MyMedR

Displaying all 8 publications

Abstract:

Sort:

Reflections of Malaysian parents of children with developmental disabilities on their experiences with AAC

Joginder Singh S, Hussein NH, Mustaffa Kamal R, Hassan FH

Augment Altern Commun, 2017 Jun;33(2):110-120.
PMID: 28387140 DOI: 10.1080/07434618.2017.1309457

Parents play an important role in the successful implementation of AAC. Previous research has indicated that parents in different countries have varying perceptions about the use of AAC and face different challenges in its implementation. To date, there is limited information about the use of AAC by children in Malaysia or parents' views about its use. The aim of this study was to explore Malaysian parents' perception of AAC and their experience when supporting their children who use AAC. For this study, 12 parents of children with autism spectrum disorder and cerebral palsy were involved in semi-structured individual interviews. Qualitative content analysis was used to analyze interview data. Following analysis, three themes were identified: (a) impact of the use of AAC, (b) challenges faced, and (c) hopes and expectations. Participants reported that the use of AAC had a positive impact on their children, but that they faced challenges related to the child, the settings, and the system itself, as well as a lack of time and support. Findings from this study provide an insight for Malaysian speech therapists about the challenges faced by parents when supporting their children who use AAC, and how important it is to overcome these challenges to ensure successful implementation of AAC.
Parents' perception on the use of augmentative and alternative communication by children with complex communication needs in Malaysia

Joginder Singh S, Mohd Ayob N, Hassan FH

Disabil Rehabil Assist Technol, 2023 Jan;18(1):118-126.
PMID: 36344474 DOI: 10.1080/17483107.2022.2140850

PURPOSE: Children with developmental disabilities who have complex communication needs (CCN) frequently need to use augmentative and alternative communication (AAC) to communicate effectively and efficiently. Speech-language pathologists (SLPs) often work closely with parents and other professionals when deciding on the best AAC system to introduce to these children. This study aimed to describe the use of AAC by children with CCN in Malaysia as reported by their parents.
MATERIALS AND METHOD: An online survey distributed for this study was completed by 235 parents.
RESULTS: Most of the parents of children with CCN who participated in this study reported that their children used low-tech AAC systems. A majority of respondents were satisfied with their child's AAC system. Parental satisfaction was positively associated with the frequency of use and whether the use of AAC helped parents understand the child better. Challenges reported by parents when using AAC and the reason some families abandoned the use of AAC were similar. Examples of challenges include parents having limited time and the child lacking the motivation to use the AAC system.
CONCLUSION: The findings of this study suggest the importance of SLPs actively involving parents in the selection of their children's AAC system so they are agreeable with the system introduced and continuously supporting children and their families to encourage and sustain the use of AAC. Implications for rehabilitationSpeech-language pathologists (SLPs) can create communication opportunities for the child to use augmentative and alternative communication (AAC) and experience success, teach parents how to incorporate AAC into the family's daily routine and activities, and reduce the demands on parents by preparing the AAC materials and programming the AAC system where possible.SLPs can provide ongoing support to school teachers to equip them with the necessary knowledge and skills to support the use of AAC in the classroom.
Fulltext Leveraging transfer learning with deep learning for crime prediction

Butt UM, Letchmunan S, Hassan FH, Koh TW

PLoS One, 2024;19(4):e0296486.
PMID: 38630687 DOI: 10.1371/journal.pone.0296486

Crime remains a crucial concern regarding ensuring a safe and secure environment for the public. Numerous efforts have been made to predict crime, emphasizing the importance of employing deep learning approaches for precise predictions. However, sufficient crime data and resources for training state-of-the-art deep learning-based crime prediction systems pose a challenge. To address this issue, this study adopts the transfer learning paradigm. Moreover, this study fine-tunes state-of-the-art statistical and deep learning methods, including Simple Moving Averages (SMA), Weighted Moving Averages (WMA), Exponential Moving Averages (EMA), Long Short Term Memory (LSTM), Bi-directional Long Short Term Memory (BiLSTMs), and Convolutional Neural Networks and Long Short Term Memory (CNN-LSTM) for crime prediction. Primarily, this study proposed a BiLSTM based transfer learning architecture due to its high accuracy in predicting weekly and monthly crime trends. The transfer learning paradigm leverages the fine-tuned BiLSTM model to transfer crime knowledge from one neighbourhood to another. The proposed method is evaluated on Chicago, New York, and Lahore crime datasets. Experimental results demonstrate the superiority of transfer learning with BiLSTM, achieving low error values and reduced execution time. These prediction results can significantly enhance the efficiency of law enforcement agencies in controlling and preventing crime.
Fulltext Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy

Butt UM, Letchmunan S, Hassan FH, Koh TW

PLoS One, 2022;17(9):e0274172.
PMID: 36070317 DOI: 10.1371/journal.pone.0274172

The continued urbanization poses several challenges for law enforcement agencies to ensure a safe and secure environment. Countries are spending a substantial amount of their budgets to control and prevent crime. However, limited efforts have been made in the crime prediction area due to the deficiency of spatiotemporal crime data. Several machine learning, deep learning, and time series analysis techniques are exploited, but accuracy issues prevail. Thus, this study proposed a Bidirectional Long Short Term Memory (Bi-LSTM) and Exponential Smoothing (ES) hybrid for crime forecasting. The proposed technique is evaluated using New York City crime data from 2010-2017. The proposed approach outperformed as compared to state-of-the-art Seasonal Autoregressive Integrated Moving Averages (SARIMA) with low Mean Absolute Percentage Error (MAPE) (0.3738, 0.3891, 0.3433,0.3964), Root Mean Square Error (RMSE)(13.146, 13.669, 13.104, 13.77), and Mean Absolute Error (MAE) (9.837, 10.896, 10.598, 10.721). Therefore, the proposed technique can help law enforcement agencies to prevent and control crime by forecasting crime patterns.
Zygomatic root abscess: A rare entity not to be forgotten!

Hong CX, Razuan NA, Alias A, Hassan FH, Nasseri Z

Auris Nasus Larynx, 2021 Aug;48(4):788-792.
PMID: 32513602 DOI: 10.1016/j.anl.2020.05.007

Zygomatic root abscess is a rare extracranial extratemporal complication of otitis media. To the best of our knowledge, there are only a few scattered cases of zygomatic root abscesses reported in the literature. We present an unusual case of a zygomatic root abscess in a 24 years old adult. He presented with one month duration of right zygomatic swelling. Otoscopic examination revealed superior and posterior external auditory canal wall sagging with an intact tympanic membrane. High Resolution Computed Tomography (HRCT) temporal bone revealed a rim enhancing lesion lateral to the zygomatic process with fluid filled mastoid air cells. He was managed with antibiotics and staged surgical interventions. He recovered well. Our case serves to shed light on the pathways of infection, clinical manifestations and timely staged surgical intervention in this rare pathology.
We're making it work! UKM'S Speech Sciences Programs' teleclinic experience in the time of COVID-19

Ahmad Rusli Y, Hassan FH, Haris SM, Mohd Azraai H, Md Almi SN

Med J Malaysia, 2021 08;76(Suppl 4):52-54.
PMID: 34558561

This paper highlights issues, challenges, and lessons learnt from implementing a speech-language therapy teleclinic service delivery model by the Speech Sciences Program, Universiti Kebangsaan Malaysia (UKM) during the wake of the recent COVID-19 pandemic. The teleclinic service provision was initially started to help our student cohorts attain and complete the required direct contact speechlanguage therapy clinical hours for graduation during the pandemic. It has since evolved to be an integral part of the clinical practicum curriculum and a service delivery model that is here to stay. Although far from perfect, the program hopes to systematically continue our endeavours in telerehabilitation as one of our niche areas, realising the wealth of benefits that this service delivery model has to offer.
Fulltext Comparisons of Clients' and Caregivers' Satisfaction Across Conventional, Virtual, and Hybrid Speech-Language Therapy Services in Malaysia

Hassan FH, Zakaria AS, Ahmad Rusli Y, Haris SM, Mohd Azraai H

Patient Prefer Adherence, 2023;17:1731-1740.
PMID: 37492636 DOI: 10.2147/PPA.S407347

PURPOSE: This study compared the satisfaction of recipients of conventional speech-language therapy (C-SLT), speech-language teletherapy (SLTT), and hybrid speech-language therapy (H-SLT), and determined sociodemographic factors that affect their satisfaction.
PATIENTS AND METHODS: Participants were clients and caregivers of a speech-language clinic at a public university. Services were primarily provided by student clinicians, who were undergoing supervised clinical training. An online survey was distributed, which consisted of three sections: Background Information, Overall Satisfaction in SLT, and Satisfaction in SLTT. All participants completed the first two sections, while the third section was completed only by those who experienced SLTT or H-SLT.
RESULTS: Most of the respondents were caregivers (89.7%), female (79.4%), of Malay ethnicity (80.9%), have received tertiary education (77.9%), within the low-income category (66.2%), held a job (76.5%), and resided in central West Malaysia (83.8%). Many participants experienced C-SLT (51%), followed by H-SLT (34%), and SLTT (15%). There were no significant differences in the overall satisfaction of the participants across three modes of services delivery (F[2,67] = 0.02, p = 0.95), and in the satisfaction with teletherapy between the H-SLT and SLTT groups (t = 0.90, p = 0.38). Income was the only sociodemographic factor that was correlated with the satisfaction level in teletherapy (r = 0.37, p = 0.04).
Machine Learning Based Diabetes Classification and Prediction for Healthcare Applications

Butt UM, Letchmunan S, Ali M, Hassan FH, Baqir A, Sherazi HHR

J Healthc Eng, 2021;2021:9930985.
PMID: 34631003 DOI: 10.1155/2021/9930985

The remarkable advancements in biotechnology and public healthcare infrastructures have led to a momentous production of critical and sensitive healthcare data. By applying intelligent data analysis techniques, many interesting patterns are identified for the early and onset detection and prevention of several fatal diseases. Diabetes mellitus is an extremely life-threatening disease because it contributes to other lethal diseases, i.e., heart, kidney, and nerve damage. In this paper, a machine learning based approach has been proposed for the classification, early-stage identification, and prediction of diabetes. Furthermore, it also presents an IoT-based hypothetical diabetes monitoring system for a healthy and affected person to monitor his blood glucose (BG) level. For diabetes classification, three different classifiers have been employed, i.e., random forest (RF), multilayer perceptron (MLP), and logistic regression (LR). For predictive analysis, we have employed long short-term memory (LSTM), moving averages (MA), and linear regression (LR). For experimental evaluation, a benchmark PIMA Indian Diabetes dataset is used. During the analysis, it is observed that MLP outperforms other classifiers with 86.08% of accuracy and LSTM improves the significant prediction with 87.26% accuracy of diabetes. Moreover, a comparative analysis of the proposed approach is also performed with existing state-of-the-art techniques, demonstrating the adaptability of the proposed approach in many public healthcare applications.