Advancing specificity in delirium: The delirium subtyping initiative

BACKGROUND

Delirium, a common syndrome with heterogeneous etiologies and clinical presentations, is associated with poor long-term outcomes. Recording and analyzing all delirium equally could be hindering the field's understanding of pathophysiology and identification of targeted treatments. Current delirium subtyping methods reflect clinically evident features but likely do not account for underlying biology.

METHODS

The Delirium Subtyping Initiative (DSI) held three sessions with an international panel of 25 experts.

RESULTS

Meeting participants suggest further characterization of delirium features to complement the existing Diagnostic and Statistical Manual of Mental Disorders Fifth Edition Text Revision diagnostic criteria. These should span the range of delirium-spectrum syndromes and be measured consistently across studies. Clinical features should be recorded in conjunction with biospecimen collection, where feasible, in a standardized way, to determine temporal associations of biology coincident with clinical fluctuations.

DISCUSSION

The DSI made recommendations spanning the breadth of delirium research including clinical features, study planning, data collection, and data analysis for characterization of candidate delirium subtypes.

HIGHLIGHTS

Delirium features must be clearly defined, standardized, and operationalized. Large datasets incorporating both clinical and biomarker variables should be analyzed together. Delirium screening should incorporate communication and reasoning.

Joint Modeling of Social Determinants and Clinical Factors to Define Subphenotypes in Out-of-Hospital Cardiac Arrest Survival: Cluster Analysis

Background

Machine learning clustering offers an unbiased approach to better understand the interactions of complex social and clinical variables via integrative subphenotypes, an approach not studied in out-of-hospital cardiac arrest (OHCA).

Objective

We conducted a cluster analysis for a cohort of OHCA survivors to examine the association of clinical and social factors for mortality at 1 year.

Methods

We used a retrospective observational OHCA cohort identified from Medicare claims data, including area-level social determinants of health (SDOH) features and hospital-level data sets. We applied k-means clustering algorithms to identify subphenotypes of beneficiaries who had survived an OHCA and examined associations of outcomes by subphenotype.

Results

We identified 27,028 unique beneficiaries who survived to discharge after OHCA. We derived 4 distinct subphenotypes. Subphenotype 1 included a distribution of more urban, female, and Black beneficiaries with the least robust area-level SDOH measures and the highest 1-year mortality (2375/4417, 53.8%). Subphenotype 2 was characterized by a greater distribution of male, White beneficiaries and had the strongest zip code-level SDOH measures, with 1-year mortality at 49.9% (4577/9165). Subphenotype 3 had the highest rates of cardiac catheterization at 34.7% (1342/3866) and the greatest distribution with a driving distance to the index OHCA hospital from their primary residence >16.1 km at 85.4% (8179/9580); more were also discharged to a skilled nursing facility after index hospitalization. Subphenotype 4 had moderate median household income at US $51,659.50 (IQR US $41,295 to $67,081) and moderate to high median unemployment at 5.5% (IQR 4.2%-7.1%), with the lowest 1-year mortality (1207/3866, 31.2%). Joint modeling of these features demonstrated an increased hazard of death for subphenotypes 1 to 3 but not for subphenotype 4 when compared to reference.

Conclusions

We identified 4 distinct subphenotypes with differences in outcomes by clinical and area-level SDOH features for OHCA. Further work is needed to determine if individual or other SDOH domains are specifically tied to long-term survival after OHCA.

Machine learning for risk stratification in kidney disease

PURPOSE OF REVIEW

Risk stratification for chronic kidney is becoming increasingly important as a clinical tool for both treatment and prevention measures. The goal of this review is to identify how machine learning tools contribute and facilitate risk stratification in the clinical setting.

RECENT FINDINGS

The two key machine learning paradigms to predictively stratify kidney disease risk are genomics-based and electronic health record based approaches. These methods can provide both quantitative information such as relative risk and qualitative information such as characterizing risk by subphenotype.

SUMMARY

The four key methods to stratify chronic kidney disease risk are genomics, multiomics, supervised and unsupervised machine learning methods. Polygenic risk scores utilize whole genome sequencing data to generate an individual's relative risk compared with the population. Multiomic methods integrate information from multiple biomarkers to generate trajectories and prognostic different outcomes. Supervised machine learning methods can directly utilize the growing compendia of electronic health records such as laboratory results and notes to generate direct risk predictions, while unsupervised machine learning methods can cluster individuals with chronic kidney disease into subphenotypes with differing approaches to care.

Differentiation of Pediatric-Onset Duchenne and Becker Muscular Dystrophy Subphenotypes Using Data from the Muscular Dystrophy Surveillance Tracking and Research Network (MD STARnet)

Duchenne muscular dystrophy (DMD) and Becker muscular dystrophy (BMD) phenotypes are used to describe disease progression in affected individuals. However, considerable heterogeneity has been observed across and within these two phenotypes, suggesting a spectrum of severity rather than distinct conditions. Characterizing the phenotypes and subphenotypes aids researchers in the design of clinical studies and clinicians in providing anticipatory guidance to affected individuals and their families. Using data from the Muscular Dystrophy Surveillance, Tracking, and Research Network (MD STARnet), we used K-means cluster analysis to group phenotypically similar males with pediatric-onset dystrophinopathy. We identified four dystrophinopathy clusters: Classical BMD, Classical DMD, late ambulatory DMD, and severe DMD. The clusters that we identified align with both 'classical' and 'non-classical' dystrophinopathy described in the literature. Individuals with dystrophinopathies have heterogenous clinical presentations that cluster into phenotypically similar groups. Use of clinically-derived phenotyping may provide a clearer understanding of disease trajectories, reduce variability in study results, and prevent exclusion of certain cohorts from analysis. Findings from studying subphenotypes may ultimately improve our ability to predict disease progression.

Association of the novel susceptible locus rs9266150 with clinical features of psoriasis vulgaris in the Chinese Han population

Psoriasis is a chronic multifactorial disease and is considered to be strongly associated with the major histocompatibility complex (MHC) region. We have discovered an independent, novel and susceptible psoriasis risk HLA loci, rs9266150; P = 4.52 × 10^-9 for the first time. In this study, we aimed to verify the relationship between the susceptible locus and the subphenotypes of psoriasis vulgaris (PV), including geographic location, gender, age of onset, family history and present skin lesion types (chronic plaque and guttate). To investigate the distribution and association of the rs9266150 gene with clinical phenotypes of PV in Chinese Han population, we conducted an analysis in case-control and case-only subjects in the 9906 controls and 8744 cases by MHC targeted sequencing stratified analysis in this study. Significant associations were found with a northern geographic location in the case-only (P = 1.97 × 10^-4 ) and the subphenotype-control analyses (P = 5.57 × 10^-5 ), males in the case-only (P = 4.77 × 10^-3 ) and the subphenotype-control analyses (P = 7.31 × 10^-4 ), and guttate psoriasis in the case-only (P = 4.08 × 10^-3 ) and the subphenotype-control analyses (P = 1.27 × 10^-3 ). There were no significant differences observed between the age of onset (OR = 1.062, 95% CI: 0.9725-1.16, P = 1.8 × 10^-1 ) and the family history of psoriasis (OR = 0.981, 95% CI: 0.9048-1.064, P = 6.43 × 10^-1 ). The recessive model provided the best fit for rs9266150 (P = 4.38 × 10^-7 ). Our results implied that rs9266150 might not only play an important role in the development of psoriasis, but also be positively associated with the geographic location, gender and present skin lesion in the Chinese population.

Acute Respiratory Distress Syndrome Subphenotypes Respond Differently to Randomized Fluid Management Strategy

RATIONALE

We previously identified two acute respiratory distress syndrome (ARDS) subphenotypes in two separate randomized controlled trials with differential response to positive end-expiratory pressure.

OBJECTIVES

To identify these subphenotypes in a third ARDS cohort, to test whether subphenotypes respond differently to fluid management strategy, and to develop a practical model for subphenotype identification.

METHODS

We used latent class analysis of baseline clinical and plasma biomarker data to identify subphenotypes in FACTT (Fluid and Catheter Treatment Trial; n = 1,000). Logistic regression was used to test for an interaction between subphenotype and treatment for mortality. We used stepwise modeling to generate a model for subphenotype identification in FACTT and validated its accuracy in the two cohorts in which we previously identified ARDS subphenotypes.

MEASUREMENTS AND MAIN RESULTS

We confirmed that a two-class (two-subphenotype) model best described the study population. Subphenotype 2 was again characterized by higher inflammatory biomarkers and hypotension. Fluid management strategy had significantly different effects on 90-day mortality in the two subphenotypes (P = 0.0039 for interaction); mortality in subphenotype 1 was 26% with fluid-liberal strategy versus 18% with fluid-conservative, whereas mortality in subphenotype 2 was 40% with fluid-liberal strategy versus 50% in fluid-conservative. A three-variable model of IL-8, bicarbonate, and tumor necrosis factor receptor-1 accurately classified the subphenotypes.

CONCLUSIONS

This analysis confirms the presence of two ARDS subphenotypes that can be accurately identified with a limited number of variables and that responded differently to randomly assigned fluid management. These findings support the presence of ARDS subtypes that may require different treatment approaches.

Functional outcome in major psychiatric disorders and associated clinical and psychosocial variables: A potential cross-diagnostic phenotype for further genetic investigations?

OBJECTIVES

Functional outcome has recently become of interest for cross-diagnostic subphenotype approaches in psychiatric genetics. Therefore, it is crucial to know about clinical, demographic and psychosocial variables that correlate with long-term functioning. Unfortunately, there is a lack of studies that directly compare the importance of correlates for functional outcome between different disorders.

METHODS

Applying regression models to samples of patients with schizophrenia (SZ, n = 238), bipolar disorder (BD, n = 533) and major depressive disorder (MDD, n = 398), we compared the magnitude of association of potential correlates with functional outcome, measured by the Global Assessment of Functioning (GAF) score.

RESULTS

Shared correlates for worse functional outcome were poor premorbid functioning, insidious illness onset and poor premorbid work or social adjustment in all three disorders, and negative symptomatology in SZ and BD. Disorder-specific correlates for SZ were longer duration of illness, lower functioning during episodes and being life-time single, for BD substance abuse and suicidality, and for MDD premorbid unemployment and having a premorbid personality disorder.

CONCLUSIONS

We found different patterns of correlates for long-term functioning in SZ, BD and MDD. Knowledge of these patterns may improve the quality of genetic investigations focussing on functional outcome.

A multiclass likelihood ratio approach for genetic risk prediction allowing for phenotypic heterogeneity

The translation of human genome discoveries into health practice is one of the major challenges in the coming decades. The use of emerging genetic knowledge for early disease prediction, prevention, and pharmacogenetics will advance genome medicine and lead to more effective prevention/treatment strategies. For this reason, studies to assess the combined role of genetic and environmental discoveries in early disease prediction represent high priority research projects, as manifested in the multiple risk prediction studies now underway. However, the risk prediction models formed to date lack sufficient accuracy for clinical use. Converging evidence suggests that diseases with the same or similar clinical manifestations could have different pathophysiological and etiological processes. When heterogeneous subphenotypes are treated as a single entity, the effect size of predictors can be reduced substantially, leading to a low-accuracy risk prediction model. The use of more refined subphenotypes facilitates the identification of new predictors and leads to improved risk prediction models. To account for the phenotypic heterogeneity, we have developed a multiclass likelihood-ratio approach, which simultaneously determines the optimum number of subphenotype groups and builds a risk prediction model for each group. Simulation results demonstrated that the new approach had more accurate and robust performance than existing approaches under various underlying disease models. The empirical study of type II diabetes (T2D) by using data from the Genes and Environment Initiatives suggested heterogeneous etiology underlying obese and nonobese T2D patients. Considering phenotypic heterogeneity in the analysis leads to improved risk prediction models for both obese and nonobese T2D subjects.

Genome-wide significant association between a 'negative mood delusions' dimension in bipolar disorder and genetic variation on chromosome 3q26.1

Research suggests that clinical symptom dimensions may be more useful in delineating the genetics of bipolar disorder (BD) than standard diagnostic models. To date, no study has applied this concept to data from genome-wide association studies (GWAS). We performed a GWAS of factor dimensions in 927 clinically well-characterized BD patients of German ancestry. Rs9875793, which is located in an intergenic region of 3q26.1 and in the vicinity of the solute carrier family 2 (facilitated glucose transporter), member 2 gene (SLC2A2), was significantly associated with the factor analysis-derived dimension 'negative mood delusions' (n=927; P=4.65 × 10(-8), odds ratio (OR)=2.66). This dimension was comprised of the symptoms delusions of poverty, delusions of guilt and nihilistic delusions. In case-control analyses, significant association with the G allele of rs9875793 was only observed in the subgroup of BD patients who displayed symptoms of 'negative mood delusions' (allelic χ(2) model: P(G)=0.0001, OR=1.92; item present, n=89). Further support for the hypothesis that rs9875793 is associated with BD in patients displaying 'negative mood delusions' symptom, such as delusions of guilt, was obtained from an European American sample (GAIN/TGEN), which included 1247 BD patients and 1434 controls (P(EA)=0.028, OR=1.27).