Bluish veil detection and lesion classification using custom deep learnable layers with explainable artificial intelligence (XAI).

Melanoma, one of the deadliest types of skin cancer, accounts for thousands of fatalities globally. The bluish, blue-whitish, or blue-white veil (BWV) is a critical feature for diagnosing melanoma, yet research into detecting BWV in dermatological images is limited. This study utilizes a non-annotated skin lesion dataset, which is converted into an annotated dataset using a proposed imaging algorithm (color threshold techniques) on lesion patches based on color palettes. A Deep Convolutional Neural Network (DCNN) is designed and trained separately on three individual and combined dermoscopic datasets, using custom layers instead of standard activation function layers. The model is developed to categorize skin lesions based on the presence of BWV. The proposed DCNN demonstrates superior performance compared to the conventional BWV detection models across different datasets. The model achieves a testing accuracy of 85.71 % on the augmented PH2 dataset, 95.00 % on the augmented ISIC archive dataset, 95.05 % on the combined augmented (PH2+ISIC archive) dataset, and 90.00 % on the Derm7pt dataset. An explainable artificial intelligence (XAI) algorithm is subsequently applied to interpret the DCNN's decision-making process about the BWV detection. The proposed approach, coupled with XAI, significantly improves the detection of BWV in skin lesions, outperforming existing models and providing a robust tool for early melanoma diagnosis.

Exploring Malaysian schoolchildren's perception of the advantages and disadvantages of the ToothPoly board game: a qualitative study.

The effectiveness of children's oral health education (OHE) is determined by the appropriateness of the educational materials used, which can influence their attitude towards oral health. However, there is a lack of studies exploring the benefits of OHE materials from the perspective of schoolchildren. This study aimed to explore schoolchildren's opinions on the newly developed ToothPoly board game as an OHE tool. A qualitative approach using focus group discussions (FGDs) was conducted among 44 schoolchildren aged 12 years old from a public school in Malaysia. Convenience sampling was employed to recruit the schoolchildren. The ToothPoly board game was playtested and FGDs were conducted after the playtesting session ended. Data collection and analyses were performed concurrently until data saturation was reached. The data were transcribed and coded using Atlas.Ti software version 9.1.3 followed by the framework method analysis. Mixed opinions were observed among the schoolchildren with a majority expressing favourable opinions on the advantages of the ToothPoly board game as an OHE tool. Five themes emerged from the advantages aspect, i.e., fun and enjoyable, promote focus, attention and oral health-related learning, attractive board game features, and enhance peer interaction. Meanwhile, two themes emerged that were related to the disadvantages of the board game, i.e., "competition with online games and media" and "not practical for a large group activity". The findings showed that the ToothPoly board game was perceived as a useful, interactive, and enjoyable tool to learn about oral health in small groups. The findings of the study highlight the importance of tailoring OHE activities to fulfil the needs of specific target groups to ensure its acceptance and future success.

A novel online multi-task learning for COVID-19 multi-output spatio-temporal prediction.

In light of the ongoing COVID-19 pandemic, predicting its trend would significantly impact decision-making. However, this is not a straightforward task due to three main difficulties: temporal autocorrelation, spatial dependency, and concept drift caused by virus mutations and lockdown policies. Although machine learning has been extensively used in related work, no previous research has successfully addressed all three challenges simultaneously. To overcome this challenge, we developed a novel online multi-task regression algorithm that incorporates a chain structure to capture spatial dependency, the ADWIN drift detector to adapt to concept drift, and the lag time series feature to capture temporal autocorrelation. We conducted several comparative experiments based on the number of daily confirmed cases in 20 areas in California and affiliated cities. The results from our experiments demonstrate that our proposed model is superior in adapting to concept drift in COVID-19 data and capturing spatial dependencies across various regions. This leads to a significant improvement in prediction accuracy when compared to existing state-of-the-art batch machine learning methods, such as N-Beats, DeepAR, TCN, and LSTM.

Adolescents' opinions on the use of a smartphone application as an oral health education tool: A qualitative study.

Developing health-related smartphone applications for oral health education should consider the end-user's perspectives to ensure they will be usable. This study aimed to explore the opinions of secondary school students in Selangor, Malaysia regarding the use of a smartphone application for oral health education and to identify the features for an oral health education smartphone application from the perspectives of adolescents. Focus group discussions were conducted among Form Two (14-year-old) and Form Four (16-year-old) students from selected government secondary schools in Selangor utilising a semi-structured topic guide until data saturation was achieved. Data were analysed using framework analysis. Ten focus group discussions were conducted involving 77 participants. Mixed opinions were recorded on the use of health-related smartphone applications for oral health education. The preferred features in a health-related smartphone application are disease detection, have games and rewards, educational and fun, access to a dentist, reminders, and user-friendliness. Adolescents are aware of the positive aspect of using health-related smartphone applications for oral health education; however, they are wary of the need to install one. Nevertheless, identifying adolescents' preferred features of an oral health education app is the first step in developing an application tailored to their needs. Smartphone application could be a timely strategy to improve oral health education delivery and behaviour improvement for this age group.

Motivators and barriers to oral hygiene self-care among adolescents in Malaysia: A qualitative study.

OBJECTIVE: Having good oral hygiene self-care, especially a regular toothbrushing habit will promote lifelong oral health. Therefore, understanding the factors that influence an adolescent's oral hygiene behaviour is important in developing effective oral health programmes for this age group. This study aimed to explore the motivators and barriers to adolescents' oral hygiene self-care by exploring the perspectives of secondary school students from three government schools in the state of Selangor, Malaysia. METHODS: Focus group discussions (FGD) were conducted with Form 2 (14-years-old) and Form 4 (16-years-old) students from selected secondary schools in Selangor using a semi-structured topic guide until data saturation was reached. Data were transcribed verbatim and analysed using framework method analysis. RESULTS: A total of 10 FGDs were conducted involving 77 adolescents. The motivators for good oral hygiene self-care were appearance, fear of oral disease, consequences of oral disease and past toothache experience. The barriers for oral hygiene self-care were poor attitude towards oral care, lack of confidence in toothbrushing skills, snacking habit and the taste of toothpaste. CONCLUSION: Understanding the motivators and barriers to adolescents' oral hygiene self-care is the first step in designing effective oral health education messages. The findings from this study can be used as a guide for oral health education programmes and development of materials that fulfil the needs of the adolescent population.

Exploring the opinions of secondary school students on the strengths and weaknesses of the school dental service in Selangor, Malaysia: a qualitative study.

BACKGROUND: The Malaysian School Dental Service (SDS) was introduced to provide systematic and comprehensive dental care to school students. The service encompasses promotive, preventive, and, curative dental care. This study aimed to undertake a process evaluation of the SDS based on the perspectives of government secondary school students in Selangor, Malaysia. METHODS: The study adopted a qualitative approach to explore the opinions of secondary school students on the SDS implementation in their schools. Data from focus group discussions involving Form Two (14-year-olds) and Form Four (16-year-olds) students from the selected schools were transcribed verbatim and coded using the NVivo software before framework method analysis was conducted. RESULTS: Among the strengths of the SDS were the convenience for students to undergo annual oral examination and dental treatment without having to visit dental clinics outside the school. The SDS also reduced possible financial burdens resulting from dental treatment costs, especially among students from low-income families. Furthermore, SDS helped to improve oral health awareness. However, the oral health education provided by the SDS personnel was deemed infrequent while the content and method of delivery were perceived to be less interesting. The poor attitude of the SDS personnel was also reported by the students. CONCLUSION: The SDS provides effective and affordable dental care to secondary school students. However, the oral health promotion and education activities need to be improved to keep up with the evolving needs of the target audience.

A New Local Fractional Entropy-Based Model for Kidney MRI Image Enhancement.

Kidney image enhancement is challenging due to the unpredictable quality of MRI images, as well as the nature of kidney diseases. The focus of this work is on kidney images enhancement by proposing a new Local Fractional Entropy (LFE)-based model. The proposed model estimates the probability of pixels that represent edges based on the entropy of the neighboring pixels, which results in local fractional entropy. When there is a small change in the intensity values (indicating the presence of edge in the image), the local fractional entropy gives fine image details. Similarly, when no change in intensity values is present (indicating smooth texture), the LFE does not provide fine details, based on the fact that there is no edge information. Tests were conducted on a large dataset of different, poor-quality kidney images to show that the proposed model is useful and effective. A comparative study with the classical methods, coupled with the latest enhancement methods, shows that the proposed model outperforms the existing methods.