AI-CORUL

Machine Learning

 
Master_-_DHRi_Website_Project_Cover_Page.jpg

 

ARTIFICIAL INTELLIGENCE FOR THE DIAGNOSIS OF CORNEAL ULCER 

 

NMRR ID-23-00262-OKU

 

Visual impairments have significantly impacted the global disease economic burden with loss of cost of productivity approximated to be USD 411 billion, as compared to significantly lower approximated cost for gap addressing the unmet need of vision impairment (estimated of USD 25 billion). Corneal blindness is undeniably an important contributing factor to total visual impairments but commonly under-reported in the developing countries. A systematic review showed one study in India reported direct costs for corneal opacity treatment with an amount of $116 ppp and productivity losses costs of $39 ppp. A total of 86.3% of the causes of blindness were preventable such as through early involvement of primary eye care for prevention of corneal opacity. Diagnosing corneal ulcers can be challenging especially from primary health care facilities without ophthalmology services. In recent years, deep learning approaches have shown to be a suitable method for diagnosing cases with difficulties in defining or quantifying image characteristics. However, there are limited studies published on artificial intelligence for corneal images in Malaysia. Thus, our study team aims to develop a deep learning model to diagnose and classify the different types of corneal ulcers for early initiation of treatments to prevent future complications.

 

 

iTBXR

Machine Learning

itb_xr.jpg

 

TESTING AND VALIDATION OF MACHINE LEARNING MODEL FOR TUBERCULOSIS SCREENING USING CHEST RADIOGRAPHS IN MALAYSIAN POPULATION

 

NMRR ID-23-00114-ETO

 

iTBXR, a vital component of the iTB initiatives, builds upon the groundwork laid by the iTB-REPOXR project. It is specifically designed to revolutionize tuberculosis screening using chest radiographs, contributing significantly to the global and national goal of ending TB by 2035.

By capitalizing on the rich iTB-REPOXR database, iTBXR is pioneering Malaysia's first-ever AI-driven solution for TB diagnosis, marking a significant milestone in the nation's fight against this disease.

iTBXR employs advanced AI algorithms and machine learning techniques to identify TB indicators swiftly and accurately within chest X-rays. This approach not only expedites diagnosis but also enhances its precision, ensuring timely and effective treatment for those at risk.

Furthermore, iTBXR aligns with global efforts to combat TB by reducing transmission risks. Prompt detection means that affected individuals can receive timely treatment, ultimately curbing the disease's spread. This initiative complements Sustainable Development Goal 3, which aims to ensure universal health and well-being.

iTBXR's AI-driven TB screening, empowered by the iTB-REPOXR database, represents the nation’s step toward a TB-free world by 2035. It underscores Malaysia's dedication to addressing this global health challenge and exemplifies the transformative potential of AI in healthcare.

 

 

iTB-REPOXR

Machine Learning

itb_repoxr.jpg

TESTING AND VALIDATION OF MACHINE LEARNING MODEL FOR TUBERCULOSIS SCREENING USING CHEST RADIOGRAPHS IN MALAYSIAN POPULATION

 

NMRR ID-23-00114-ETO

 

iTB-REPOXR, part of the broader iTB project, is a pioneering initiative that leverages advanced technology to transform medical diagnosis, while also contributing to the global and national efforts to end tuberculosis by 2035. This endeavor focuses on creating a comprehensive repository consisting of chest radiographs and associated clinical information. The primary purpose of this repository is to facilitate the development of machine learning techniques specifically tailored for medical image analysis, with a primary emphasis on diagnosing lung diseases, including the prominent case of tuberculosis.

The core essence of iTB-REPOXR lies in its foundational role, laying the groundwork for a more ambitious undertaking known as  iTBXR. This subsequent phase is characterized by the aspiration to construct an artificial intelligence (AI) model of remarkable sophistication, engineered to scrutinize and diagnose an extensive array of lung-related ailments. The significance of this endeavor is underscored by its objective to identify not just tuberculosis but a diverse spectrum of at least 12 distinct lung diseases and disorders. By creating a vast reservoir of chest radiographs supplemented with clinical insights, this initiative provides fertile ground for the evolution of AI-powered medical image analysis. Such advancements have the potential to redefine the landscape of healthcare, offering enhanced accuracy and efficiency in disease diagnosis and treatment planning.

By establishing a comprehensive repository with iTB-REPOXR and validating machine learning algorithms for lung disease diagnosis, it paves the way for iTBXR's more ambitious aim of creating an AI model capable of identifying a diverse array of lung-related conditions. Through these initiatives, the healthcare industry stands poised to embrace a new era of precision medicine and improved patient care.

 

Cof'e

Machine Learning

Tracie X 2.0

Machine Learning

 

TracieX2.png

 

PORTABLE BREATHALYZER FOR RAPID COVID-19 SCREENING 2.0

 

RSCH ID-22-00022-SPI

 

This is a sequel to the Tracie project after a hardware upgrade. This study is sponsored by M&B Healthcare Sdn. Bhd and Silver Factory  Technology, Singapore. The aim of this study is to validate the diagnostic capability of the upgraded hardware and enhanced algorithm in the current COVID-19 situation. This study was conducted for 6 months beginning 2nd quarter of 2022.