Can AI detect malnutrition in hospitals?

Jan 12, 2022 1:59pm

 Happy new year! I hope you've had a good rest and time to reflect on how you'll make an impact this year. We have our plans mapped out, and are excited to kick off the year with some very interesting projects and our first newsletter.
 
This week’s newsletter: The latest research, plenty of tech news and MHRA guidance on using real world evidence.

Stay safe and make every day count!
Mariette

 

Research update

A Systematic Review and Recommendations Around Frameworks for Evaluating Scientific Validity in Nutritional Genomics

This review, which analyzed 41 frameworks, aimed to examine the scientific validity of nutrigenetic research. The results show factors considered important for the evaluating of nutrigenetic evidence are: design and quality, generalizability, directness, consistency, precision, confounding, effect size, biological plausibility, publication/funding bias, allele, and nutrient dose-response, and summary levels of evidence. Also, "consideration of biological plausibility was more common in frameworks used in genetics [and] dose-response effects were rarely considered".

 

Loss of sucrase-isomaltase function increases acetate levels and improves metabolic health in Greenlandic cohorts

The sucrase-isomaltase (SI) c.273_274delAG loss-of-function variant is common in Arctic populations. This study aimed to describe the health of adults with a sucrase-isomaltase deficiency in two cohorts of Greenlandic adults (N=4,922 and N=1,629). The results show: "homozygous carriers of the variant had a markedly healthier metabolic profile than the remaining population, including lower BMI (β (SE), body weight, fat percentage, fasting triglyceride, and remnant cholesterol". They also had higher circulating levels of acetate. "These results suggest that sucrase-isomaltase constitutes a promising drug target for improvement of metabolic health and that the health benefits are mediated by reduced dietary sucrose uptake and possibly also by higher levels of circulating acetate". 

 

“The current study aimed to gain causal insight to the role that taste plays in coffee drinking behavior. Genetically inferred caffeine and bitter taste perception contributed to coffee drinking behavior but, contrary to our hypothesis, to a weaker extent than genetically inferred caffeine sensitivity. Specifically, a greater preference for caffeine inferred by genetic differences in the physiological effects of caffeine leads to a stronger preference for the taste/smell of coffee inferred by liking-scales and reported intake. Similar findings were reported for tea but also dark chocolate”.

 

Technology News

Gousto goes for the gold, rakes in $150 million at valuation pushing $2 billion

The London-based startup, Gousto provides consumers with a steady stream of over 60 various recipe box kits delivered fresh to their doorstep. Now they have announced new funds ($150 million), that will be used to push forward with the launch of an automated and AI-driven fulfillment centre near Birmingham.
 

HealthLeap raises $1,1M pre-seed to reduce malnutrition in hospitals with clinical AI Assistant

HealthLeap is a South African startup that operates in the US intending to prevent and treat malnutrition in hospitals. Malnutrition in hospitals is associated with 3-5x mortality during a hospital stay. It affects 30-50% of patients, but only 5% are diagnosed. With this in mind, HealthLeap created an AI-based clinical assistant product: NutriLeap. This tool will help hospital dietitians (and soon other healthcare providers) with automated clinical calculations and research-backed suggestions. With this, they can determine precise, personalized nutritional needs significantly faster for patients.
 

Ness. The card that keeps you healthy

Ness is a credit card that helps people get healthier. By earning points for healthy purchases, the card gives customers access to exclusive perks to complement their lifestyle. For example, the perks can include training sessions, wearables, or supplements.

Replacing meat with alternative plant-based products (RE-MAP): a randomized controlled trial of a multicomponent behavioral intervention to reduce meat consumption

This study aimed to implement a behavioral intervention to reduce meat consumption. The intervention comprised free meat substitutes, information about the benefits of eating less meat, success stories, and recipes. After the intervention, the sample of 115 participants, measured the consumption of meat substitutes, cardiovascular risk factors, psychosocial variables related to meat consumption, and the nutritional composition of the diet. The results show: "(...) Relative to the control, the intervention reduced meat consumption at 4 weeks by 63 g/d and at eight weeks by 39 g/d. The intervention significantly increased the consumption of meat substitutes without changing the intake of other principal food groups. The intervention increased intentions, positive attitudes, perceived control, and subjective norms of eating a low meat diet and using meat substitutes, and decreased attachment to meat".

 

Thorne HealthTech's First-of-Its-Kind 'Wellth Report' Reveals Shifts in Individuals' Health Behaviors with Ripple Effects for the Healthcare Industry and Broader Workforce

Thorne HealthTech has released findings from their national longitudinal study, the 2021 Wellth Report, which explores how the health and wellness priorities of consumers have shifted during COVID-19. Some highlights:

- "More than half (67%) of survey respondents revealed they continue to experience the negative impacts of COVID-19 on their personal health and wellness over the past year and a half;

- 89% of respondents tried to improve at least one area of their health in the past 12 months, the momentum that continues when they set future health goals;

- 55% of adults rate their sleep quality as fair or poor and 38% rated their mental health as fair or poor, and these numbers are higher for women, younger individuals, and those in lower income brackets".
 
 

Resources:

 

MHRA guidance on the use of real-world data in clinical studies to support regulatory decisions

This document provides an introduction to the MHRA’s real-world data (RWD) guideline series and points to consider when evaluating whether a RWD source is of sufficient quality for the intended use.

RWD is defined as data relating to patient health status or delivery of health care collected outside of a clinical study. Sources of RWD include electronic healthcare records (EHR) defined as structured, digital collections of patient-level medical data, primary and secondary care records, disease registries, and administrative data on births and deaths. Other sources of RWD include patient-reported outcomes (PRO) data and data which is collected outside of a clinical study setting such as through wearable devices, specialized/secure websites, or tablets.