Development of Medical Imaging Data Standardization for Imaging-Based Observational Research: OMOP Common Data Model Extension

The rapid growth of artificial intelligence (AI) and deep learning techniques require access to large inter-institutional cohorts of data to enable the development of robust models, e.g., targeting the identification of disease biomarkers and quantifying disease progression and treatment efficacy. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) has been designed to accommodate a harmonized representation of observational healthcare data. This study proposes the Medical Imaging CDM (MI-CDM) extension, adding two new tables and two vocabularies to the OMOP CDM to address the structural and semantic requirements to support imaging research. The tables provide the capabilities of linking DICOM data sources as well as tracking the provenance of imaging features derived from those images. The implementation of the extension enables phenotype definitions using imaging features and expanding standardized computable imaging biomarkers. This proposal offers a comprehensive and unified approach for conducting imaging research and outcome studies utilizing imaging features.

Integrated multimodal artificial intelligence framework for healthcare applications

Artificial intelligence (AI) systems hold great promise to improve healthcare over the next decades. Specifically, AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of applications. In this work, we propose and evaluate a unified Holistic AI in Medicine (HAIM) framework to facilitate the generation and testing of AI systems that leverage multimodal inputs. Our approach uses generalizable data pre-processing and machine learning modeling stages that can be readily adapted for research and deployment in healthcare environments. We evaluate our HAIM framework by training and characterizing 14,324 independent models based on HAIM-MIMIC-MM, a multimodal clinical database (N = 34,537 samples) containing 7279 unique hospitalizations and 6485 patients, spanning all possible input combinations of 4 data modalities (i.e., tabular, time-series, text, and images), 11 unique data sources and 12 predictive tasks. We show that this framework can consistently and robustly produce models that outperform similar single-source approaches across various healthcare demonstrations (by 6–33%), including 10 distinct chest pathology diagnoses, along with length-of-stay and 48 h mortality predictions. We also quantify the contribution of each modality and data source using Shapley values, which demonstrates the heterogeneity in data modality importance and the necessity of multimodal inputs across different healthcare-relevant tasks. The generalizable properties and flexibility of our Holistic AI in Medicine (HAIM) framework could offer a promising pathway for future multimodal predictive systems in clinical and operational healthcare settings.

Sensitivity of comorbidity network analysis

OBJECTIVES

Comorbidity network analysis (CNA) is a graph-theoretic approach to systems medicine based on associations revealed from disease co-occurrence data. Researchers have used CNA to explore epidemiological patterns, differentiate populations, characterize disorders, and more; but these techniques have not been comprehensively evaluated. Our objectives were to assess the stability of common CNA techniques.

MATERIALS AND METHODS

We obtained seven co-occurrence data sets, most from previous CNAs, coded using several ontologies. We constructed comorbidity networks under various modeling procedures and calculated summary statistics and centrality rankings. We used regression, ordination, and rank correlation to assess these properties' sensitivity to the source of data and construction parameters.

RESULTS

Most summary statistics were robust to variation in link determination but somewhere sensitive to the association measure. Some more effectively than others discriminated among networks constructed from different data sets. Centrality rankings, especially among hubs, were somewhat sensitive to link determination and highly sensitive to ontology. As multivariate models incorporated additional effects, comorbid associations among low-prevalence disorders weakened while those between high-prevalence disorders shifted negative.

DISCUSSION

Pairwise CNA techniques are generally robust, but some analyses are highly sensitive to certain parameters. Multivariate approaches expose additional conceptual and technical limitations to the usual pairwise approach.

CONCLUSION

We conclude with a set of recommendations we believe will help CNA researchers improve the robustness of results and the potential of follow-up research.

Systems Biology, Systems Medicine, Systems Pharmacology: The What and The Why

Systems biology is today such a widespread discipline that it becomes difficult to propose a clear definition of what it really is. For some, it remains restricted to the genomic field. For many, it designates the integrated approach or the corpus of computational methods employed to handle the vast amount of biological or medical data and investigate the complexity of the living. Although defining systems biology might be difficult, on the other hand its purpose is clear: systems biology, with its emerging subfields systems medicine and systems pharmacology, clearly aims at making sense of complex observations/experimental and clinical datasets to improve our understanding of diseases and their treatments without putting aside the context in which they appear and develop. In this short review, we aim to specifically focus on these new subfields with the new theoretical tools and approaches that were developed in the context of cancer. Systems pharmacology and medicine now give hope for major improvements in cancer therapy, making personalized medicine closer to reality. As we will see, the current challenge is to be able to improve the clinical practice according to the paradigm shift of systems sciences.

Applications of network analysis to routinely collected health care data: a systematic review

Objective

To survey network analyses of datasets collected in the course of routine operations in health care settings and identify driving questions, methods, needs, and potential for future research.

Materials and Methods

A search strategy was designed to find studies that applied network analysis to routinely collected health care datasets and was adapted to 3 bibliographic databases. The results were grouped according to a thematic analysis of their settings, objectives, data, and methods. Each group received a methodological synthesis.

Results

The search found 189 distinct studies reported before August 2016. We manually partitioned the sample into 4 groups, which investigated institutional exchange, physician collaboration, clinical co-occurrence, and workplace interaction networks. Several robust and ongoing research programs were discerned within (and sometimes across) the groups. Little interaction was observed between these programs, despite conceptual and methodological similarities.

Discussion

We use the literature sample to inform a discussion of good practice at this methodological interface, including the concordance of motivations, study design, data, and tools and the validation and standardization of techniques. We then highlight instances of positive feedback between methodological development and knowledge domains and assess the overall cohesion of the sample.

A Machine Learning-based Method for Question Type Classification in Biomedical Question Answering

Background and Objective: Biomedical question type classification is one of the important components of an automatic biomedical question answering system. The performance of the latter depends directly on the performance of its biomedical question type classification system, which consists of assigning a category to each question in order to determine the appropriate answer extraction algorithm. This study aims to automatically classify biomedical questions into one of the four categories: (1) yes/no, (2) factoid, (3) list, and (4) summary.

Methods: In this paper, we propose a biomedical question type classification method based on machine learning approaches to automatically assign a category to a biomedical question. First, we extract features from biomedical questions using the proposed handcrafted lexico-syntactic patterns. Then, we feed these features for machine- learning algorithms. Finally, the class label is predicted using the trained classifiers.

Results: Experimental evaluations performed on large standard annotated datasets of biomedical questions, provided by the BioASQ challenge, demonstrated that our method exhibits significant improved performance when compared to four baseline systems. The proposed method achieves a roughly 10-point increase over the best baseline in terms of accuracy. Moreover, the obtained results show that using handcrafted lexico-syntactic patterns as features’ provider of support vector machine (SVM) lead to the highest accuracy of 89.40%.

Conclusion: The proposed method can automatically classify BioASQ questions into one of the four categories: yes/no, factoid, list, and summary. Furthermore, the results demonstrated that our method produced the best classification performance compared to four baseline systems.

Applying systems biology to biomedical research and health care: a précising definition of systems medicine

BACKGROUND

Systems medicine has become a key word in biomedical research. Although it is often referred to as P4-(predictive, preventive, personalized and participatory)-medicine, it still lacks a clear definition and is open to interpretation. This conceptual lack of clarity complicates the scientific and public discourse on chances, risks and limits of Systems Medicine and may lead to unfounded hopes. Against this background, our goal was to develop a sufficiently precise and widely acceptable definition of Systems Medicine.

METHODS

In a first step, PubMed was searched using the keyword "systems medicine". A data extraction tabloid was developed putting forward a means/ends-division. Full-texts of articles containing Systems Medicine in title or abstract were screened for definitions. Definitions were extracted; their semantic elements were assigned as either means or ends. To reduce complexity of the resulting list, summary categories were developed inductively. In a second step, we applied six criteria for adequate definitions (necessity, non-circularity, non-redundancy, consistency, non-vagueness, and coherence) to these categories to derive a so-called précising definition of Systems Medicine.

RESULTS

We identified 185 articles containing the term Systems Medicine in title or abstract. 67 contained at least one definition of Systems Medicine. In 98 definitions, we found 114 means and 132 ends. From these we derived the précising definition: Systems Medicine is an approach seeking to improve medical research (i.e. the understanding of complex processes occurring in diseases, pathologies and health states as well as innovative approaches to drug discovery) and health care (i.e. prevention, prediction, diagnosis and treatment) through stratification by means of Systems Biology (i.e. data integration, modeling, experimentation and bioinformatics). Our study also revealed the visionary character of Systems Medicine.

CONCLUSIONS

Our insights, on the one hand, allow for a realistic identification of actual ethical as well as legal issues arising in the context of Systems Medicine and, in consequence, for a realistic debate of questions concerning its matter and (future) handling. On the other hand, they help avoiding unfounded hopes and unrealistic expectations. This especially holds for goals like improving patient participation which are intensely debated in the context of Systems Medicine, however not implied in the concept.

Interactions Between Genetics, Lifestyle, and Environmental Factors for Healthcare

The occurrence and progression of diseases are strongly associated with a combination of genetic, lifestyle, and environmental factors. Understanding the interplay between genetic and nongenetic components provides deep insights into disease pathogenesis and promotes personalized strategies for people healthcare. Recently, the paradigm of systems medicine, which integrates biomedical data and knowledge at multidimensional levels, is considered to be an optimal way for disease management and clinical decision-making in the era of precision medicine. In this chapter, epigenetic-mediated genetics-lifestyle-environment interactions within specific diseases and different ethnic groups are systematically discussed, and data sources, computational models, and translational platforms for systems medicine research are sequentially presented. Moreover, feasible suggestions on precision healthcare and healthy longevity are kindly proposed based on the comprehensive review of current studies.