Artificial Intelligence (AI) and Malnutrition: Transforming Nutritional Care

Malnutrition is a growing global health concern, especially among older adults. Currently, 1 in 10 people is over 65, and this number is expected to rise to 1 in 6 by 2050 (WHO). Despite advancements in healthcare, malnutrition remains prevalent in nursing homes, hospitals, and acute care units, even in developed countries. Traditional nutritional assessments rely on analog questionnaires and consensus guidelines, limiting early detection and intervention.

AI has emerged as a powerful tool in healthcare, offering advanced detection, diagnosis, and management of diseases, including malnutrition. Through image-based analysis, predictive data processing, and continuous monitoring, AI can revolutionize nutritional assessments and improve patient outcomes.

AI in Malnutrition Detection and Assessment

AI-powered technologies enhance early identification of malnutrition by leveraging diverse health indicators, including:

1. Image-Based Diagnosis

AI-driven imaging can detect physical signs of malnutrition, such as muscle wasting and facial indicators of deficiencies. Machine learning (ML) models analyze body composition, X-rays, and facial images to identify signs of sarcopenia (age-related muscle loss) and nutrient deficiencies.

2. Growth Metrics and Body Measurements

AI can analyze weight, height, BMI, and mid-upper arm circumference (MUAC) to assess malnutrition risk. Computer vision algorithms can measure body composition from photographs or video footage, reducing reliance on manual measurements and minimizing errors.

3. Nutritional Data Processing and Predictive Analytics

AI can process dietary intake data and correlate it with health outcomes to predict malnutrition risk. By analyzing:

• Caloric and nutrient intake
• Meal frequency and portion sizes
• Dietary patterns over time
• Biomarkers from blood tests

AI can detect trends and risk factors before malnutrition becomes severe. Smart diet tracking apps powered by AI can estimate nutritional content from meal photos, offering real-time feedback to users.

4. AI-Powered Dietary Assessment and Monitoring

AI-enhanced tools use:

• Acoustic analysis – Monitoring chewing sounds to assess food intake.
• Jaw motion tracking – Evaluating bite patterns.
• Visual image processing – Detecting eating and swallowing efficiency.

These technologies identify changes in eating behavior that may signal nutritional deficiencies, especially in elderly patients.

AI in Malnutrition Prevention and Management

Beyond detection, AI facilitates personalized nutrition plans and automated meal management to prevent and treat malnutrition.

1. AI-Driven Personalized Nutrition

AI considers genetic factors, metabolism, lifestyle, and dietary preferences to create customized meal plans. Virtual dietitians use AI to provide real-time meal recommendations tailored to:

• Current nutritional status
• Macronutrient and micronutrient needs
• Medical conditions (e.g., diabetes, heart disease)
• Dietary restrictions

This personalization improves dietary adherence and reduces malnutrition risks.

2. AI in Meal Planning for Elderly Care

In hospitals and nursing homes, AI optimizes meal planning by:

• Tracking patient food intake
• Adjusting portion sizes based on health needs
• Detecting inadequate eating behavior
• Ensuring balanced nutrition in daily meals

This helps caregivers provide targeted nutritional support to vulnerable individuals.

3. AI for Continuous Monitoring and Early Intervention

Wearable devices and smart sensors track:

• Heart rate, blood glucose, and blood pressure
• Physical activity levels
• Appetite and eating habits

AI can analyze this data in real-time, alerting caregivers or healthcare providers if a patient is at risk of malnutrition.

Challenges and Future Directions

Despite its potential, AI-driven malnutrition assessment faces challenges:

• Data Privacy & Security – Sensitive health data must be protected.
• Algorithm Bias & Accuracy – AI models must be trained on diverse datasets.
• Integration into Healthcare Systems – AI tools must be aligned with electronic health records (EHRs).
• Accessibility & Cost – AI-based nutritional assessments should be affordable and widely available.

Future advancements will require collaboration between AI researchers, nutritionists, and healthcare professionals to refine algorithms and improve patient outcomes.

Conclusion

AI is transforming malnutrition detection and management through advanced imaging, predictive analytics, and personalized nutrition strategies. By integrating AI-powered tools into healthcare, early malnutrition detection, real-time monitoring, and tailored dietary interventions become possible.

As AI continues to evolve, it has the potential to revolutionize nutritional care, particularly for the elderly, ensuring better health, improved quality of life, and reduced malnutrition-related complications.

https://www.sciencedirect.com/science/article/abs/pii/S2405457723011865