Exploration of critical care data by using unsupervised machine learning

Artificial intelligence and machine learning: Definition of terms and current concepts in critical care research

With increasing computing power, artificial intelligence (AI) and machine learning (ML) have prospered, which facilitate the analysis of large datasets, especially those found in critical care. It is important to define these terminologies, to inform a standardized approach to critical care research. This manuscript hopes to clarify these terms with examples from medical literature. Three major components that are required for a successful ML implementation: (i) reliable dataset, (ii) ML algorithm, and (iii) unbiased model evaluation, are discussed. A reliable dataset can be structured or unstructured with limited noise, outliers, and missing values. ML, a subset of AI, is typically focused on supervised or unsupervised learning tasks in which the output is based on inputs and derived from iterative pattern recognition algorithms, while AI is the overall ability of a machine to "think" or mimic human behavior; and to analyze data free from human influence. Even with successful implementation, advanced AI and ML algorithms have faced challenges in adoption into practice, mainly due to their lack of interpretability, which hinders trust, buy-in, and engagement from clinicians. Consequently, traditional algorithms, such as linear and logistic regression, that may have reduced predictive power but are highly interpretable, continue to be widely used.

Cluster analysis of thoracic muscle mass using artificial intelligence in severe pneumonia

Severe pneumonia results in high morbidity and mortality despite advanced treatments. This study investigates thoracic muscle mass from chest CT scans as a biomarker for predicting clinical outcomes in ICU patients with severe pneumonia. Analyzing electronic medical records and chest CT scans of 778 ICU patients with severe community-acquired pneumonia from January 2016 to December 2021, AI-enhanced 3D segmentation was used to assess thoracic muscle mass. Patients were categorized into clusters based on muscle mass profiles derived from CT scans, and their effects on clinical outcomes such as extubation success and in-hospital mortality were assessed. The study identified three clusters, showing that higher muscle mass (Cluster 1) correlated with lower in-hospital mortality (8% vs. 29% in Cluster 3) and improved clinical outcomes like extubation success. The model integrating muscle mass metrics outperformed conventional scores, with an AUC of 0.844 for predicting extubation success and 0.696 for predicting mortality. These findings highlight the strong predictive capacity of muscle mass evaluation over indices such as APACHE II and SOFA. Using AI to analyze thoracic muscle mass via chest CT provides a promising prognostic approach in severe pneumonia, advocating for its integration into clinical practice for better outcome predictions and personalized patient management.

Interventions to improve appropriateness of laboratory testing in the intensive care unit: a narrative review

Healthcare expenses are increasing, as is the utilization of laboratory resources. Despite this, between 20% and 40% of requested tests are deemed inappropriate. Improper use of laboratory resources leads to unwanted consequences such as hospital-acquired anemia, infections, increased costs, staff workload and patient stress and discomfort. The most unfavorable consequences result from unnecessary follow-up tests and treatments (overuse) and missed or delayed diagnoses (underuse). In this context, several interventions have been carried out to improve the appropriateness of laboratory testing. To date, there have been few published assessments of interventions specific to the intensive care unit. We reviewed the literature for interventions implemented in the ICU to improve the appropriateness of laboratory testing. We searched literature from 2008 to 2023 in PubMed, Embase, Scopus, and Google Scholar databases between April and June 2023. Five intervention categories were identified: education and guidance (E&G), audit and feedback, gatekeeping, computerized physician order entry (including reshaping of ordering panels), and multifaceted interventions (MFI). We included a sixth category exploring the potential role of artificial intelligence and machine learning (AI/ML)-based assisting tools in such interventions. E&G-based interventions and MFI are the most frequently used approaches. MFI is the most effective type of intervention, and shows the strongest persistence of effect over time. AI/ML-based tools may offer valuable assistance to the improvement of appropriate laboratory testing in the near future. Patient safety outcomes are not impaired by interventions to reduce inappropriate testing. The literature focuses mainly on reducing overuse of laboratory tests, with only one intervention mentioning underuse. We highlight an overall poor quality of methodological design and reporting and argue for standardization of intervention methods. Collaboration between clinicians and laboratory staff is key to improve appropriate laboratory utilization. This article offers practical guidance for optimizing the effectiveness of an intervention protocol designed to limit inappropriate use of laboratory resources.

Chinese experts' consensus on the application of intensive care big data

The development of intensive care medicine is inseparable from the diversified monitoring data. Intensive care medicine has been closely integrated with data since its birth. Critical care research requires an integrative approach that embraces the complexity of critical illness and the computational technology and algorithms that can make it possible. Considering the need of standardization of application of big data in intensive care, Intensive Care Medicine Branch of China Health Information and Health Care Big Data Society, Standard Committee has convened expert group, secretary group and the external audit expert group to formulate Chinese Experts' Consensus on the Application of Intensive Care Big Data (2022). This consensus makes 29 recommendations on the following five parts: Concept of intensive care big data, Important scientific issues, Standards and principles of database, Methodology in solving big data problems, Clinical application and safety consideration of intensive care big data. The consensus group believes this consensus is the starting step of application big data in the field of intensive care. More explorations and big data based retrospective research should be carried out in order to enhance safety and reliability of big data based models of critical care field.

A scoping review of the clinical application of machine learning in data-driven population segmentation analysis

OBJECTIVE

Data-driven population segmentation is commonly used in clinical settings to separate the heterogeneous population into multiple relatively homogenous groups with similar healthcare features. In recent years, machine learning (ML) based segmentation algorithms have garnered interest for their potential to speed up and improve algorithm development across many phenotypes and healthcare situations. This study evaluates ML-based segmentation with respect to (1) the populations applied, (2) the segmentation details, and (3) the outcome evaluations.

MATERIALS AND METHODS

MEDLINE, Embase, Web of Science, and Scopus were used following the PRISMA-ScR criteria. Peer-reviewed studies in the English language that used data-driven population segmentation analysis on structured data from January 2000 to October 2022 were included.

RESULTS

We identified 6077 articles and included 79 for the final analysis. Data-driven population segmentation analysis was employed in various clinical settings. K-means clustering is the most prevalent unsupervised ML paradigm. The most common settings were healthcare institutions. The most common targeted population was the general population.

DISCUSSION

Although all the studies did internal validation, only 11 papers (13.9%) did external validation, and 23 papers (29.1%) conducted methods comparison. The existing papers discussed little validating the robustness of ML modeling.

CONCLUSION

Existing ML applications on population segmentation need more evaluations regarding giving tailored, efficient integrated healthcare solutions compared to traditional segmentation analysis. Future ML applications in the field should emphasize methods' comparisons and external validation and investigate approaches to evaluate individual consistency using different methods.

[Recent research on machine learning in the diagnosis and treatment of necrotizing enterocolitis in neonates]

Necrotizing enterocolitis (NEC), with the main manifestations of bloody stool, abdominal distension, and vomiting, is one of the leading causes of death in neonates, and early identification and diagnosis are crucial for the prognosis of NEC. The emergence and development of machine learning has provided the potential for early, rapid, and accurate identification of this disease. This article summarizes the algorithms of machine learning recently used in NEC, analyzes the high-risk predictive factors revealed by these algorithms, evaluates the ability and characteristics of machine learning in the etiology, definition, and diagnosis of NEC, and discusses the challenges and prospects for the future application of machine learning in NEC.

Novel architecture for gated recurrent unit autoencoder trained on time series from electronic health records enables detection of ICU patient subgroups

Electronic health records (EHRs) are used in hospitals to store diagnoses, clinician notes, examinations, lab results, and interventions for each patient. Grouping patients into distinct subsets, for example, via clustering, may enable the discovery of unknown disease patterns or comorbidities, which could eventually lead to better treatment through personalized medicine. Patient data derived from EHRs is heterogeneous and temporally irregular. Therefore, traditional machine learning methods like PCA are ill-suited for analysis of EHR-derived patient data. We propose to address these issues with a new methodology based on training a gated recurrent unit (GRU) autoencoder directly on health record data. Our method learns a low-dimensional feature space by training on patient data time series, where the time of each data point is expressed explicitly. We use positional encodings for time, allowing our model to better handle the temporal irregularity of the data. We apply our method to data from the Medical Information Mart for Intensive Care (MIMIC-III). Using our data-derived feature space, we can cluster patients into groups representing major classes of disease patterns. Additionally, we show that our feature space exhibits a rich substructure at multiple scales.

Has the Flood Entered the Basement? A Systematic Literature Review about Machine Learning in Laboratory Medicine

This article presents a systematic literature review that expands and updates a previous review on the application of machine learning to laboratory medicine. We used Scopus and PubMed to collect, select and analyse the papers published from 2017 to the present in order to highlight the main studies that have applied machine learning techniques to haematochemical parameters and to review their diagnostic and prognostic performance. In doing so, we aim to address the question we asked three years ago about the potential of these techniques in laboratory medicine and the need to leverage a tool that was still under-utilised at that time.

Multilevel clustering approach driven by continuous glucose monitoring data for further classification of type 2 diabetes

INTRODUCTION

Mining knowledge from continuous glucose monitoring (CGM) data to classify highly heterogeneous patients with type 2 diabetes according to their characteristics remains unaddressed. A refined clustering method that retrieves hidden information from CGM data could provide a viable method to identify patients with different degrees of dysglycemia and clinical phenotypes.

RESEARCH DESIGN AND METHODS

From Shanghai Jiao Tong University Affiliated Sixth People's Hospital, we selected 908 patients with type 2 diabetes (18-83 years) who wore blinded CGM sensors (iPro2, Medtronic, California, USA). Participants were clustered based on CGM data during a 24-hour period by our method. The first level extracted the knowledge-based and statistics-based features to describe CGM signals from multiple perspectives. The Fisher score and variables cluster analysis were applied to fuse features into low dimensions at the second level. The third level divided subjects into subgroups with different clinical phenotypes. The four subgroups of patients were determined by clinical phenotypes.

RESULTS

Four subgroups of patients with type 2 diabetes with significantly different statistical features and clinical phenotypes were identified by our method. In particular, individuals in cluster 1 were characterized by the lowest glucose level factor and glucose fluctuation factor, and the highest negative glucose factor and C peptide index. By contrast, cluster 2 had the highest glucose level factor and the lowest C peptide index. Cluster 4 was characterized by the greatest degree of glucose fluctuation factor, was the most insulin-sensitive, and had the lowest insulin resistance. Cluster 3 ranked in the middle concerning the CGM-derived metrics and clinical phenotypes compared with those of the other three groups.

CONCLUSION

A novel multilevel clustering approach for knowledge mining from CGM data in type 2 diabetes is presented. The results demonstrate that subgroups are adequately distinguished with notable statistical and clinical differences.