Development and validation of machine learning-based clinical decision support tool for identifying malnutrition in NICU patients

Computational Approaches for Predicting Preterm Birth and Newborn Outcomes

Preterm birth (PTB) and its associated morbidities are a leading cause of infant mortality and morbidity. Accurate predictive models and a better biological understanding of PTB-associated morbidities are critical in reducing their adverse effects. Increasing availability of multimodal high-dimensional data sets with concurrent advances in artificial intelligence (AI) have created a rich opportunity to gain novel insights into PTB, a clinically complex and multifactorial disease. Here, the authors review the use of AI to analyze 3 modes of data: electronic health records, biological omics, and social determinants of health metrics.

The potential of machine learning models to identify malnutrition diagnosed by GLIM combined with NRS-2002 in colorectal cancer patients without weight loss information

BACKGROUND & AIMS

The key step of the Global Leadership Initiative on Malnutrition (GLIM) is nutritional risk screening, while the most appropriate screening tool for colorectal cancer (CRC) patients is yet unknown. The GLIM diagnosis relies on weight loss information, and bias or even failure to recall patients' historical weight can cause misestimates of malnutrition. We aimed to compare the suitability of several screening tools in GLIM diagnosis, and establish machine learning (ML) models to predict malnutrition in CRC patients without weight loss information.

METHODS

This multicenter cohort study enrolled 4487 CRC patients. The capability of GLIM diagnoses combined with four screening tools in predicting survival probability was compared by Kaplan-Meier curves, and the most accurate one was selected as the malnutrition reference standard. Participants were randomly assigned to a training cohort (n = 3365) and a validation cohort (n = 1122). Several ML approaches were adopted to establish models for predicting malnutrition without weight loss data. We estimated feature importance and reserved the top 30% of variables for retraining simplified models. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to assess and compare model performance.

RESULTS

NRS-2002 was the most suitable screening tool for GLIM diagnosis in CRC patients, with the highest hazard ratio (1.59; 95% CI, 1.43-1.77). A total of 2076 (46.3%) patients were malnourished diagnosed by GLIM combined with NRS-2002. The simplified random forest (RF) model outperformed other models with an AUC of 0.830 (95% CI, 0.805-0.854), and accuracy, sensitivity and specificity were 0.775, 0.835 and 0.742, respectively. We deployed an online application based on the simplified RF model to accurately estimate malnutrition probability in CRC patients without weight loss information (https://zzuwtt1998.shinyapps.io/dynnomapp/).

CONCLUSIONS

Nutrition Risk Screening 2002 was the optimal initial nutritional risk screening tool in the GLIM process. The RF model outperformed other models, and an online prediction tool was developed to properly identify patients at high risk of malnutrition.

The use of machine learning in paediatric nutrition

PURPOSE OF REVIEW

In recent years, there has been a burgeoning interest in using machine learning methods. This has been accompanied by an expansion in the availability and ease of use of machine learning tools and an increase in the number of large, complex datasets which are suited to machine learning approaches. This review summarizes recent work in the field and sets expectations for its impact in the future.

RECENT FINDINGS

Much work has focused on establishing good practices and ethical frameworks to guide the use of machine learning in research. Machine learning has an established role in identifying features in 'omics' research and is emerging as a tool to generate predictive models to identify people at risk of disease and patients at risk of complications. They have been used to identify risks for malnutrition and obesity. Machine learning techniques have also been used to develop smartphone apps to track behaviour and provide healthcare advice.

SUMMARY

Machine learning techniques are reaching maturity and their impact on observational data analysis and behaviour change will come to fruition in the next 5 years. A set of standards and best practices are emerging and should be implemented by researchers and publishers.

A clinical informatics approach to bronchopulmonary dysplasia: current barriers and future possibilities

Bronchopulmonary dysplasia (BPD) is a complex, multifactorial lung disease affecting preterm neonates that can result in long-term pulmonary and non-pulmonary complications. Current therapies mainly focus on symptom management after the development of BPD, indicating a need for innovative approaches to predict and identify neonates who would benefit most from targeted or earlier interventions. Clinical informatics, a subfield of biomedical informatics, is transforming healthcare by integrating computational methods with patient data to improve patient outcomes. The application of clinical informatics to develop and enhance clinical therapies for BPD presents opportunities by leveraging electronic health record data, applying machine learning algorithms, and implementing clinical decision support systems. This review highlights the current barriers and the future potential of clinical informatics in identifying clinically relevant BPD phenotypes and developing clinical decision support tools to improve the management of extremely preterm neonates developing or with established BPD. However, the full potential of clinical informatics in advancing our understanding of BPD with the goal of improving patient outcomes cannot be achieved unless we address current challenges such as data collection, storage, privacy, and inherent data bias.