Displaying publications 61 - 80 of 261 in total

Abstract:
Sort:
  1. Remote protein homology detection and fold recognition using two-layer support vector machine classifiers
    Muda HM, Saad P, Othman RM
    Comput Biol Med, 2011 Aug;41(8):687-99.
    PMID: 21704312 DOI: 10.1016/j.compbiomed.2011.06.004
    Remote protein homology detection and fold recognition refer to detection of structural homology in proteins where there are small or no similarities in the sequence. To detect protein structural classes from protein primary sequence information, homology-based methods have been developed, which can be divided to three types: discriminative classifiers, generative models for protein families and pairwise sequence comparisons. Support Vector Machines (SVM) and Neural Networks (NN) are two popular discriminative methods. Recent studies have shown that SVM has fast speed during training, more accurate and efficient compared to NN. We present a comprehensive method based on two-layer classifiers. The 1st layer is used to detect up to superfamily and family in SCOP hierarchy using optimized binary SVM classification rules. It used the kernel function known as the Bio-kernel, which incorporates the biological information in the classification process. The 2nd layer uses discriminative SVM algorithm with string kernel that will detect up to protein fold level in SCOP hierarchy. The results obtained were evaluated using mean ROC and mean MRFP and the significance of the result produced with pairwise t-test was tested. Experimental results show that our approaches significantly improve the performance of remote protein homology detection and fold recognition for all three different version SCOP datasets (1.53, 1.67 and 1.73). We achieved 4.19% improvements in term of mean ROC in SCOP 1.53, 4.75% in SCOP 1.67 and 4.03% in SCOP 1.73 datasets when compared to the result produced by well-known methods. The combination of first layer and second layer of BioSVM-2L performs well in remote homology detection and fold recognition even in three different versions of datasets.
    Matched MeSH terms: Artificial Intelligence
  2. Fulltext Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks
    Ardakani AA, Kanafi AR, Acharya UR, Khadem N, Mohammadi A
    Comput Biol Med, 2020 06;121:103795.
    PMID: 32568676 DOI: 10.1016/j.compbiomed.2020.103795
    Fast diagnostic methods can control and prevent the spread of pandemic diseases like coronavirus disease 2019 (COVID-19) and assist physicians to better manage patients in high workload conditions. Although a laboratory test is the current routine diagnostic tool, it is time-consuming, imposing a high cost and requiring a well-equipped laboratory for analysis. Computed tomography (CT) has thus far become a fast method to diagnose patients with COVID-19. However, the performance of radiologists in diagnosis of COVID-19 was moderate. Accordingly, additional investigations are needed to improve the performance in diagnosing COVID-19. In this study is suggested a rapid and valid method for COVID-19 diagnosis using an artificial intelligence technique based. 1020 CT slices from 108 patients with laboratory proven COVID-19 (the COVID-19 group) and 86 patients with other atypical and viral pneumonia diseases (the non-COVID-19 group) were included. Ten well-known convolutional neural networks were used to distinguish infection of COVID-19 from non-COVID-19 groups: AlexNet, VGG-16, VGG-19, SqueezeNet, GoogleNet, MobileNet-V2, ResNet-18, ResNet-50, ResNet-101, and Xception. Among all networks, the best performance was achieved by ResNet-101 and Xception. ResNet-101 could distinguish COVID-19 from non-COVID-19 cases with an AUC of 0.994 (sensitivity, 100%; specificity, 99.02%; accuracy, 99.51%). Xception achieved an AUC of 0.994 (sensitivity, 98.04%; specificity, 100%; accuracy, 99.02%). However, the performance of the radiologist was moderate with an AUC of 0.873 (sensitivity, 89.21%; specificity, 83.33%; accuracy, 86.27%). ResNet-101 can be considered as a high sensitivity model to characterize and diagnose COVID-19 infections, and can be used as an adjuvant tool in radiology departments.
    Matched MeSH terms: Artificial Intelligence
  3. Explainable deep learning ensemble for food image analysis on edge devices
    Tahir GA, Loo CK
    Comput Biol Med, 2021 12;139:104972.
    PMID: 34749093 DOI: 10.1016/j.compbiomed.2021.104972
    Food recognition systems recently garnered much research attention in the relevant field due to their ability to obtain objective measurements for dietary intake. This feature contributes to the management of various chronic conditions. Challenges such as inter and intraclass variations alongside the practical applications of smart glasses, wearable cameras, and mobile devices require resource-efficient food recognition models with high classification performance. Furthermore, explainable AI is also crucial in health-related domains as it characterizes model performance, enhancing its transparency and objectivity. Our proposed architecture attempts to address these challenges by drawing on the strengths of the transfer learning technique upon initializing MobiletNetV3 with weights from a pre-trained model of ImageNet. The MobileNetV3 achieves superior performance using the squeeze and excitation strategy, providing unequal weight to different input channels and contrasting equal weights in other variants. Despite being fast and efficient, there is a high possibility for it to be stuck in the local optima like other deep neural networks, reducing the desired classification performance of the model. Thus, we overcome this issue by applying the snapshot ensemble approach as it enables the M model in a single training process without any increase in the required training time. As a result, each snapshot in the ensemble visits different local minima before converging to the final solution which enhances recognition performance. On overcoming the challenge of explainability, we argue that explanations cannot be monolithic, since each stakeholder perceive the results', explanations based on different objectives and aims. Thus, we proposed a user-centered explainable artificial intelligence (AI) framework to increase the trust of the involved parties by inferencing and rationalizing the results according to needs and user profile. Our framework is comprehensive in terms of a dietary assessment app as it detects Food/Non-Food, food categories, and ingredients. Experimental results on the standard food benchmarks and newly contributed Malaysian food dataset for ingredient detection demonstrated superior performance on an integrated set of measures over other methodologies.
    Matched MeSH terms: Artificial Intelligence*
  4. Fulltext Generalizability assessment of COVID-19 3D CT data for deep learning-based disease detection
    Fallahpoor M, Chakraborty S, Heshejin MT, Chegeni H, Horry MJ, Pradhan B
    Comput Biol Med, 2022 Jun;145:105464.
    PMID: 35390746 DOI: 10.1016/j.compbiomed.2022.105464
    BACKGROUND: Artificial intelligence technologies in classification/detection of COVID-19 positive cases suffer from generalizability. Moreover, accessing and preparing another large dataset is not always feasible and time-consuming. Several studies have combined smaller COVID-19 CT datasets into "supersets" to maximize the number of training samples. This study aims to assess generalizability by splitting datasets into different portions based on 3D CT images using deep learning.

    METHOD: Two large datasets, including 1110 3D CT images, were split into five segments of 20% each. Each dataset's first 20% segment was separated as a holdout test set. 3D-CNN training was performed with the remaining 80% from each dataset. Two small external datasets were also used to independently evaluate the trained models.

    RESULTS: The total combination of 80% of each dataset has an accuracy of 91% on Iranmehr and 83% on Moscow holdout test datasets. Results indicated that 80% of the primary datasets are adequate for fully training a model. The additional fine-tuning using 40% of a secondary dataset helps the model generalize to a third, unseen dataset. The highest accuracy achieved through transfer learning was 85% on LDCT dataset and 83% on Iranmehr holdout test sets when retrained on 80% of Iranmehr dataset.

    CONCLUSION: While the total combination of both datasets produced the best results, different combinations and transfer learning still produced generalizable results. Adopting the proposed methodology may help to obtain satisfactory results in the case of limited external datasets.

    Matched MeSH terms: Artificial Intelligence
  5. Fulltext Automatic identification of hypertension and assessment of its secondary effects using artificial intelligence: A systematic review (2013-2023)
    Gudigar A, Kadri NA, Raghavendra U, Samanth J, Maithri M, Inamdar MA, et al.
    Comput Biol Med, 2024 Apr;172:108207.
    PMID: 38489986 DOI: 10.1016/j.compbiomed.2024.108207
    Artificial Intelligence (AI) techniques are increasingly used in computer-aided diagnostic tools in medicine. These techniques can also help to identify Hypertension (HTN) in its early stage, as it is a global health issue. Automated HTN detection uses socio-demographic, clinical data, and physiological signals. Additionally, signs of secondary HTN can also be identified using various imaging modalities. This systematic review examines related work on automated HTN detection. We identify datasets, techniques, and classifiers used to develop AI models from clinical data, physiological signals, and fused data (a combination of both). Image-based models for assessing secondary HTN are also reviewed. The majority of the studies have primarily utilized single-modality approaches, such as biological signals (e.g., electrocardiography, photoplethysmography), and medical imaging (e.g., magnetic resonance angiography, ultrasound). Surprisingly, only a small portion of the studies (22 out of 122) utilized a multi-modal fusion approach combining data from different sources. Even fewer investigated integrating clinical data, physiological signals, and medical imaging to understand the intricate relationships between these factors. Future research directions are discussed that could build better healthcare systems for early HTN detection through more integrated modeling of multi-modal data sources.
    Matched MeSH terms: Artificial Intelligence
  6. Clinical evaluation of watermarked medical images
    Zain JM, Fauzi AM, Aziz AA
    Conf Proc IEEE Eng Med Biol Soc, 2007 10 20;2006:5459-62.
    PMID: 17946306
    Digital watermarking medical images provides security to the images. The purpose of this study was to see whether digitally watermarked images changed clinical diagnoses when assessed by radiologists. We embedded 256 bits watermark to various medical images in the region of non-interest (RONI) and 480K bits in both region of interest (ROI) and RONI. Our results showed that watermarking medical images did not alter clinical diagnoses. In addition, there was no difference in image quality when visually assessed by the medical radiologists. We therefore concluded that digital watermarking medical images were safe in terms of preserving image quality for clinical purposes.
    Matched MeSH terms: Artificial Intelligence
  7. Biosensing based on surface-enhanced Raman spectroscopy as an emerging/next-generation point-of-care approach for acute myocardial infarction diagnosis
    Low JSY, Thevarajah TM, Chang SW, Goh BT, Khor SM
    Crit Rev Biotechnol, 2020 Dec;40(8):1191-1209.
    PMID: 32811205 DOI: 10.1080/07388551.2020.1808582
    Cardiovascular disease is a major global health issue. In particular, acute myocardial infarction (AMI) requires urgent attention and early diagnosis. The use of point-of-care diagnostics has resulted in the improved management of cardiovascular disease, but a major drawback is that the performance of POC devices does not rival that of central laboratory tests. Recently, many studies and advances have been made in the field of surface-enhanced Raman scattering (SERS), including the development of POC biosensors that utilize this detection method. Here, we present a review of the strengths and limitations of these emerging SERS-based biosensors for AMI diagnosis. The ability of SERS to multiplex sensing against existing POC detection methods are compared and discussed. Furthermore, SERS calibration-free methods that have recently been explored to minimize the inconvenience and eliminate the limitations caused by the limited linear range and interassay differences found in the calibration curves are outlined. In addition, the incorporation of artificial intelligence (AI) in SERS techniques to promote multivariate analysis and enhance diagnostic accuracy are discussed. The future prospects for SERS-based POC devices that include wearable POC SERS devices toward predictive, personalized medicine following the Fourth Industrial Revolution are proposed.
    Matched MeSH terms: Artificial Intelligence
  8. New insights in improving sustainability in meat production: opportunities and challenges
    Kumar P, Abubakar AA, Verma AK, Umaraw P, Adewale Ahmed M, Mehta N, et al.
    Crit Rev Food Sci Nutr, 2023 Nov;63(33):11830-11858.
    PMID: 35821661 DOI: 10.1080/10408398.2022.2096562
    Treating livestock as senseless production machines has led to rampant depletion of natural resources, enhanced greenhouse gas emissions, gross animal welfare violations, and other ethical issues. It has essentially instigated constant scrutiny of conventional meat production by various experts and scientists. Sustainably in the meat sector is a big challenge which requires a multifaced and holistic approach. Novel tools like digitalization of the farming system and livestock market, precision livestock farming, application of remote sensing and artificial intelligence to manage production and environmental impact/GHG emission, can help in attaining sustainability in this sector. Further, improving nutrient use efficiency and recycling in feed and animal production through integration with agroecology and industrial ecology, improving individual animal and herd health by ensuring proper biosecurity measures and selective breeding, and welfare by mitigating animal stress during production are also key elements in achieving sustainability in meat production. In addition, sustainability bears a direct relationship with various social dimensions of meat production efficiency such as non-market attributes, balance between demand and consumption, market and policy failures. The present review critically examines the various aspects that significantly impact the efficiency and sustainability of meat production.
    Matched MeSH terms: Artificial Intelligence*
  9. The role of artificial intelligence in the battle against antimicrobial-resistant bacteria
    Lau HJ, Lim CH, Foo SC, Tan HS
    Curr Genet, 2021 Jun;67(3):421-429.
    PMID: 33585980 DOI: 10.1007/s00294-021-01156-5
    Antimicrobial resistance (AMR) in bacteria is a global health crisis due to the rapid emergence of multidrug-resistant bacteria and the lengthy development of new antimicrobials. In light of this, artificial intelligence in the form of machine learning has been viewed as a potential counter to delay the spread of AMR. With the aid of AI, there are possibilities to predict and identify AMR in bacteria efficiently. Furthermore, a combination of machine learning algorithms and lab testing can help to accelerate the process of discovering new antimicrobials. To date, many machine learning algorithms for antimicrobial-resistance discovery had been created and vigorously validated. Most of these algorithms produced accurate results and outperformed the traditional methods which relied on sequence comparison within a database. This mini-review will provide an updated overview of antimicrobial design workflow using the latest machine-learning antimicrobial discovery algorithms in the last 5 years. With this review, we hope to improve upon the current AMR identification and antimicrobial development techniques by introducing the use of AI into the mix, including how the algorithms could be made more effective.
    Matched MeSH terms: Artificial Intelligence*
  10. Recent Applications of Artificial Intelligence in detection of Gastrointestinal, Hepatic and Pancreatic Diseases
    Kumar R, Khan FU, Sharma A, Aziz IB, Poddar NK
    Curr Med Chem, 2021 Apr 04.
    PMID: 33820515 DOI: 10.2174/0929867328666210405114938
    There is substantial progress in artificial intelligence (AI) algorithms and their medical sciences applications in the last two decades. AI-assisted programs have already been established for remotely health monitoring using sensors and smartphones. A variety of AI-based prediction models available for the gastrointestinal inflammatory, non-malignant diseases, and bowel bleeding using wireless capsule endoscopy, electronic medical records for hepatitis-associated fibrosis, pancreatic carcinoma using endoscopic ultrasounds. AI-based models may be of immense help for healthcare professionals in the identification, analysis, and decision support using endoscopic images to establish prognosis and risk assessment of patient's treatment using multiple factors. Although enough randomized clinical trials are warranted to establish the efficacy of AI-algorithms assisted and non-AI based treatments before approval of such techniques from medical regulatory authorities. In this article, available AI approaches and AI-based prediction models for detecting gastrointestinal, hepatic, and pancreatic diseases are reviewed. The limitation of AI techniques in such disease prognosis, risk assessment, and decision support are discussed.
    Matched MeSH terms: Artificial Intelligence
  11. Computational Approaches in the Discovery and Development of Therapeutic and Prophylactic Agents for Viral Diseases
    Gaurav A, Agrawal N, Al-Nema M, Gautam V
    Curr Top Med Chem, 2022;22(26):2190-2206.
    PMID: 36278463 DOI: 10.2174/1568026623666221019110334
    Over the last two decades, computational technologies have played a crucial role in antiviral drug development. Whenever a virus spreads and becomes a threat to global health, it brings along the challenge of developing new therapeutics and prophylactics. Computational drug and vaccine discovery has evolved quickly over the years. Some interesting examples of computational drug discovery are anti-AIDS drugs, where HIV protease and reverse transcriptase have been targeted by agents developed using computational methods. Various computational methods that have been applied to anti-viral research include ligand-based methods that rely on known active compounds, i.e., pharmacophore modeling, machine learning or classical QSAR; structure-based methods that rely on an experimentally determined 3D structure of the targets, i.e., molecular docking and molecular dynamics and methods for the development of vaccines such as reverse vaccinology; structural vaccinology and vaccine epitope prediction. This review summarizes these approaches to battle viral diseases and underscores their importance for anti-viral research. We discuss the role of computational methods in developing small molecules and vaccines against human immunodeficiency virus, yellow fever, human papilloma virus, SARS-CoV-2, and other viruses. Various computational tools available for the abovementioned purposes have been listed and described. A discussion on applying artificial intelligence-based methods for antiviral drug discovery has also been included.
    Matched MeSH terms: Artificial Intelligence
  12. Exploratory study on student perception on the use of chat AI in process-driven problem-based learning
    Hamid H, Zulkifli K, Naimat F, Che Yaacob NL, Ng KW
    Curr Pharm Teach Learn, 2023 Dec;15(12):1017-1025.
    PMID: 37923639 DOI: 10.1016/j.cptl.2023.10.001
    INTRODUCTION: With the increasing prevalence of artificial intelligence (AI) technology, it is imperative to investigate its influence on education and the resulting impact on student learning outcomes. This includes exploring the potential application of AI in process-driven problem-based learning (PDPBL). This study aimed to investigate the perceptions of students towards the use of ChatGPT) build on GPT-3.5 in PDPBL in the Bachelor of Pharmacy program.

    METHODS: Eighteen students with prior experience in traditional PDPBL processes participated in the study, divided into three groups to perform PDPBL sessions with various triggers from pharmaceutical chemistry, pharmaceutics, and clinical pharmacy fields, while utilizing chat AI provided by ChatGPT to assist with data searching and problem-solving. Questionnaires were used to collect data on the impact of ChatGPT on students' satisfaction, engagement, participation, and learning experience during the PBL sessions.

    RESULTS: The survey revealed that ChatGPT improved group collaboration and engagement during PDPBL, while increasing motivation and encouraging more questions. Nevertheless, some students encountered difficulties understanding ChatGPT's information and questioned its reliability and credibility. Despite these challenges, most students saw ChatGPT's potential to eventually replace traditional information-seeking methods.

    CONCLUSIONS: The study suggests that ChatGPT has the potential to enhance PDPBL in pharmacy education. However, further research is needed to examine the validity and reliability of the information provided by ChatGPT, and its impact on a larger sample size.

    Matched MeSH terms: Artificial Intelligence
  13. Fulltext What's been trending with OSCEs in pharmacy education over the last 20 years? A bibliometric review and content analysis
    Lim AS, Ling YL, Wilby KJ, Mak V
    Curr Pharm Teach Learn, 2024 Mar;16(3):212-220.
    PMID: 38171979 DOI: 10.1016/j.cptl.2023.12.028
    BACKGROUND: Objective structured clinical examinations (OSCEs) remain an integral part of pharmacy education. This study aimed to characterize key researchers, areas, and themes in pharmacy education OSCEs using a bibliometric review with content analysis.

    METHODS: A bibliometric review was conducted on literature from over 23 years from January 2000 to May 2023. Articles focusing on any type of OSCE research in pharmacy education in both undergraduate and postgraduate sectors were included. Articles were excluded if they were not original articles or not published in English. A summative content analysis was also conducted to identify key topics.

    RESULTS: A total of 192 articles were included in the analysis. There were 242 institutions that contributed to the OSCE literature in pharmacy education, with the leading country being Canada. Most OSCE research came from developed countries and were descriptive studies based on single institution data. The top themes emerging from content analysis were student perceptions on OSCE station styles (n = 98), staff perception (n = 19), grade assessment of OSCEs (n = 145), interprofessional education (n = 11), standardized patients (n = 12), and rubric development and standard setting (n = 8).

    IMPLICATIONS: There has been a growth in virtual OSCEs, interprofessional OSCEs, and artificial intelligence OSCEs. Communication rubrics and minimizing assessor variability are still trending research areas. There is scope to conduct more research on evaluating specific types of OSCEs, when best to hold an OSCE, and comparing OSCEs to other assessments.

    Matched MeSH terms: Artificial Intelligence*
  14. Fulltext MYNursingHome: A fully-labelled image dataset for indoor object classification
    Ismail A, Ahmad SA, Che Soh A, Hassan MK, Harith HH
    Data Brief, 2020 Oct;32:106268.
    PMID: 32984464 DOI: 10.1016/j.dib.2020.106268
    A fully labelled image dataset serves as a valuable tool for reproducible research inquiries and data processing in various computational areas, such as machine learning, computer vision, artificial intelligence and deep learning. Today's research on ageing is intended to increase awareness on research results and their applications to assist public and private sectors in selecting the right equipments for the elderlies. Many researches related to development of support devices and care equipment had been done to improve the elderly's quality of life. Indoor object detection and classification for autonomous systems require large annotated indoor images for training and testing of smart computer vision applications. This dataset entitled MYNursingHome is an image dataset for commonly used objects surrounding the elderlies in their home cares. Researchers may use this data to build up a recognition aid for the elderlies. This dataset was collected from several nursing homes in Malaysia comprises 37,500 digital images from 25 different indoor object categories including basket bin, bed, bench, cabinet and others.
    Matched MeSH terms: Artificial Intelligence
  15. Fulltext Data on the mechanisms of antidiarrhoeal activity of methanol leaf extract of Combretum hypopilinum Diels (Combretaceae): Involvement of opioidergic and (α1 and β)-adrenergic pathways
    Ahmad MH, Zezi AU, Anafi SB, Alhassan Z, Mohammed M, Danraka RN
    Data Brief, 2021 Jun;36:107155.
    PMID: 34041327 DOI: 10.1016/j.dib.2021.107155
    This article describes the dataset for the elucidation of the possible mechanisms of antidiarrhoeal actions of methanol leaves extract of Combretum hypopilinum (Diels) Combretaceae in mice. The plant has been used in traditional medicine to treat diarrhoea in Nigeria and other African countries. We introduce the data for the antidiarrhoeal activity of the methanol leaf extract of Combretum hypopilinum at 1,000 mg/kg investigated using charcoal meal test in mice with loperamide (5 mg/kg) as the standard antidiarrhoeal agent. To elucidate the possible mechanisms of its antidiarrhoeal action, naloxone (2 mg/kg), prazosin (1 mg/kg), yohimbine (2 mg/kg), propranolol (1 mg/kg), pilocarpine (1 mg/kg) and isosorbide dinitrate (150 mg/kg) were separately administered to different groups of mice 30 minutes before administration of the extract. Each mouse was dissected using dissecting set, and the small intestine was immediately removed from pylorus to caecum, placed lengthwise on moist filter paper and measured the distance travelled by charcoal relative to the length of the intestine using a calibrated ruler in centimetre. Besides, the peristaltic index and inhibition of charcoal movement of each animal were calculated and recorded. The methods for the data collection is similar to the one used to investigate the possible pathways involved in the antidiarrhoeal action of Combretum hypopilinum in mice in the research article by Ahmad et al. (2020) "Mechanisms of Antidiarrhoeal Activity of Methanol Leaf Extract of Combretum hypopilinum Diels (Combretaceae): Involvement of Opioidergic and (α1 and β)-Adrenergic Pathways" (https://doi.org/10.1016/j.jep.2020.113750) [1]. Therefore, this datasets could form a basis for in-depth research to elucidate further the pharmacological properties of the plant Combretum hypopilinum and its bioactive compounds to develop standardized herbal product and novel compound for management of diarrhoea. It could also be instrumental for evaluating the plant's pharmacological potentials using other computational-based and artificial intelligence approaches, including predictive modelling and simulation.
    Matched MeSH terms: Artificial Intelligence
  16. Global variations in diagnostic guidelines for Barrett's esophagus
    Kusano C, Singh R, Lee YY, Soh YSA, Sharma P, Ho KY, et al.
    Dig Endosc, 2022 Nov;34(7):1320-1328.
    PMID: 35475586 DOI: 10.1111/den.14342
    Endoscopic diagnosis of gastroesophageal junction and Barrett's esophagus is essential for surveillance and early detection of esophageal adenocarcinoma and esophagogastric junction cancer. Despite its small size, the gastroesophageal junction has many inherent problems, including marked differences in diagnostic methods for Barrett's esophagus in international guidelines. To define Barrett's esophagus, gastroesophageal junction location should be clarified. Although gastric folds and palisade vessels are landmarks for identifying this junction, they are sometimes difficult to observe due to air entry or reflux esophagitis. The possibility of diagnosing a malignancy associated with Barrett's esophagus <1 cm, identified using palisade vessels, should be re-examined. Nontargeted biopsies of Barrett's esophagus are commonly used to detect intestinal metaplasia, dysplasia, and cancer as described in the Seattle protocol. Barrett's esophagus with intestinal metaplasia has a high risk of becoming cancerous. Furthermore, the frequency of cancer in patients with Barrett's esophagus without intestinal metaplasia is high, and the guidelines differ on whether to include the presence of intestinal metaplasia in the diagnosis of Barrett's esophagus. Use of advanced imaging technologies, including narrow-band imaging with magnifying endoscopy and linked color imaging, is reportedly valid for diagnosing Barrett's esophagus. Furthermore, artificial intelligence has facilitated the diagnosis of Barrett's esophagus through its deep learning and image recognition capabilities. However, it is necessary to first use the endoscopic definition of the gastroesophageal junction, which is common in all countries, and then elucidate the characteristics of Barrett's esophagus in each region, for example, length differences in the risk of carcinogenesis with and without intestinal metaplasia.
    Matched MeSH terms: Artificial Intelligence
  17. Artificial intelligence in drug development: present status and future prospects
    Mak KK, Pichika MR
    Drug Discov Today, 2019 03;24(3):773-780.
    PMID: 30472429 DOI: 10.1016/j.drudis.2018.11.014
    Artificial intelligence (AI) uses personified knowledge and learns from the solutions it produces to address not only specific but also complex problems. Remarkable improvements in computational power coupled with advancements in AI technology could be utilised to revolutionise the drug development process. At present, the pharmaceutical industry is facing challenges in sustaining their drug development programmes because of increased R&D costs and reduced efficiency. In this review, we discuss the major causes of attrition rates in new drug approvals, the possible ways that AI can improve the efficiency of the drug development process and collaboration of pharmaceutical industry giants with AI-powered drug discovery firms.
    Matched MeSH terms: Artificial Intelligence*
  18. Fulltext IoT-based smart wheelchair system for physically impaired person
    Muhammad Afiq Mohd Aizam, Nor Shahanim Mohamad Hadis, Samihah Abdullah
    ESTEEM Academic Journal, 2020;16(1):59-73.
    MyJurnal
    Disabled persons usually require an assistant to help them in their daily routines especially for their mobility. The limitation of being physically impaired affects the quality of life in executing their daily routine especially the ones with a wheelchair. Pushing a wheelchair has its own side effects for the user especially the person with hands and arms impairments. This paper aims to develop a smart wheelchair system integrated with home automation. With the advent of the Internet of Things (IoT), a smart wheelchair can be operated using voice command through the Google assistant Software Development Kit (SDK). The smart wheelchair system and the home automation of this study were powered by Raspberry Pi 3 B+ and NodeMCU, respectively. Voice input commands were processed by the Google assistant Artificial Intelligence Yourself (AIY) to steer the movement of wheelchair. Users were able to speak to Google to discover any information from the website. For the safety of the user, a streaming camera was added on the wheelchair. An improvement to the wheelchair system that was added on the wheelchair is its combination with the home automation to help the impaired person to control their home appliances through Blynk application.
    Observations on three voice tones (low, medium and high) of voice command show that the minimum voice intensity for this smart wheelchair system is 68.2 dB. Besides, the user is also required to produce a clear voice command to increase the system accuracy.
    Matched MeSH terms: Artificial Intelligence
  19. Hybrid Harmony Search-Artificial Intelligence Models in Credit Scoring
    Goh RY, Lee LS, Seow HV, Gopal K
    Entropy (Basel), 2020 Sep 04;22(9).
    PMID: 33286758 DOI: 10.3390/e22090989
    Credit scoring is an important tool used by financial institutions to correctly identify defaulters and non-defaulters. Support Vector Machines (SVM) and Random Forest (RF) are the Artificial Intelligence techniques that have been attracting interest due to their flexibility to account for various data patterns. Both are black-box models which are sensitive to hyperparameter settings. Feature selection can be performed on SVM to enable explanation with the reduced features, whereas feature importance computed by RF can be used for model explanation. The benefits of accuracy and interpretation allow for significant improvement in the area of credit risk and credit scoring. This paper proposes the use of Harmony Search (HS), to form a hybrid HS-SVM to perform feature selection and hyperparameter tuning simultaneously, and a hybrid HS-RF to tune the hyperparameters. A Modified HS (MHS) is also proposed with the main objective to achieve comparable results as the standard HS with a shorter computational time. MHS consists of four main modifications in the standard HS: (i) Elitism selection during memory consideration instead of random selection, (ii) dynamic exploration and exploitation operators in place of the original static operators, (iii) a self-adjusted bandwidth operator, and (iv) inclusion of additional termination criteria to reach faster convergence. Along with parallel computing, MHS effectively reduces the computational time of the proposed hybrid models. The proposed hybrid models are compared with standard statistical models across three different datasets commonly used in credit scoring studies. The computational results show that MHS-RF is most robust in terms of model performance, model explainability and computational time.
    Matched MeSH terms: Artificial Intelligence
  20. Application of artificial intelligence methods for monsoonal river classification in Selangor river basin, Malaysia
    Wong YJ, Shimizu Y, Kamiya A, Maneechot L, Bharambe KP, Fong CS, et al.
    Environ Monit Assess, 2021 Jun 22;193(7):438.
    PMID: 34159431 DOI: 10.1007/s10661-021-09202-y
    Rivers in Malaysia are classified based on water quality index (WQI) that comprises of six parameters, namely, ammoniacal nitrogen (AN), biochemical oxygen demand (BOD), chemical oxygen demand (COD), dissolved oxygen (DO), pH, and suspended solids (SS). Due to its tropical climate, the impact of seasonal monsoons on river quality is significant, with the increased occurrence of extreme precipitation events; however, there has been little discussion on the application of artificial intelligence models for monsoonal river classification. In light of these, this study had applied artificial neural network (ANN) and support vector machine (SVM) models for monsoonal (dry and wet seasons) river classification using three of the water quality parameters to minimise the cost of river monitoring and associated errors in WQI computation. A structured trial-and-error approach was applied on input parameter selection and hyperparameter optimisation for both models. Accuracy, sensitivity, and precision were selected as the performance criteria. For dry season, BOD-DO-pH was selected as the optimum input combination by both ANN and SVM models, with testing accuracy of 88.7% and 82.1%, respectively. As for wet season, the optimum input combinations of ANN and SVM models were BOD-pH-SS and BOD-DO-pH with testing accuracy of 89.5% and 88.0%, respectively. As a result, both optimised ANN and SVM models have proven their prediction capacities for river classification, which may be deployed as effective and reliable tools in tropical regions. Notably, better learning and higher capacity of the ANN model for dataset characteristics extraction generated better predictability and generalisability than SVM model under imbalanced dataset.
    Matched MeSH terms: Artificial Intelligence
Related Terms
Filters
Contact Us

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

External Links