Review Article
The Application of AI in Clinical Nutrition
Director Critical Care in SL Raheja, ISPEN- President, India. 2CEO: Docmode health technologies pvt Ltd, India.
*Corresponding Author: Sanjith Saseedharan,1Director Critical Care in SL Raheja, ISPEN- President, India. 2CEO: Docmode health technologies pvt Ltd, India.
Citation: S. Sanjith, L. Hans. (2024). The Application of AI in Clinical Nutrition. International Journal of Nutrition Research and Health, BioRes Scientia Publishers. 3(1):1-5. DOI: 10.59657/2871-6021.brs.24.032
Copyright: © 2024 Sanjith Saseedharan, this is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Received: August 06, 2024 | Accepted: October 10, 2024 | Published: November 30, 2024
Abstract
The concept of nutrition is moving towers therapy and helping in disease modification where the aim is to modify the contents of the diet in an attempt to attenuate the metabolic response to stress, to prevent oxidative cellular injury, prevent the scientific switching off of autophagy and to favorably modulate immune response. There are technical and ethical difficulties in performing experiments, formulating nutrition and delivering a comprehensive care are encountered. In most of the Indian ICU, enteral nutrition (EN) is very often prescribed by physicians with limited training in nutrition with use of approximations, estimations and sometimes even without scientific understanding. Generally, nutrition is not something that the average physician is even concerned about when it comes to illness and more-so in critical care. There is a dearth of trained dietitians in the country. The integration of technology can help in making critical care nutrition significantly scientific, simple and objective by helping to estimate the energy needs of the patient, probably determine the utilization of the proteins and calories and provide real time monitoring of the feed delivery by automated systems. Technology can further help in the data analysis with the help of electronic medical records for improving scientific knowhow. Infect the field of healthcare has witnessed a remarkable transformation in recent years, largely owing to the integration of Artificial Intelligence (AI) into various aspects of medical practice. AI, in its current state, has become a powerful tool for improving patient care, and one of its promising applications is in the realm of clinical nutrition. This article explores the growing significance of AI in clinical nutrition, highlighting its role in nutrition therapy across diverse healthcare settings.
Keywords: nutrition; patient; diabetes; diseases
Introduction
Understanding AI Today
Before delving into the application of AI in clinical nutrition, it is essential to define what AI represents today. Artificial Intelligence refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. These machines are capable of performing tasks that typically require human intelligence, such as problem-solving, decision-making, language understanding, and pattern recognition.
In the context of healthcare, AI leverages advanced algorithms and data analysis techniques to assist healthcare professionals in diagnosing diseases, designing treatment plans, and improving overall patient care. One notable application of AI in healthcare is Clinical Decision Support Systems (CDSS), which play a pivotal role in guiding healthcare providers through complex medical scenarios.
The Role of AI in Clinical Nutrition
Nutrition therapy has gained immense importance in modern healthcare, not only for disease prevention but also for aiding recovery and improving overall patient outcomes. AI has found its way into various healthcare domains, and clinical nutrition is no exception. Here are some key areas where AI is making a significant impact:
Outpatient Department (OPD)
In outpatient settings, AI-driven tools assist healthcare professionals in assessing patients' nutritional needs, planning personalized dietary interventions, and monitoring progress over time. These tools use patient data and medical guidelines to recommend tailored nutrition plans.
Critical Care Nutrition
In critical care units, AI plays a crucial role in optimizing the nutrition delivery for patients who are critically ill. AI-driven systems can calculate the precise nutritional requirements of patients, monitor their intake, and ensure that they receive the appropriate nutrients for their condition.
Women's Health and Maternity
AI-powered solutions are used to provide nutritional guidance to pregnant women, ensuring they receive the essential nutrients during pregnancy. These tools can help manage nutrition-related complications and support healthy pregnancies.
Diabetes Management
For individuals with diabetes, AI-based systems can assist in tracking blood glucose levels, analyzing dietary choices, and recommending suitable meal plans to help manage the condition effectively.
Home Care and Palliative Care
AI is also becoming increasingly valuable in-home care and palliative care settings. It helps caregivers and patients manage nutritional needs at home, ensuring that individuals receive proper nutrition even when they are not in a clinical setting.
Oncology and Autoimmune Diseases
In the context of cancer and autoimmune diseases, AI-driven nutrition management tools assist in designing specialized diets that support patients during their treatment journeys. These tools consider the unique nutritional requirements of patients with these conditions.
Nutrition Management Tools
There are multiple technological advances that have helped the planning, and management of nutrition. Presently even while entering nutrition data in the usual electronic record there are facilities for voice prompts, alarms and red flags placed on the screen which would ensure early provision of enteral nutrition. While feeding in data during missed delivery or unstuffiness delivery would automatically calculate the deficit in protein, calories and micronutrients.
Such systems would help in setting up of aggressive and optimum feeding protocols with the help of computer-generated algorithms which help in increasing the enteral intake and thus provision of feeding
Personal digital assistant (PDA)based clinical decision support system (CDSS), Nutria, for the management of artificial nutrition has been developed and used income intensive care units for nutrition delivery after cardiothoracic surgery. It has demonstrated improvement in caloric intake in the intensive care ununtrium is an interactive, multi user, graphical frontend, computer-aided nutrition calculation program written in JAVA (Oracle Inc, California USA). Use of such a software has helped in stricter adherence to established guidelines
One noteworthy AI-driven solution in the field of clinical nutrition is intimin which arguably appears to be a game changer in this segment. This innovative tool, co-created by the author of this article is currently deployed in 15 of India's top-tier hospitals and serves approximately 3000 patients daily. interion is a web application designed to empower clinical nutrition teams, including dietitians, physicians, nurses, and food and beverage professionals. It streamlines the nutrition management process, addressing malnutrition cases in hospitals while minimizing food wastage. This software-based nutrition management tool performs an array of tasks.
Automated Anthropometric Data Calculation: interion automates the calculation of ideal, actual, and adjusted body weight based on chosen BMI formulas. This eliminates the need for manual calculations and potential errors.
Nutritional Assessment and Screening Tools: The tool provides access to various assessment and screening tools, including Nitric Score, Nutritional Risk Screening (NRS), Subjective Global Assessment (SGS), and more. These tools aid in comprehensive patient evaluation.
Customized Nutritional Recommendations: intimin suggests macro-nutritional requirements based on guidelines from the European Society for Clinical Nutrition and Metabolism (ESPEN) and the American Society for Parenteral and Enteral Nutrition (ASPEN). It can also integrate readings from indirect calorimeters for precise calorie requirements.
Nutrition Delivery Management: The tool facilitates the management of nutrition delivery, including kitchen feed, enteral or parenteral nutrition, and additives. It monitors delivery and deficits, enabling healthcare professionals to track patient recovery due to improved nutrition.
The next frontier for similar software’s and the intimin is AI integration, which involves leveraging Large Language Models (LLMs) and semantic search. Integration of such software’s like the nutriment with search engines like AIDE/PubMed search etc., in the authors opinion, help to provide evidence-based insights to healthcare professionals with 100
Conclusion
Increasing availability of newer monitoring tools, re-defining of the nutritional standards based on individual needs, evaluation of organ functions with newer technology, more and more of available data on critical illness and a better co-ordination between various medical specialties will definitely help in optimizing the delivery of nutritional care. The specialized versions of AI tools tailored for dietitians are poised to revolutionize the field of clinical nutrition and dietetics. These AI-powered solutions empower Healthcare professionals including physicians and dietitians to provide evidence-based, personalized dietary guidance to their patients, enhance their education and training, optimize their practice, foster patient engagement, and contribute to cutting-edge research in the field of nutrition. As AI continues to evolve, it will play an increasingly vital role in elevating the standards of care in clinical nutrition and dietetics, ultimately leading to improved health and well-being for individuals and communities. intimin, in the authors opinion with its AI integration plans, promises to enhance the accuracy and efficiency of nutritional care delivery. As AI continues to evolve and adapt to the specific needs of healthcare, it has the potential to revolutionize clinical nutrition, ultimately leading to improved patient outcomes and a healthier future for all.
References
- Obermeyer, Z., & Emanuel, E. J. (2016). Predicting the future—big data, machine learning, and clinical medicine. New England Journal of Medicine, 375(13):1216-1219.
Publisher | Google Scholor - Esteva, A., Robicquet, A., Ramsundar, B., et al. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1):24-29.
Publisher | Google Scholor - Boushey, C. J., & Kerr, D. A. (2017). Wright, J.L., Lutes, K.D., Linnan, L., Preparing Registered Dietitian Nutritionists for leadership in digital health. Journal of the Academy of Nutrition and Dietetics, 117(10):1495-1498.
Publisher | Google Scholor - Zhang, H., & Gao, Y. (2019). Artificial intelligence in clinical laboratory diagnostics. Clinica Chimica Acta, 498:6-12.
Publisher | Google Scholor - Kawamoto, K., Houlihan, C. A., Balas, E. A., & Lobach, D. F. (2005). Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success. BMJ, 330(7494):765.
Publisher | Google Scholor - Sasheedharan, S. et al. suggestion based software called as “intimin” helps to screen out the patients which are at risk of malnutrition, formulate a plan, monitor and manage enteral nutrition of patients
Publisher | Google Scholor - Dugdale, D. C., & Wu, J. S. (2020). Artificial intelligence and machine learning in diabetes care. Journal of Diabetes Science and Technology, 14(1):15-19.
Publisher | Google Scholor