vehicle or fraction (10, 20 and 40 mg/kg). Behavioural and hippocampal neuroplasticity studies were conducted following 4 weeks post-surgery. The brain hippocampus was extracted for proteins and neurotransmitters analyses. HPLC analysis showed that CTRF contained 25% (w/w) of CLA. All tested doses of CTRF and CLA (10 mg/kg) significantly restored cognitive deficits and reversed the inhibition of neuroplasticity by CCH. However, only CTRF (40 mg/kg) and CLA (10 mg/kg) significantly reversed the elevation of amyloid-beta plaque. Subsequently, treatment with CTRF (40 mg/kg) and CLA (10 mg/kg) alleviated the downregulation of molecular synaptic signalling proteins levels caused by CCH. The neurotransmitters level was restored following treatment of CTRF and CLA. Our finding suggested that CTRF improves memory and neuroplasticity in CCH rats which was mainly contributed by CLA.
    Matched MeSH terms: Maze Learning
  15. Othman SA, Kamarudin Y, Sivarajan S, Soh EX, Lau MN, Zakaria NN, et al.
    Eur J Dent Educ, 2023 Aug;27(3):419-427.
    PMID: 35579042 DOI: 10.1111/eje.12823
    OBJECTIVE: To explore students' perception on the implementation of flipped classroom (FC) combined with formative assessment during the undergraduate teaching of orthodontic wire-bending skills.

    METHODS: Third-year undergraduate dental students were taught wire-bending skills via FC teaching method using a series of pre-recorded online video demonstrations. As part of the formative assessment, the students were given the results and assessment rubrics of their prior wire-bending assessment before every subsequent session. Purposive sampling method for focus group discussion was used to recruit eight students comprising four high achievers and four low achievers. Strengths, weaknesses and suggestions for improvement of the FC with formative assessment were explored. Data were transcribed and thematically analysed.

    RESULTS: Students perceived that FC allowed for a more convenient and flexible learning experience with personalised learning and improved in-class teaching efficiency. The pre-recorded online videos were useful to aid in teaching wire-bending skills but lacked three-dimensional representation of the wire-bending process. Students suggested better standardisation of instructions and access to the marking rubric before and after assessment.

    CONCLUSIONS: FC teaching with continuous formative assessment and constructive feedback as a form of personalised learning was viewed favourably by students. The implementation of periodic individual feedback can further enhance their learning experience.

    Matched MeSH terms: Learning*; Problem-Based Learning
  16. Mohd Yani AA, Ahmad MS, Ngah NA, Md Sabri BA
    Eur J Dent Educ, 2023 Aug;27(3):449-456.
    PMID: 35579452 DOI: 10.1111/eje.12826
    Gauging dental graduates' perceptions of their university training and of how it prepares them for professional practice is useful in measuring the quality and adequacy of the curriculum to which they were exposed.

    OBJECTIVES: This study aimed to evaluate the perceptions of dental graduates' educational environment as well as preparedness to practice, and how these two components are correlated.

    METHODS: A self-administered, validated questionnaire, developed from previous studies, was distributed to dental graduates of a public Malaysian university (n = 178, response rate = 60%) via online and postal surveys. Bivariate analyses were carried out using Spearman's rank-order correlation (Spearman's Rho, significance level p 

    Matched MeSH terms: Learning
  17. Letchumanan N, Wong JHD, Tan LK, Ab Mumin N, Ng WL, Chan WY, et al.
    J Digit Imaging, 2023 Aug;36(4):1533-1540.
    PMID: 37253893 DOI: 10.1007/s10278-022-00753-1
    This study investigates the feasibility of using texture radiomics features extracted from mammography images to distinguish between benign and malignant breast lesions and to classify benign lesions into different categories and determine the best machine learning (ML) model to perform the tasks. Six hundred and twenty-two breast lesions from 200 retrospective patient data were segmented and analysed. Three hundred fifty radiomics features were extracted using the Standardized Environment for Radiomics Analysis (SERA) library, one of the radiomics implementations endorsed by the Image Biomarker Standardisation Initiative (IBSI). The radiomics features and selected patient characteristics were used to train selected machine learning models to classify the breast lesions. A fivefold cross-validation was used to evaluate the performance of the ML models and the top 10 most important features were identified. The random forest (RF) ensemble gave the highest accuracy (89.3%) and positive predictive value (66%) and likelihood ratio of 13.5 in categorising benign and malignant lesions. For the classification of benign lesions, the RF model again gave the highest likelihood ratio of 3.4 compared to the other models. Morphological and textural radiomics features were identified as the top 10 most important features from the random forest models. Patient age was also identified as one of the significant features in the RF model. We concluded that machine learning models trained against texture-based radiomics features and patient features give reasonable performance in differentiating benign versus malignant breast lesions. Our study also demonstrated that the radiomics-based machine learning models were able to emulate the visual assessment of mammography lesions, typically used by radiologists, leading to a better understanding of how the machine learning model arrive at their decision.
    Matched MeSH terms: Machine Learning
  18. Jamil N, Zainal ZA, Alias SH, Chong LY, Hashim R
    Res Social Adm Pharm, 2023 Aug;19(8):1131-1145.
    PMID: 37202279 DOI: 10.1016/j.sapharm.2023.05.006
    BACKGROUND: Self-management interventions often employ behaviour change techniques in order to produce desired target behaviours that are necessary for day-to-day living with a chronic disease. Despite the large number of self-management interventions for patients with chronic obstructive pulmonary disease (COPD), previously reported interventions have been typically delivered by healthcare providers other than the pharmacist.

    OBJECTIVE: This systematic review examined the components of pharmacists-delivered COPD self-management interventions according to an established taxonomy of behaviour change techniques (BCTs).

    METHODS: A systematic search was conducted on PubMed, ScienceDirect, OVID, and Google Scholar from January 2011 to December 2021 for studies of pharmacist-delivered self-management interventions in COPD patients.

    RESULTS: A total of seventeen studies of intervention were eligible for inclusion in the narrative review. Interventions were educational and were delivered individually and face-to-face for the first session. Across studies, pharmacists spent an average of 35 min on the first meeting and had an average of 6 follow-up sessions. Recurrent BCTs in pharmacist interventions were "Information on the health consequence", "Feedback on behaviour", "Instruction on how to perform a behaviour", "Demonstration of the behaviour" and "Behavioural practice/rehearsal".

    CONCLUSIONS: Pharmacists have provided interventions towards improving health behaviours, especially on adherence and usage of inhaler devices for patients with COPD. Future self-management interventions should be designed using the identified BCTs for the improvement of COPD self-management and disease outcomes.

    Matched MeSH terms: Learning
  19. Lim JY, Lim KM, Lee CP, Tan YX
    Neural Netw, 2023 Aug;165:19-30.
    PMID: 37263089 DOI: 10.1016/j.neunet.2023.05.037
    Few-shot learning aims to train a model with a limited number of base class samples to classify the novel class samples. However, to attain generalization with a limited number of samples is not a trivial task. This paper proposed a novel few-shot learning approach named Self-supervised Contrastive Learning (SCL) that enriched the model representation with multiple self-supervision objectives. Given the base class samples, the model is trained with the base class loss. Subsequently, contrastive-based self-supervision is introduced to minimize the distance between each training sample with their augmented variants to improve the sample discrimination. To recognize the distant sample, rotation-based self-supervision is proposed to enable the model to learn to recognize the rotation degree of the samples for better sample diversity. The multitask environment is introduced where each training sample is assigned with two class labels: base class label and rotation class label. Complex augmentation is put forth to help the model learn a deeper understanding of the object. The image structure of the training samples are augmented independent of the base class information. The proposed SCL is trained to minimize the base class loss, contrastive distance loss, and rotation class loss simultaneously to learn the generic features and improve the novel class performance. With the multiple self-supervision objectives, the proposed SCL outperforms state-of-the-art few-shot approaches on few-shot image classification benchmark datasets.
    Matched MeSH terms: Learning*
  20. Lim ZN, Ng WJ, Lee CC
    Z Evid Fortbild Qual Gesundhwes, 2023 Aug;180:103-106.
    PMID: 37357108 DOI: 10.1016/j.zefq.2023.05.019
    BACKGROUND: In Malaysia, advance care planning is still in its infancy. There is no national implementation of Advance Care Planning.

    AIMS: To describe the national state of advance care planning development in Malaysia METHODS: Review of relevant advance care planning literature locally and internationally was undertaken.

    RESULTS: Positive development in Malaysia includes implementation of advance care planning at institutional level, initiatives to develop educational programmes as well as research activities to understand the attitude and perception of patients on advance care planning. However, there remain challenges, including lack of knowledge and awareness, lack of legislative framework to guide advance care planning implementation and lack of strong initiatives at a national level.

    CONCLUSIONS: It is evident that there is much to learn nationally and internationally about ACP before any decision on implementation of ACP is made in Malaysia. ACP is a public health issue and requires concerted effort of all stakeholders, including Government agencies, academic institutions, and non-government organizations to raise public awareness. More research is needed to shape the future direction of ACP development in Malaysia.

    Matched MeSH terms: Learning
Filters
Contact Us

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

External Links