Deep phenotyping for precision medicine

From molecular mechanisms of prostate cancer to translational applications: based on multi-omics fusion analysis and intelligent medicine

Prostate cancer is the most common cancer in men worldwide and has a high mortality rate. The complex and heterogeneous development of prostate cancer has become a core obstacle in the treatment of prostate cancer. Simultaneously, the issues of overtreatment in early-stage diagnosis, oligometastasis and dormant tumor recognition, as well as personalized drug utilization, are also specific concerns that require attention in the clinical management of prostate cancer. Some typical genetic mutations have been proved to be associated with prostate cancer's initiation and progression. However, single-omic studies usually are not able to explain the causal relationship between molecular alterations and clinical phenotypes. Exploration from a systems genetics perspective is also lacking in this field, that is, the impact of gene network, the environmental factors, and even lifestyle behaviors on disease progression. At the meantime, current trend emphasizes the utilization of artificial intelligence (AI) and machine learning techniques to process extensive multidimensional data, including multi-omics. These technologies unveil the potential patterns, correlations, and insights related to diseases, thereby aiding the interpretable clinical decision making and applications, namely intelligent medicine. Therefore, there is a pressing need to integrate multidimensional data for identification of molecular subtypes, prediction of cancer progression and aggressiveness, along with perosonalized treatment performing. In this review, we systematically elaborated the landscape from molecular mechanism discovery of prostate cancer to clinical translational applications. We discussed the molecular profiles and clinical manifestations of prostate cancer heterogeneity, the identification of different states of prostate cancer, as well as corresponding precision medicine practices. Taking multi-omics fusion, systems genetics, and intelligence medicine as the main perspectives, the current research results and knowledge-driven research path of prostate cancer were summarized.

First copy number variant in trans with single nucleotide variant in CCN6 causing progressive pseudorheumatoid dysplasia revealed by genome sequencing and deep phenotyping in monozygotic twins

Biallelic pathogenic variants in CCN6 cause progressive pseudorheumatoid dysplasia (PPD), a rare skeletal dysplasia. The predominant features include noninflammatory progressive joint stiffness and enlargement, which are not unique to this condition. Nearly 100% of the reported variants are single nucleotide variants or small indels, and missing of a second variant has been reported. Genome sequencing (GS) covers various types of variants and deep phenotyping (DP) provides detailed and precise information facilitating genetic data interpretation. The combination of GS and DP improves diagnostic yield, especially in rare and undiagnosed diseases. We identified a novel compound heterozygote involving a disease-causing copy number variant (g.112057664_112064205del) in trans with a single nucleotide variant (c.624dup(p.Cys209MetfsTer21)) in CCN6 in a pair of monozygotic twins, through the methods of GS and DP. The twins had received three nondiagnostic results before. The g.112057664_112064205del variant was missed by all the tests, and the recorded phenotypes were inaccurate or even misleading. The twins were diagnosed with PPD, ending a 13-year diagnostic odyssey. There may be other patients with PPD experiencing underdiagnosis and misdiagnosis due to inadequate genetic testing or phenotyping methods. This case highlights the critical role of GS and DP in facilitating an accurate and timely diagnosis.

Precision phenotyping from routine laboratory parameters for out of hospital survival prediction in an all comers prospective PCI registry

Out-of-hospital mortality in coronary artery disease (CAD) is particularly high and established adverse event prediction tools are yet to be available. Our study aimed to investigate whether precision phenotyping can be performed using routine laboratory parameters for the prediction of out-of-hospital survival in a CAD population treated by percutaneous coronary intervention (PCI). All patients treated by PCI and discharged alive in a tertiary center between January 2016 - December 2022 that have been included prospectively in the local registry were analyzed. 115 parameters from the PCI registry and 266 parameters derived from routine laboratory testing were used. An extreme gradient-boosted decision tree machine learning (ML) algorithm was trained and used to predict all-cause and cardiovascular-cause survival. A total of 4027 patients with 4981 PCI hospitalizations were randomly included in the 70% training dataset and 1729 patients with 2160 PCI hospitalizations were randomly included in the 30% validation dataset. All-cause and cardiovascular cause mortality was 17.5% and 12.2%. The integrated area under the receiver operator characteristic curve for prediction of all-cause and cardiovascular cause mortality by the ML on the validation dataset was 0.844 and 0.837, respectively (all p < 0.001). Parameters reflecting renal function (first and maximum serum creatinine), hematologic function (mean corpuscular hemoglobin concentration, platelet distribution width), and inflammatory status (lymphocyte per monocyte ratio) were among the most important predictors. Accurate out-of-hospital survival prediction in CAD can be achieved using routine laboratory parameters. ML outperformed clinical risk scores in predicting out-of-hospital mortality in a prospective all-comers PCI population and has the potential to precisely phenotype patients.

Integrating deep phenotyping with genetic analysis: a comprehensive workflow for diagnosis and management of rare bone diseases

Phenotypes play a fundamental role in medical genetics, serving as external manifestations of underlying genotypes. Deep phenotyping, a cornerstone of precision medicine, involves precise multi-system phenotype assessments, facilitating disease subtyping and genetic understanding. Despite their significance, the field lacks standardized protocols for accurate phenotype evaluation, hindering clinical comprehension and research comparability. We present a comprehensive workflow of deep phenotyping for rare bone diseases from the Genetics Clinic of Skeletal Deformity at Peking Union Medical College Hospital. Our workflow integrates referral, informed consent, and detailed phenotype evaluation through HPO standards, capturing nuanced phenotypic characteristics using clinical examinations, questionnaires, and multimedia documentation. Genetic testing and counseling follow, based on deep phenotyping results, ensuring personalized interventions. Multidisciplinary team consultations facilitate comprehensive patient care and clinical guideline development. Regular follow-up visits emphasize dynamic phenotype reassessment, ensuring treatment strategies remain responsive to evolving patient needs. In conclusion, this study highlights the importance of deep phenotyping in rare bone diseases, offering a standardized framework for phenotype evaluation, genetic analysis, and multidisciplinary intervention. By enhancing clinical care and research outcomes, this approach contributes to the advancement of precision medicine in the field of medical genetics.

Phenotyping variability in early socio-communicative skills in young children with autism and its influence on later development

Children with autism spectrum disorder (ASD) often face challenges in early social communication skills, prompting the need for a detailed exploration of specific behaviors and their impact on cognitive and adaptive functioning. This study aims to address this gap by examining the developmental trajectories of early social communication skills in preschoolers with ASD aged 18-60 months, comparing them to age-matched typically developing (TD) children. Utilizing the early social communication scales (ESCS), the research employs a longitudinal design to capture changes over time. We apply a principal component analysis (PCA) to ESCS variables to identify underlying components, and cluster analysis to identify subgroups based on preverbal communication profiles. The results reveal consistent differences in early social communication skills between ASD and TD children, with ASD children exhibiting reduced skills. PCA identifies two components, distinguishing objects-directed behaviors and social interaction-directed behaviors. Cluster analysis identifies three subgroups of autistic children, each displaying specific communication profiles associated with distinct cognitive and adaptive functioning trajectories. In conclusion, this study provides a nuanced understanding of early social communication development in ASD, emphasizing the importance of low-level behaviors. The identification of subgroups and their unique trajectories contributes to a more comprehensive understanding of ASD heterogeneity. These findings underscore the significance of early diagnosis, focusing on specific behaviors predicting cognitive and adaptive functioning outcomes. The study encourages further research to explore the sequential development of these skills, offering valuable insights for interventions and support strategies.

Considerations on the basis of medical reasoning for the use in AI applications

This study discusses the integration of artificial intelligence (AI) and machine learning (ML) in medical reasoning and decision-making, with a focus on the challenges and opportunities associated with the massive consumption of data required for training AI systems, and contrasts this with the limited data typically available to medical practitioners. We advocate for a balanced approach that includes small data and emphasize the importance of maintaining the art of clinical reasoning amid technological advancements. Finally, we highlight the potential of multidisciplinary research in addressing the complexities of medical reasoning and suggest the necessity of careful abstraction and conceptual modeling in AI applications.

Using Data-Driven Algorithms with Large-Scale Plasma Proteomic Data to Discover Novel Biomarkers for Diagnosing Depression

Given recent technological advances in proteomics, it is now possible to quantify plasma proteomes in large cohorts of patients to screen for biomarkers and to guide the early diagnosis and treatment of depression. Here we used CatBoost machine learning to model and discover biomarkers of depression in UK Biobank data sets (depression n = 4,479, healthy control n = 19,821). CatBoost was employed for model construction, with Shapley Additive Explanations (SHAP) being utilized to interpret the resulting model. Model performance was corroborated through 5-fold cross-validation, and its diagnostic efficacy was evaluated based on the area under the receiver operating characteristic (AUC) curve. A total of 45 depression-related proteins were screened based on the top 20 important features output by the CatBoost model in six data sets. Of the nine diagnostic models for depression, the performance of the traditional risk factor model was improved after the addition of proteomic data, with the best model having an average AUC of 0.764 in the test sets. KEGG pathway analysis of 45 screened proteins showed that the most significant pathway involved was the cytokine-cytokine receptor interaction. It is feasible to explore diagnostic biomarkers of depression using data-driven machine learning methods and large-scale data sets, although the results require validation.

Interpretable Fine-Grained Phenotypes of Subcellular Dynamics via Unsupervised Deep Learning

Uncovering fine-grained phenotypes of live cell dynamics is pivotal for a comprehensive understanding of the heterogeneity in healthy and diseased biological processes. However, this endeavor poses significant technical challenges for unsupervised machine learning, requiring the extraction of features that not only faithfully preserve this heterogeneity but also effectively discriminate between established biological states, all while remaining interpretable. To tackle these challenges, a self-training deep learning framework designed for fine-grained and interpretable phenotyping is presented. This framework incorporates an unsupervised teacher model with interpretable features to facilitate feature learning in a student deep neural network (DNN). Significantly, an autoencoder-based regularizer is designed to encourage the student DNN to maximize the heterogeneity associated with molecular perturbations. This method enables the acquisition of features with enhanced discriminatory power, while simultaneously preserving the heterogeneity associated with molecular perturbations. This study successfully delineated fine-grained phenotypes within the heterogeneous protrusion dynamics of migrating epithelial cells, revealing specific responses to pharmacological perturbations. Remarkably, this framework adeptly captured a concise set of highly interpretable features uniquely linked to these fine-grained phenotypes, each corresponding to specific temporal intervals crucial for their manifestation. This unique capability establishes it as a valuable tool for investigating diverse cellular dynamics and their heterogeneity.

Is Tunisia ready for precision medicine? Challenges of medical genomics within a LMIC healthcare system

As one of the key tools on the precision medicine workbench, high-throughput genetic testing has enormous promise for improving healthcare outcomes. Tunisia has made tremendous progress in acquiring and implementing the technology in the clinical context. However, current utilization does not ensure the whole range of benefits that high-throughput genomic testing provides which impedes the country's ability to move forward into the new era of precision medicine. This issue is primarily related to the current state of Tunisia's healthcare ecosystem and the sociological attributes of its population, creating numerous challenges that must be addressed. In the current review, we aimed to identify and highlight these challenges that may be prevalent in other low and middle-income countries. Essentially, they fall into three main categories that include the socio-economic landscape in Tunisia, which prevents citizens from engaging in precision medicine activities; the current settings of the healthcare system that lack or miss key components for the successful implementation of precision medicine practices; and the inability of the current infrastructure and resources to handle the various challenges related to genomic data and metadata. We also propose five pillar solutions as a framework for addressing all of these challenges, which could strengthen Tunisia's capability for effective precision medicine implementation in today's clinical environment.

Early trajectories and moderators of autistic language profiles: A longitudinal study in preschoolers

LAY ABSTRACT

Language development can greatly vary among autistic children. Children who struggle with language acquisition often face many challenges and experience lower quality of life. However, little is known about the early language trajectories of autistic preschoolers and their moderators. Autistic language can be stratified into three profiles. Language unimpaired experience little to no language difficulties; language impaired show significant difficulties in language; minimally verbal never develop functional language. In this study, we used a longitudinal sample of preschoolers with autism and with typical development (aged 1.5-5.7 years). We replicated the three language profiles through a data-driven approach. We also found that different factors modulated the language outcome within each group. For instance, non-verbal cognition at age 2.4 moderated the participants' attribution to each language profile. Moreover, early intervention moderated verbal outcome in the language impaired profile. In conclusion, we provided a detailed description of how autistic preschoolers acquire language, and what factors might influence their trajectories. Our findings could inspire more personalized intervention for early autistic language difficulties.

Children with dyslexia show no deficit in exogenous spatial attention but show differences in visual encoding

In the search for mechanisms that contribute to dyslexia, the term "attention" has been invoked to explain performance in a variety of tasks, creating confusion since all tasks do, indeed, demand "attention." Many studies lack an experimental manipulation of attention that would be necessary to determine its influence on task performance. Nonetheless, an emerging view is that children with dyslexia have an impairment in the exogenous (automatic/reflexive) orienting of spatial attention. Here we investigated the link between exogenous attention and reading ability by presenting exogenous spatial cues in the multi-letter processing task-a task relevant for reading. The task was gamified and administered online to a large sample of children (N = 187) between 6 and 17 years. Children with dyslexia performed worse overall at rapidly recognizing and reporting strings of letters. However, we found no evidence for a difference in the utilization of exogenous spatial cues, resolving two decades of ambiguity in the field. Previous studies that claimed otherwise may have failed to distinguish attention effects from overall task performance or found spurious group differences in small samples. RESEARCH HIGHLIGHTS: We manipulated exogenous visual spatial attention using pre-cues in a task that is relevant for reading and we see robust task effects of exogenous attention. We found no evidence for a deficit in utilizing exogenous spatial pre-cues in children with dyslexia. However, children with dyslexia showed reduced recognition ability for all letter positions. Children with dyslexia were just as likely to make letter transposition errors as typical readers.

Improving reporting standards for phenotyping algorithm in biomedical research: 5 fundamental dimensions

INTRODUCTION

Phenotyping algorithms enable the interpretation of complex health data and definition of clinically relevant phenotypes; they have become crucial in biomedical research. However, the lack of standardization and transparency inhibits the cross-comparison of findings among different studies, limits large scale meta-analyses, confuses the research community, and prevents the reuse of algorithms, which results in duplication of efforts and the waste of valuable resources.

RECOMMENDATIONS

Here, we propose five independent fundamental dimensions of phenotyping algorithms-complexity, performance, efficiency, implementability, and maintenance-through which researchers can describe, measure, and deploy any algorithms efficiently and effectively. These dimensions must be considered in the context of explicit use cases and transparent methods to ensure that they do not reflect unexpected biases or exacerbate inequities.

PCAO2: an ontology for integration of prostate cancer associated genotypic, phenotypic and lifestyle data

Disease ontologies facilitate the semantic organization and representation of domain-specific knowledge. In the case of prostate cancer (PCa), large volumes of research results and clinical data have been accumulated and needed to be standardized for sharing and translational researches. A formal representation of PCa-associated knowledge will be essential to the diverse data standardization, data sharing and the future knowledge graph extraction, deep phenotyping and explainable artificial intelligence developing. In this study, we constructed an updated PCa ontology (PCAO2) based on the ontology development life cycle. An online information retrieval system was designed to ensure the usability of the ontology. The PCAO2 with a subclass-based taxonomic hierarchy covers the major biomedical concepts for PCa-associated genotypic, phenotypic and lifestyle data. The current version of the PCAO2 contains 633 concepts organized under three biomedical viewpoints, namely, epidemiology, diagnosis and treatment. These concepts are enriched by the addition of definition, synonym, relationship and reference. For the precision diagnosis and treatment, the PCa-associated genes and lifestyles are integrated in the viewpoint of epidemiological aspects of PCa. PCAO2 provides a standardized and systematized semantic framework for studying large amounts of heterogeneous PCa data and knowledge, which can be further, edited and enriched by the scientific community. The PCAO2 is freely available at https://bioportal.bioontology.org/ontologies/PCAO, http://pcaontology.net/ and http://pcaontology.net/mobile/.

Digital twins for health: a scoping review

The use of digital twins (DTs) has proliferated across various fields and industries, with a recent surge in the healthcare sector. The concept of digital twin for health (DT4H) holds great promise to revolutionize the entire healthcare system, including management and delivery, disease treatment and prevention, and health well-being maintenance, ultimately improving human life. The rapid growth of big data and continuous advancement in data science (DS) and artificial intelligence (AI) have the potential to significantly expedite DT research and development by providing scientific expertise, essential data, and robust cybertechnology infrastructure. Although various DT initiatives have been underway in the industry, government, and military, DT4H is still in its early stages. This paper presents an overview of the current applications of DTs in healthcare, examines consortium research centers and their limitations, and surveys the current landscape of emerging research and development opportunities in healthcare. We envision the emergence of a collaborative global effort among stakeholders to enhance healthcare and improve the quality of life for millions of individuals worldwide through pioneering research and development in the realm of DT technology.

Development of phenotyping algorithms for hypertensive disorders of pregnancy (HDP) and their application in more than 22,000 pregnant women

Recently, many phenotyping algorithms for high-throughput cohort identification have been developed. Prospective genome cohort studies are critical resources for precision medicine, but there are many hurdles in the precise cohort identification. Consequently, it is important to develop phenotyping algorithms for cohort data collection. Hypertensive disorders of pregnancy (HDP) is a leading cause of maternal morbidity and mortality. In this study, we developed, applied, and validated rule-based phenotyping algorithms of HDP. Two phenotyping algorithms, algorithms 1 and 2, were developed according to American and Japanese guidelines, and applied into 22,452 pregnant women in the Birth and Three-Generation Cohort Study of the Tohoku Medical Megabank project. To precise cohort identification, we analyzed both structured data (e.g., laboratory and physiological tests) and unstructured clinical notes. The identified subtypes of HDP were validated against reference standards. Algorithms 1 and 2 identified 7.93% and 8.08% of the subjects as having HDP, respectively, along with their HDP subtypes. Our algorithms were high performing with high positive predictive values (0.96 and 0.90 for algorithms 1 and 2, respectively). Overcoming the hurdle of precise cohort identification from large-scale cohort data collection, we achieved both developed and implemented phenotyping algorithms, and precisely identified HDP patients and their subtypes from large-scale cohort data collection.

CranioRate: An Image-Based, Deep-Phenotyping Analysis Toolset and Online Clinician Interface for Metopic Craniosynostosis

BACKGROUND

The diagnosis and management of metopic craniosynostosis involve subjective decision-making at the point of care. The purpose of this work was to describe a quantitative severity metric and point-of-care user interface to aid clinicians in the management of metopic craniosynostosis and to provide a platform for future research through deep phenotyping.

METHODS

Two machine-learning algorithms were developed that quantify the severity of craniosynostosis-a supervised model specific to metopic craniosynostosis [Metopic Severity Score (MSS)] and an unsupervised model used for cranial morphology in general [Cranial Morphology Deviation (CMD)]. Computed tomographic (CT) images from multiple institutions were compiled to establish the spectrum of severity, and a point-of-care tool was developed and validated.

RESULTS

Over the study period (2019 to 2021), 254 patients with metopic craniosynostosis and 92 control patients who underwent CT scanning between the ages of 6 and 18 months were included. CT scans were processed using an unsupervised machine-learning based dysmorphology quantification tool, CranioRate. The average MSS was 0.0 ± 1.0 for normal controls and 4.9 ± 2.3 ( P < 0.001) for those with metopic synostosis. The average CMD was 85.2 ± 19.2 for normal controls and 189.9 ± 43.4 ( P < 0.001) for those with metopic synostosis. A point-of-care user interface (craniorate.org) has processed 46 CT images from 10 institutions.

CONCLUSIONS

The resulting quantification of severity using MSS and CMD has shown an improved capacity, relative to conventional measures, to automatically classify normal controls versus patients with metopic synostosis. The authors have mathematically described, in an objective and quantifiable manner, the distribution of phenotypes in metopic craniosynostosis.

An Evolutionary Concept Analysis of Precision Medicine, and Its Contribution to a Precision Health Model for Nursing Practice

Precision medicine is a new concept that has been routinely encountered in the literature for little more than a decade. With increasing use, it becomes crucial to understand the meaning of this concept as it is applied in various settings. An evolutionary concept analysis was conducted to develop an understanding of the essential features of precision medicine and its use. The analysis led to a comprehensive list of the antecedents, attributes, and consequences of precision medicine in multiple settings. With this understanding, precision medicine becomes part of the broader practice of precision health, an important process proposed by nursing scholars to provide complete, holistic care to our patients. A model for precision health is presented as a framework for care.

A methodology of phenotyping ICU patients from EHR data: High-fidelity, personalized, and interpretable phenotypes estimation

OBJECTIVE

Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR).

METHODS

A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation.

RESULTS

The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83%±27%.

CONCLUSION

The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

SSLpheno: a self-supervised learning approach for gene-phenotype association prediction using protein-protein interactions and gene ontology data

MOTIVATION

Medical genomics faces significant challenges in interpreting disease phenotype and genetic heterogeneity. Despite the establishment of standardized disease phenotype databases, computational methods for predicting gene-phenotype associations still suffer from imbalanced category distribution and a lack of labeled data in small categories.

RESULTS

To address the problem of labeled-data scarcity, we propose a self-supervised learning strategy for gene-phenotype association prediction, called SSLpheno. Our approach utilizes an attributed network that integrates protein-protein interactions and gene ontology data. We apply a Laplacian-based filter to ensure feature smoothness and use self-supervised training to optimize node feature representation. Specifically, we calculate the cosine similarity of feature vectors and select positive and negative sample nodes for reconstruction training labels. We employ a deep neural network for multi-label classification of phenotypes in the downstream task. Our experimental results demonstrate that SSLpheno outperforms state-of-the-art methods, especially in categories with fewer annotations. Moreover, our case studies illustrate the potential of SSLpheno as an effective prescreening tool for gene-phenotype association identification.

AVAILABILITY AND IMPLEMENTATION

https://github.com/bixuehua/SSLpheno.

Advancing the Management of Long COVID by Integrating into Health Informatics Domain: Current and Future Perspectives

The ongoing COVID-19 pandemic has profoundly affected millions of lives globally, with some individuals experiencing persistent symptoms even after recovering. Understanding and managing the long-term sequelae of COVID-19 is crucial for research, prevention, and control. To effectively monitor the health of those affected, maintaining up-to-date health records is essential, and digital health informatics apps for surveillance play a pivotal role. In this review, we overview the existing literature on identifying and characterizing long COVID manifestations through hierarchical classification based on Human Phenotype Ontology (HPO). We outline the aspects of the National COVID Cohort Collaborative (N3C) and Researching COVID to Enhance Recovery (RECOVER) initiative in artificial intelligence (AI) to identify long COVID. Through knowledge exploration, we present a concept map of clinical pathways for long COVID, which offers insights into the data required and explores innovative frameworks for health informatics apps for tackling the long-term effects of COVID-19. This study achieves two main objectives by comprehensively reviewing long COVID identification and characterization techniques, making it the first paper to explore incorporating long COVID as a variable risk factor within a digital health informatics application. By achieving these objectives, it provides valuable insights on long COVID's challenges and impact on public health.

Automated detection of causal relationships among diseases and imaging findings in textual radiology reports

OBJECTIVE

Textual radiology reports contain a wealth of information that may help understand associations among diseases and imaging observations. This study evaluated the ability to detect causal associations among diseases and imaging findings from their co-occurrence in radiology reports.

MATERIALS AND METHODS

This IRB-approved and HIPAA-compliant study analyzed 1 702 462 consecutive reports of 1 396 293 patients; patient consent was waived. Reports were analyzed for positive mention of 16 839 entities (disorders and imaging findings) of the Radiology Gamuts Ontology (RGO). Entities that occurred in fewer than 25 patients were excluded. A Bayesian network structure-learning algorithm was applied at P < 0.05 threshold: edges were evaluated as possible causal relationships. RGO and/or physician consensus served as ground truth.

RESULTS

2742 of 16 839 RGO entities were included, 53 849 patients (3.9%) had at least one included entity. The algorithm identified 725 pairs of entities as causally related; 634 were confirmed by reference to RGO or physician review (87% precision). As shown by its positive likelihood ratio, the algorithm increased detection of causally associated entities 6876-fold.

DISCUSSION

Causal relationships among diseases and imaging findings can be detected with high precision from textual radiology reports.

CONCLUSION

This approach finds causal relationships among diseases and imaging findings with high precision from textual radiology reports, despite the fact that causally related entities represent only 0.039% of all pairs of entities. Applying this approach to larger report text corpora may help detect unspecified or heretofore unrecognized associations.

Dissecting Schizotypy and Its Association With Cognition and Polygenic Risk for Schizophrenia in a Nonclinical Sample

Schizotypy is a multidimensional construct that captures a continuum of risk for developing schizophrenia-spectrum psychopathology. Existing 3-factor models of schizotypy, consisting of positive, negative, and disorganized dimensions have yielded mixed evidence of genetic continuity with schizophrenia using polygenic risk scores. Here, we propose an approach that involves splitting positive and negative schizotypy into more specific subdimensions that are phenotypically continuous with distinct positive symptoms and negative symptoms recognized in clinical schizophrenia. We used item response theory to derive high-precision estimates of psychometric schizotypy using 251 self-report items obtained from a non-clinical sample of 727 (424 females) adults. These subdimensions were organized hierarchically using structural equation modeling into 3 empirically independent higher-order dimensions enabling associations with polygenic risk for schizophrenia to be examined at different levels of phenotypic generality and specificity. Results revealed that polygenic risk for schizophrenia was associated with variance specific to delusional experiences (γ = 0.093, P = .001) and reduced social interest and engagement (γ = 0.076, P = .020), and these effects were not mediated via the higher-order general, positive, or negative schizotypy factors. We further fractionated general intellectual functioning into fluid and crystallized intelligence in 446 (246 females) participants that underwent onsite cognitive assessment. Polygenic risk scores explained 3.6% of the variance in crystallized intelligence. Our precision phenotyping approach could be used to enhance the etiologic signal in future genetic association studies and improve the detection and prevention of schizophrenia-spectrum psychopathology.

Clinical characteristics indexing genetic differences in bipolar disorder - a systematic review

Bipolar disorder is a heterogenous condition with a varied clinical presentation. While progress has been made in identifying genetic variants associated with bipolar disorder, most common genetic variants have not yet been identified. More detailed phenotyping (beyond diagnosis) may increase the chance of finding genetic variants. Our aim therefore was to identify clinical characteristics that index genetic differences in bipolar disorder.We performed a systematic review of all genome-wide molecular genetic, family, and twin studies investigating familial/genetic influences on the clinical characteristics of bipolar disorder. We performed an electronic database search of PubMed and PsycInfo until October 2022. We reviewed title/abstracts of 2693 unique records and full texts of 391 reports, identifying 445 relevant analyses from 142 different reports. These reports described 199 analyses from family studies, 183 analyses from molecular genetic studies and 63 analyses from other types of studies. We summarized the overall evidence per phenotype considering study quality, power, and number of studies.We found moderate to strong evidence for a positive association of age at onset, subtype (bipolar I versus bipolar II), psychotic symptoms and manic symptoms with familial/genetic risk of bipolar disorder. Sex was not associated with overall genetic risk but could indicate qualitative genetic differences. Assessment of genetically relevant clinical characteristics of patients with bipolar disorder can be used to increase the phenotypic and genetic homogeneity of the sample in future genetic studies, which may yield more power, increase specificity, and improve understanding of the genetic architecture of bipolar disorder.

Modeling psychotic disorders: Environment x environment interaction

Schizophrenia is a major psychotic disorder with multifactorial etiology that includes interactions between genetic vulnerability and environmental risk factors. In addition, interplay of multiple environmental adversities affects neurodevelopment and may increase the individual risk of developing schizophrenia. Consistent with the two-hit hypothesis of schizophrenia, we review rodent models that combine maternal immune activation as the first hit with other adverse environmental exposures as the second hit. We discuss the strengths and pitfalls of the current animal models of environment x environment interplay and propose some future directions to advance the field.

Comorbidities of community-dwelling older adults with urinary incontinence: A scoping review

BACKGROUND

Identifying comorbidities is a critical first step to building clinical phenotypes to improve assessment, management, and outcomes.

OBJECTIVES

1) Identify relevant comorbidities of community-dwelling older adults with urinary incontinence, 2) provide insights about relationships between conditions.

METHODS

PubMed, Cumulative Index of Nursing and Allied Health Literature, and Embase were searched. Eligible studies had quantitative designs that analyzed urinary incontinence as the exposure or outcome variable. Critical appraisal was performed using the Joanna Briggs Institute Critical Appraisal Checklists.

RESULTS

Ten studies were included. Most studies had methodological weaknesses in the measurement of conditions. Comorbidities affecting the neurologic, cardiovascular, psychologic, respiratory, endocrine, genitourinary, and musculoskeletal systems were found to be associated with urinary incontinence.

CONCLUSION

Existing literature suggests that comorbidities and urinary incontinence are interrelated. Further research is needed to examine symptoms, shared mechanisms, and directionality of relationships to generate clinical phenotypes, evidence-based holistic care guidelines, and improve outcomes.

A methodology of phenotyping ICU patients from EHR data: high-fidelity, personalized, and interpretable phenotypes estimation

Objective

Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR).

Methods

A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation.

Results

The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83% ± 27%.

Conclusion

The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

The All of Us Data and Research Center: Creating a Secure, Scalable, and Sustainable Ecosystem for Biomedical Research

The All of Us Research Program's Data and Research Center (DRC) was established to help acquire, curate, and provide access to one of the world's largest and most diverse datasets for precision medicine research. Already, over 500,000 participants are enrolled in All of Us, 80% of whom are underrepresented in biomedical research, and data are being analyzed by a community of over 2,300 researchers. The DRC created this thriving data ecosystem by collaborating with engaged participants, innovative program partners, and empowered researchers. In this review, we first describe how the DRC is organized to meet the needs of this broad group of stakeholders. We then outline guiding principles, common challenges, and innovative approaches used to build the All of Us data ecosystem. Finally, we share lessons learned to help others navigate important decisions and trade-offs in building a modern biomedical data platform.

Precision Medicine: Disease Subtyping and Tailored Treatment

The genomics-based concept of precision medicine began to emerge following the completion of the Human Genome Project. In contrast to evidence-based medicine, precision medicine will allow doctors and scientists to tailor the treatment of different subpopulations of patients who differ in their susceptibility to specific diseases or responsiveness to specific therapies. The current precision medicine model was proposed to precisely classify patients into subgroups sharing a common biological basis of diseases for more effective tailored treatment to achieve improved outcomes. Precision medicine has become a term that symbolizes the new age of medicine. In this review, we examine the history, development, and future perspective of precision medicine. We also discuss the concepts, principles, tools, and applications of precision medicine and related fields. In our view, for precision medicine to work, two essential objectives need to be achieved. First, diseases need to be classified into various subtypes. Second, targeted therapies must be available for each specific disease subtype. Therefore, we focused this review on the progress in meeting these two objectives.

Phenomics and Robust Multiomics Data for Cardiovascular Disease Subtyping

The complex landscape of cardiovascular diseases encompasses a wide range of related pathologies arising from diverse molecular mechanisms and exhibiting heterogeneous phenotypes. This variety of manifestations poses significant challenges in the development of treatment strategies. The increasing availability of precise phenotypic and multiomics data of cardiovascular disease patient populations has spurred the development of a variety of computational disease subtyping techniques to identify distinct subgroups with unique underlying pathogeneses. In this review, we outline the essential components of computational approaches to select, integrate, and cluster omics and clinical data in the context of cardiovascular disease research. We delve into the challenges faced during different stages of the analysis, including feature selection and extraction, data integration, and clustering algorithms. Next, we highlight representative applications of subtyping pipelines in heart failure and coronary artery disease. Finally, we discuss the current challenges and future directions in the development of robust subtyping approaches that can be implemented in clinical workflows, ultimately contributing to the ongoing evolution of precision medicine in health care.

Inter-rater agreement for the annotation of neurologic signs and symptoms in electronic health records

The extraction of patient signs and symptoms recorded as free text in electronic health records is critical for precision medicine. Once extracted, signs and symptoms can be made computable by mapping to signs and symptoms in an ontology. Extracting signs and symptoms from free text is tedious and time-consuming. Prior studies have suggested that inter-rater agreement for clinical concept extraction is low. We have examined inter-rater agreement for annotating neurologic concepts in clinical notes from electronic health records. After training on the annotation process, the annotation tool, and the supporting neuro-ontology, three raters annotated 15 clinical notes in three rounds. Inter-rater agreement between the three annotators was high for text span and category label. A machine annotator based on a convolutional neural network had a high level of agreement with the human annotators but one that was lower than human inter-rater agreement. We conclude that high levels of agreement between human annotators are possible with appropriate training and annotation tools. Furthermore, more training examples combined with improvements in neural networks and natural language processing should make machine annotators capable of high throughput automated clinical concept extraction with high levels of agreement with human annotators.

Deep Clinical Phenotyping of Schizophrenia Spectrum Disorders Using Data-Driven Methods: Marching towards Precision Psychiatry

Heterogeneity is the main challenge in the traditional classification of mental disorders, including schizophrenia spectrum disorders (SSD). This can be partly attributed to the absence of objective diagnostic criteria and the multidimensional nature of symptoms and their associated factors. This article provides an overview of findings from the Genetic Risk and Outcome of Psychosis (GROUP) cohort study on the deep clinical phenotyping of schizophrenia spectrum disorders targeting positive and negative symptoms, cognitive impairments and psychosocial functioning. Three to four latent subtypes of positive and negative symptoms were identified in patients, siblings and controls, whereas four to six latent cognitive subtypes were identified. Five latent subtypes of psychosocial function-multidimensional social inclusion and premorbid adjustment-were also identified in patients. We discovered that the identified subtypes had mixed profiles and exhibited stable, deteriorating, relapsing and ameliorating longitudinal courses over time. Baseline positive and negative symptoms, premorbid adjustment, psychotic-like experiences, health-related quality of life and PRSSCZ were found to be the strong predictors of the identified subtypes. Our findings are comprehensive, novel and of clinical interest for precisely identifying high-risk population groups, patients with good or poor disease prognosis and the selection of optimal intervention, ultimately fostering precision psychiatry by tackling diagnostic and treatment selection challenges pertaining to heterogeneity.

Opportunities for Systems Biology and Quantitative Systems Pharmacology to Address Knowledge Gaps for Drug Development in Pregnancy

Pregnant women are still viewed as therapeutic orphans to the extent that they are avoided as participants in mainstream clinical trials and not considered a priority for targeted drug research despite the fact that many clinical conditions exist during pregnancy for which pharmacotherapy is warranted. Part of the challenge is the uncertain risk potential that pregnant women represent in the absence of timely and costly toxicology and developmental pharmacology studies, which only partly mitigate such risks. Even when clinical trials are conducted in pregnant women, they are often underpowered and absent biomarkers and exclude evaluation across multiple stages of pregnancy where relevant development risk could have been assessed. Quantitative systems pharmacology model development has been proposed as one solution to fill knowledge gaps, make earlier and perhaps more informed risk assessment, and design more informative trials with better recommendations for biomarker and end point selection including design and sample size optimality. Funding for translational research in pregnancy is limited but will fill some of these gaps, especially when joined with ongoing clinical trials in pregnancy that also fill certain knowledge gaps, especially biomarker and end point evaluation across pregnancy states linked to clinical outcomes. Opportunities exist for further advances in quantitative systems pharmacology model development with the inclusion of real-world data sources and complimentary artificial intelligence/machine learning approaches. The successful coordination of the approach reliant on these new data sources will require commitments to share data and a diverse multidisciplinary group that seeks to develop open science models that benefit the entire research community, ensuring that such models can be used with high fidelity. New data opportunities and computational resources are highlighted in an effort to project how these efforts can move forward.

Phenomic Studies on Diseases: Potential and Challenges

The rapid development of such research field as multi-omics and artificial intelligence (AI) has made it possible to acquire and analyze the multi-dimensional big data of human phenomes. Increasing evidence has indicated that phenomics can provide a revolutionary strategy and approach for discovering new risk factors, diagnostic biomarkers and precision therapies of diseases, which holds profound advantages over conventional approaches for realizing precision medicine: first, the big data of patients' phenomes can provide remarkably richer information than that of the genomes; second, phenomic studies on diseases may expose the correlations among cross-scale and multi-dimensional phenomic parameters as well as the mechanisms underlying the correlations; and third, phenomics-based studies are big data-driven studies, which can significantly enhance the possibility and efficiency for generating novel discoveries. However, phenomic studies on human diseases are still in early developmental stage, which are facing multiple major challenges and tasks: first, there is significant deficiency in analytical and modeling approaches for analyzing the multi-dimensional data of human phenomes; second, it is crucial to establish universal standards for acquirement and management of phenomic data of patients; third, new methods and devices for acquirement of phenomic data of patients under clinical settings should be developed; fourth, it is of significance to establish the regulatory and ethical guidelines for phenomic studies on diseases; and fifth, it is important to develop effective international cooperation. It is expected that phenomic studies on diseases would profoundly and comprehensively enhance our capacity in prevention, diagnosis and treatment of diseases.

Democratising or disrupting diagnosis? Ethical issues raised by the use of AI tools for rare disease diagnosis

Computational phenotyping (CP) technology uses facial recognition algorithms to classify and potentially diagnose rare genetic disorders on the basis of digitised facial images. This AI technology has a number of research as well as clinical applications, such as supporting diagnostic decision-making. Using the example of CP, we examine stakeholders' views of the benefits and costs of using AI as a diagnostic tool within the clinic. Through a series of in-depth interviews (n ​= ​20) with: clinicians, clinical researchers, data scientists, industry and support group representatives, we report stakeholder views regarding the adoption of this technology in a clinical setting. While most interviewees were supportive of employing CP as a diagnostic tool in some capacity we observed ambivalence around the potential for artificial intelligence to overcome diagnostic uncertainty in a clinical context. Thus, while there was widespread agreement amongst interviewees concerning the public benefits of AI assisted diagnosis, namely, its potential to increase diagnostic yield and enable faster more objective and accurate diagnoses by up skilling non specialists and thereby enabling access to diagnosis that is potentially lacking, interviewees also raised concerns about ensuring algorithmic reliability, expunging algorithmic bias and that the use of AI could result in deskilling the specialist clinical workforce. We conclude that, prior to widespread clinical implementation, on-going reflection is needed regarding the trade-offs required to determine acceptable levels of bias and conclude that diagnostic AI tools should only be employed as an assistive technology within the dysmorphology clinic.

Ontologizing health systems data at scale: making translational discovery a reality

Common data models solve many challenges of standardizing electronic health record (EHR) data but are unable to semantically integrate all of the resources needed for deep phenotyping. Open Biological and Biomedical Ontology (OBO) Foundry ontologies provide computable representations of biological knowledge and enable the integration of heterogeneous data. However, mapping EHR data to OBO ontologies requires significant manual curation and domain expertise. We introduce OMOP2OBO, an algorithm for mapping Observational Medical Outcomes Partnership (OMOP) vocabularies to OBO ontologies. Using OMOP2OBO, we produced mappings for 92,367 conditions, 8611 drug ingredients, and 10,673 measurement results, which covered 68-99% of concepts used in clinical practice when examined across 24 hospitals. When used to phenotype rare disease patients, the mappings helped systematically identify undiagnosed patients who might benefit from genetic testing. By aligning OMOP vocabularies to OBO ontologies our algorithm presents new opportunities to advance EHR-based deep phenotyping.

CEP55 as a promising biomarker and therapeutic target on gallbladder cancer

Introduction

Gallbladder cancer (GBC) is a highly malignant biliary tumor with a poor prognosis. As existing therapies for advanced metastatic GBC are rarely effective, there is an urgent need to identify more effective targets for treatment.

Methods

Hub genes of GBC were identified by bioinformatics analysis and their expression in GBC was analyzed by tissue validation. The biological role of CEP55 in GBC cell and the underlying mechanism of the anticancer effect of CEP55 knockdown were evaluated via CCK8, colony formation assay, EDU staining, flow cytometry, western blot, immunofluorescence, and an alkaline comet assay.

Results

We screened out five hub genes of GBC, namely PLK1, CEP55, FANCI, NEK2 and PTTG1. CEP55 is not only overexpressed in the GBC but also correlated with advanced TNM stage, differentiation grade and poorer survival. After CEP55 knockdown, the proliferation of GBC cells was inhibited with cell cycle arrest in G2/M phase and DNA damage. There was a marked increase in the apoptosis of GBC cells in the siCEP55 group. Besides, in vivo, CEP55 inhibition attenuated the growth and promoted apoptosis of GBC cells. Mechanically, the tumor suppressor effect of CEP55 knockdown is associated with dysregulation of the AKT and ERK signaling networks.

Discussion

These data not only demonstrate that CEP55 is identified as a potential independent predictor crucial to the diagnosis and prognosis of gallbladder cancer but also reveal the possibility for CEP55 to be used as a promising target in the treatment of GBC.

Precision Medicine in Neurocritical Care for Cerebrovascular Disease Cases

Scientific advances have informed many aspects of acute stroke care but have also highlighted the complexity and heterogeneity of cerebrovascular diseases. While practice guidelines are essential in supporting the clinical decision-making process, they may not capture the nuances of individual cases. Personalized stroke care in ICU has traditionally relied on integrating clinical examinations, neuroimaging studies, and physiologic monitoring to develop a treatment plan tailored to the individual patient. However, to realize the potential of precision medicine in stroke, we need advances and evidence in several critical areas, including data capture, clinical phenotyping, serum biomarker development, neuromonitoring, and physiology-based treatment targets. Mathematical tools are being developed to analyze the multitude of data and provide clinicians with real-time information and personalized treatment targets for the critical care management of patients with cerebrovascular diseases. This review summarizes research advances in these areas and outlines principles for translating precision medicine into clinical practice.

Managing re-identification risks while providing access to the All of Us research program

OBJECTIVE

The All of Us Research Program makes individual-level data available to researchers while protecting the participants' privacy. This article describes the protections embedded in the multistep access process, with a particular focus on how the data was transformed to meet generally accepted re-identification risk levels.

METHODS

At the time of the study, the resource consisted of 329 084 participants. Systematic amendments were applied to the data to mitigate re-identification risk (eg, generalization of geographic regions, suppression of public events, and randomization of dates). We computed the re-identification risk for each participant using a state-of-the-art adversarial model specifically assuming that it is known that someone is a participant in the program. We confirmed the expected risk is no greater than 0.09, a threshold that is consistent with guidelines from various US state and federal agencies. We further investigated how risk varied as a function of participant demographics.

RESULTS

The results indicated that 95th percentile of the re-identification risk of all the participants is below current thresholds. At the same time, we observed that risk levels were higher for certain race, ethnic, and genders.

CONCLUSIONS

While the re-identification risk was sufficiently low, this does not imply that the system is devoid of risk. Rather, All of Us uses a multipronged data protection strategy that includes strong authentication practices, active monitoring of data misuse, and penalization mechanisms for users who violate terms of service.

EULAR study group on ‘MHC-I-opathy’: identifying disease-overarching mechanisms across disciplines and borders

The ‘MHC-I (major histocompatibility complex class I)-opathy’ concept describes a family of inflammatory conditions with overlapping clinical manifestations and a strong genetic link to the MHC-I antigen presentation pathway. Classical MHC-I-opathies such as spondyloarthritis, Behçet’s disease, psoriasis and birdshot uveitis are widely recognised for their strong association with certain MHC-I alleles and gene variants of the antigen processing aminopeptidases ERAP1 and ERAP2 that implicates altered MHC-I peptide presentation to CD8+T cells in the pathogenesis. Progress in understanding the cause and treatment of these disorders is hampered by patient phenotypic heterogeneity and lack of systematic investigation of the MHC-I pathway.

Here, we discuss new insights into the biology of MHC-I-opathies that strongly advocate for disease-overarching and integrated molecular and clinical investigation to decipher underlying disease mechanisms. Because this requires transformative multidisciplinary collaboration, we introduce the EULAR study group on MHC-I-opathies to unite clinical expertise in rheumatology, dermatology and ophthalmology, with fundamental and translational researchers from multiple disciplines such as immunology, genomics and proteomics, alongside patient partners. We prioritise standardisation of disease phenotypes and scientific nomenclature and propose interdisciplinary genetic and translational studies to exploit emerging therapeutic strategies to understand MHC-I-mediated disease mechanisms. These collaborative efforts are required to address outstanding questions in the etiopathogenesis of MHC-I-opathies towards improving patient treatment and prognostication.

Trends and opportunities in computable clinical phenotyping: A scoping review

Identifying patient cohorts meeting the criteria of specific phenotypes is essential in biomedicine and particularly timely in precision medicine. Many research groups deliver pipelines that automatically retrieve and analyze data elements from one or more sources to automate this task and deliver high-performing computable phenotypes. We applied a systematic approach based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines to conduct a thorough scoping review on computable clinical phenotyping. Five databases were searched using a query that combined the concepts of automation, clinical context, and phenotyping. Subsequently, four reviewers screened 7960 records (after removing over 4000 duplicates) and selected 139 that satisfied the inclusion criteria. This dataset was analyzed to extract information on target use cases, data-related topics, phenotyping methodologies, evaluation strategies, and portability of developed solutions. Most studies supported patient cohort selection without discussing the application to specific use cases, such as precision medicine. Electronic Health Records were the primary source in 87.1 % (N = 121) of all studies, and International Classification of Diseases codes were heavily used in 55.4 % (N = 77) of all studies, however, only 25.9 % (N = 36) of the records described compliance with a common data model. In terms of the presented methods, traditional Machine Learning (ML) was the dominant method, often combined with natural language processing and other approaches, while external validation and portability of computable phenotypes were pursued in many cases. These findings revealed that defining target use cases precisely, moving away from sole ML strategies, and evaluating the proposed solutions in the real setting are essential opportunities for future work. There is also momentum and an emerging need for computable phenotyping to support clinical and epidemiological research and precision medicine.

The visualization of Orphadata neurology phenotypes

Disease phenotypes are characterized by signs (what a physician observes during the examination of a patient) and symptoms (the complaints of a patient to a physician). Large repositories of disease phenotypes are accessible through the Online Mendelian Inheritance of Man, Human Phenotype Ontology, and Orphadata initiatives. Many of the diseases in these datasets are neurologic. For each repository, the phenotype of neurologic disease is represented as a list of concepts of variable length where the concepts are selected from a restricted ontology. Visualizations of these concept lists are not provided. We address this limitation by using subsumption to reduce the number of descriptive features from 2,946 classes into thirty superclasses. Phenotype feature lists of variable lengths were converted into fixed-length vectors. Phenotype vectors were aggregated into matrices and visualized as heat maps that allowed side-by-side disease comparisons. Individual diseases (representing a row in the matrix) were visualized as word clouds. We illustrate the utility of this approach by visualizing the neuro-phenotypes of 32 dystonic diseases from Orphadata. Subsumption can collapse phenotype features into superclasses, phenotype lists can be vectorized, and phenotypes vectors can be visualized as heat maps and word clouds.

Relevance of Biochemical Deep Phenotyping for a Personalised Approach to Parkinson's Disease

Parkinson's disease (PD) is a multifactorial neurodegenerative disorder characterised by the progressive loss of dopaminergic neurons in the nigrostriatal tract. The identification of disease-modifying therapies is the Holy Grail of PD research, but to date no drug has been approved as such a therapy. A possible reason is the remarkable phenotypic heterogeneity of PD patients, which can generate confusion in the interpretation of results or even mask the efficacy of a therapeutic intervention. This heterogeneity should be taken into account in clinical trials, stratifying patients by their expected response to drugs designed to engage selected molecular targets. In this setting, stratification methods (clinical and genetic) should be supported by biochemical phenotyping of PD patients, in line with the deep phenotyping concept. Collection, from single patients, of a range of biological samples would streamline the generation of these profiles. Several studies have proposed biochemical characterisations of patient cohorts based on analysis of blood, cerebrospinal fluid, urine, stool, saliva and skin biopsy samples, with extracellular vesicles attracting increasing interest as a source of biomarkers. In this review we report and critically discuss major studies that used a biochemical approach to stratify their PD cohorts. The analyte most studied is α-synuclein, while other studies have focused on neurofilament light chain, lysosomal proteins, inflammasome-related proteins, LRRK2 and the urinary proteome. At present, stratification of PD patients, while promising, is still a nascent approach. Deep phenotyping of patients will allow clinical researchers to identify homogeneous subgroups for the investigation of tailored disease-modifying therapies, enhancing the chances of therapeutic success.

Management of patients with hidradenitis suppurativa having underlying genetic variation: a systematic review and a call for precision medicine

Hidradenitis suppurativa (HS) is a chronic inflammatory condition of the pilosebaceous unit characterized by inflammation and hyperkeratinization. A small but significant proportion of patients with HS have a strong genetic susceptibility to (or a syndromic form of) the disease. Current HS treatment guidelines prioritize patients who manifest classic HS and may therefore not be suitable for the minority of patients harbouring genetically driven forms of disease. In this manuscript, we review the extant literature with regards to therapeutic strategies used for patients with HS having disease-associated genetic variants and syndromic forms of the condition. The findings of this review suggest that patients with HS harbouring underlying genetic variants may not be adequately represented in current European and British HS treatment guidelines. Moreover, these patients may be less responsive to the recommended therapeutic options. We therefore make recommendations for future therapeutic guidelines to incorporate considerations for the management of this patient subset.

Predicting Physiological Response in Heart Failure Management: A Graph Representation Learning Approach using Electronic Health Records

Heart failure management is challenging due to the complex and heterogenous nature of its pathophysiology which makes the conventional treatments based on the "one size fits all" ideology not suitable. Coupling the longitudinal medical data with novel deep learning and network-based analytics will enable identifying the distinct patient phenotypic characteristics to help individualize the treatment regimen through the accurate prediction of the physiological response. In this study, we develop a graph representation learning framework that integrates the heterogeneous clinical events in the electronic health records (EHR) as graph format data, in which the patient-specific patterns and features are naturally infused for personalized predictions of lab test response. The framework includes a novel Graph Transformer Network that is equipped with a self-attention mechanism to model the underlying spatial interdependencies among the clinical events characterizing the cardiac physiological interactions in the heart failure treatment and a graph neural network (GNN) layer to incorporate the explicit temporality of each clinical event, that would help summarize the therapeutic effects induced on the physiological variables, and subsequently on the patient's health status as the heart failure condition progresses over time. We introduce a global attention mask that is computed based on event co-occurrences and is aggregated across all patient records to enhance the guidance of neighbor selection in graph representation learning. We test the feasibility of our model through detailed quantitative and qualitative evaluations on observational EHR data.

Plant Hormonomics: A Key Tool for Deep Physiological Phenotyping to Improve Crop Productivity

Agriculture is particularly vulnerable to climate change. To cope with the risks posed by climate-related stressors to agricultural production, global population growth, and changes in food preferences, it is imperative to develop new climate-smart crop varieties with increased yield and environmental resilience. Molecular genetics and genomic analyses have revealed that allelic variations in genes involved in phytohormone-mediated growth regulation have greatly improved productivity in major crops. Plant science has remarkably advanced our understanding of the molecular basis of various phytohormone-mediated events in plant life. These findings provide essential information for improving the productivity of crops growing in changing climates. In this review, we highlight the recent advances in plant hormonomics (multiple phytohormone profiling) and discuss its application to crop improvement. We present plant hormonomics as a key tool for deep physiological phenotyping, focusing on representative plant growth regulators associated with the improvement of crop productivity. Specifically, we review advanced methodologies in plant hormonomics, highlighting mass spectrometry- and nanosensor-based plant hormone profiling techniques. We also discuss the applications of plant hormonomics in crop improvement through breeding and agricultural management practices.

IL-13, periostin and dipeptidyl-peptidase-4 reveal endotype-phenotype associations in atopic dermatitis

BACKGROUND

The heterogeneous (endo)phenotypes of atopic dermatitis (AD) require precision medicine. Currently, systemic therapy is recommended to patients with an Eczema Area and Severity Index (EASI)≥16. Previous studies have demonstrated an improved treatment response to the anti-interleukin (IL)-13 antibody tralokinumab in AD subgroups with elevated levels of the IL-13-related biomarkers dipeptidyl-peptidase (DPP)-4 and periostin.

METHODS

Herein, 373 AD patients aged≥12 years were stratified by IL-13high , periostinhigh and DPP-4high endotypes using cross-sectional data from the ProRaD cohort Bonn. "High" was defined as >80th quantile of 47 non-atopic controls. We analyzed endotype-phenotype associations using machine-learning gradient boosting compared to logistic regression.

RESULTS

AD severity and eosinophils correlated with IL-13 and periostin levels. Correlations of IL-13 with EASI were stronger in patients with increased (rs=0.482) than with normal (rs=0.342) periostin levels. We identified eosinophilia>6% and an EASI range of 5.5-17 dependent on the biomarker combination to be associated with increasing probabilities of biomarkerhigh endotypes. Also patients with mild-to-low-moderate severity (EASI<16) featured increased biomarkers (IL-13high : 41%, periostinhigh : 48.4%, DPP-4high : 22.3%). Herthoge sign (adjusted Odds Ratio (aOR)=1.89, 95% Confidence Interval (CI) [1.14-3.14]) and maternal allergic rhinitis (aOR=2.79-4.47) increased the probability of an IL-13high -endotype, "dirty neck" (aOR=2.83 [1.32-6.07]), orbital darkening (aOR=2.43 [1.08-5.50]), keratosis pilaris (aOR=2.21 [1.1-4.42]) and perleche (aOR=3.44 [1.72-6.86]) of a DPP-4high -endotype.

CONCLUSIONS

A substantial proportion of patients with EASI<16 featured high biomarker levels suggesting systemic impact of skin inflammation already below the current cut-off for systemic therapy. Our findings facilitate the identification of patients with distinct endotypes potentially linked to response to IL-13-targeted therapy.

Advancing the precision management of inflammatory bowel disease in the era of omics approaches and new technology

There is great heterogeneity among inflammatory bowel disease (IBD) patients in terms of pathogenesis, clinical manifestation, response to treatment, and prognosis, which requires the individualized and precision management of patients. Many studies have focused on prediction biomarkers and models for assessing IBD disease type, activity, severity, and prognosis. During the era of biologics, how to predict the response and side effects of patients to different treatments and how to quickly recognize the loss of response have also become important topics. Multiomics is a promising area for investigating the complex network of IBD pathogenesis. Integrating numerous amounts of data requires the use of artificial intelligence.

Subtypes of relapsing-remitting multiple sclerosis identified by network analysis

We used network analysis to identify subtypes of relapsing-remitting multiple sclerosis subjects based on their cumulative signs and symptoms. The electronic medical records of 113 subjects with relapsing-remitting multiple sclerosis were reviewed, signs and symptoms were mapped to classes in a neuro-ontology, and classes were collapsed into sixteen superclasses by subsumption. After normalization and vectorization of the data, bipartite (subject-feature) and unipartite (subject-subject) network graphs were created using NetworkX and visualized in Gephi. Degree and weighted degree were calculated for each node. Graphs were partitioned into communities using the modularity score. Feature maps visualized differences in features by community. Network analysis of the unipartite graph yielded a higher modularity score (0.49) than the bipartite graph (0.25). The bipartite network was partitioned into five communities which were named fatigue, behavioral, hypertonia/weakness, abnormal gait/sphincter, and sensory, based on feature characteristics. The unipartite network was partitioned into five communities which were named fatigue, pain, cognitive, sensory, and gait/weakness/hypertonia based on features. Although we did not identify pure subtypes (e.g., pure motor, pure sensory, etc.) in this cohort of multiple sclerosis subjects, we demonstrated that network analysis could partition these subjects into different subtype communities. Larger datasets and additional partitioning algorithms are needed to confirm these findings and elucidate their significance. This study contributes to the literature investigating subtypes of multiple sclerosis by combining feature reduction by subsumption with network analysis.

Design considerations for a hierarchical semantic compositional framework for medical natural language understanding

Medical natural language processing (NLP) systems are a key enabling technology for transforming Big Data from clinical report repositories to information used to support disease models and validate intervention methods. However, current medical NLP systems fall considerably short when faced with the task of logically interpreting clinical text. In this paper, we describe a framework inspired by mechanisms of human cognition in an attempt to jump the NLP performance curve. The design centers on a hierarchical semantic compositional model (HSCM), which provides an internal substrate for guiding the interpretation process. The paper describes insights from four key cognitive aspects: semantic memory, semantic composition, semantic activation, and hierarchical predictive coding. We discuss the design of a generative semantic model and an associated semantic parser used to transform a free-text sentence into a logical representation of its meaning. The paper discusses supportive and antagonistic arguments for the key features of the architecture as a long-term foundational framework.

Enhanced neurologic concept recognition using a named entity recognition model based on transformers

Although deep learning has been applied to the recognition of diseases and drugs in electronic health records and the biomedical literature, relatively little study has been devoted to the utility of deep learning for the recognition of signs and symptoms. The recognition of signs and symptoms is critical to the success of deep phenotyping and precision medicine. We have developed a named entity recognition model that uses deep learning to identify text spans containing neurological signs and symptoms and then maps these text spans to the clinical concepts of a neuro-ontology. We compared a model based on convolutional neural networks to one based on bidirectional encoder representation from transformers. Models were evaluated for accuracy of text span identification on three text corpora: physician notes from an electronic health record, case histories from neurologic textbooks, and clinical synopses from an online database of genetic diseases. Both models performed best on the professionally-written clinical synopses and worst on the physician-written clinical notes. Both models performed better when signs and symptoms were represented as shorter text spans. Consistent with prior studies that examined the recognition of diseases and drugs, the model based on bidirectional encoder representations from transformers outperformed the model based on convolutional neural networks for recognizing signs and symptoms. Recall for signs and symptoms ranged from 59.5% to 82.0% and precision ranged from 61.7% to 80.4%. With further advances in NLP, fully automated recognition of signs and symptoms in electronic health records and the medical literature should be feasible.