Saturday, July 13, 2024

AI Tools for Early Detection of Malnutrition: A Systematic Review

Similar articles

Malnutrition remains a pervasive yet frequently overlooked issue affecting both children and adults globally. The development of screening and diagnostic tools aimed at early detection is crucial to mitigate long-term health complications. While traditional methods rely on predefined questionnaires and consensus guidelines, the integration of artificial intelligence (AI) promises to revolutionize early detection and intervention strategies.

AI in Malnutrition Detection

A systematic literature review was conducted to gather detailed insights into patient demographics, screening tools, machine learning algorithms, data types, and variables employed in current AI-based malnutrition detection tools. Despite the promising potential of AI, more than 90% of the developed models are not yet integrated into everyday clinical practice. Supervised learning algorithms emerged as the most commonly utilized type, with disease-related malnutrition being the primary focus in most of the studies analyzed.

Challenges and Limitations

The review highlights several barriers to the widespread adoption of AI tools in clinical settings. These include issues related to data quality and volume, algorithm transparency, and the need for extensive validation. Moreover, there are concerns about the interoperability of these AI tools with existing healthcare systems, which can further impede market access. Addressing these challenges is essential for the broader implementation and acceptance of AI-driven solutions in malnutrition detection.

The current landscape of AI in malnutrition detection is characterized by significant research activity but limited practical application. Researchers are encouraged to focus on overcoming these barriers to facilitate the transition from theoretical models to real-world applications. This would not only enhance early detection but also improve patient outcomes and well-being.

Key Inferences

Important Findings:

  • Over 90% of AI models for malnutrition detection are not in routine clinical use.
  • Supervised learning models are the most popular approach.
  • Disease-related malnutrition is the most frequently studied category.
  • Data quality and volume are significant barriers to market access.
  • Interoperability with healthcare systems remains a critical challenge.

The findings of this review provide a valuable resource for researchers aiming to explore new directions in the use of AI for malnutrition detection. By addressing the highlighted challenges, there is potential for significant advancements in both the technology and its application, ultimately improving patient care and outcomes.

Original Article:

Adv Nutr. 2024 Jul 4:100264. doi: 10.1016/j.advnut.2024.100264. Online ahead of print.

ABSTRACT

You can follow our news on our Telegram and LinkedIn accounts.

Malnutrition among the population of the world is a frequent yet underdiagnosed problem in both children and adults. Development of malnutrition screening and diagnostic tools for early detection of malnutrition is necessary to prevent long-term complications to patients’ health and well-being. Most of these tools are based on predefined questionnaires and consensus guidelines. The use of artificial intelligence (AI) allows for automated tools to detect malnutrition in an earlier stage to prevent long-term consequences. In this study, a systematic literature review was carried out with the goal of providing detailed information on what patient groups, screening tools, machine learning algorithms, data types, and variables are being used as well as the current limitations and implementation stage of these AI based tools. The results showed that a staggering majority exceeding 90 percent of all AI models go unused in day-to-day clinical practice. Furthermore, supervised learning models seemed to be the most popular type of learning. Alongside this, disease-related malnutrition was the most common category of malnutrition found in the analysis of all primary studies. The current research provides a resource for researchers to identify directions for their research on the use of AI in in Malnutrition.

PMID:38971229 | DOI:10.1016/j.advnut.2024.100264

Subscribe to our newsletter

To be updated with all the latest news, offers and special announcements.

Latest article