Conditional Disease Development extracted from Longitudinal Health Care Cohort Data using Layered Network Construction

Machine learning for administrative health records: A systematic review of techniques and applications

Machine learning provides many powerful and effective techniques for analysing heterogeneous electronic health records (EHR). Administrative Health Records (AHR) are a subset of EHR collected for administrative purposes, and the use of machine learning on AHRs is a growing subfield of EHR analytics. Existing reviews of EHR analytics emphasise that the data-modality of the EHR limits the breadth of suitable machine learning techniques, and pursuable healthcare applications. Despite emphasising the importance of data modality, the literature fails to analyse which techniques and applications are relevant to AHRs. AHRs contain uniquely well-structured, categorically encoded records which are distinct from other data-modalities captured by EHRs, and they can provide valuable information pertaining to how patients interact with the healthcare system. This paper systematically reviews AHR-based research, analysing 70 relevant studies and spanning multiple databases. We identify and analyse which machine learning techniques are applied to AHRs and which health informatics applications are pursued in AHR-based research. We also analyse how these techniques are applied in pursuit of each application, and identify the limitations of these approaches. We find that while AHR-based studies are disconnected from each other, the use of AHRs in health informatics research is substantial and accelerating. Our synthesis of these studies highlights the utility of AHRs for pursuing increasingly complex and diverse research objectives despite a number of pervading data- and technique-based limitations. Finally, through our findings, we propose a set of future research directions that can enhance the utility of AHR data and machine learning techniques for health informatics research.

Characterizing chronological accumulation of comorbidities in healthy veterans: a computational approach

Understanding patient accumulation of comorbidities can facilitate healthcare strategy and personalized preventative care. We applied a directed network graph to electronic health record (EHR) data and characterized comorbidities in a cohort of healthy veterans undergoing screening colonoscopy. The Veterans Affairs Cooperative Studies Program #380 was a prospective longitudinal study of screening and surveillance colonoscopy. We identified initial instances of three-digit ICD-9 diagnoses for participants with at least 5 years of linked EHR history (October 1999 to December 2015). For diagnoses affecting at least 10% of patients, we calculated pairwise chronological relative risk (RR). iGraph was used to produce directed graphs of comorbidities with RR > 1, as well as summary statistics, key diseases, and communities. A directed graph based on 2210 patients visualized longitudinal development of comorbidities. Top hub (preceding) diseases included ischemic heart disease, inflammatory and toxic neuropathy, and diabetes. Top authority (subsequent) diagnoses were acute kidney failure and hypertensive chronic kidney failure. Four communities of correlated comorbidities were identified. Close analysis of top hub and authority diagnoses demonstrated known relationships, correlated sequelae, and novel hypotheses. Directed network graphs portray chronologic comorbidity relationships. We identified relationships between comorbid diagnoses in this aging veteran cohort. This may direct healthcare prioritization and personalized care.

Decompression of Multimorbidity Along the Disease Trajectories of Diabetes Mellitus Patients

Multimorbidity, the presence of two or more diseases in a patient, is maybe the greatest health challenge for the aging populations of many high-income countries. One of the main drivers of multimorbidity is diabetes mellitus (DM) due to its large number of risk factors and complications. Yet, we currently have very limited understanding of how to quantify multimorbidity beyond a simple counting of diseases and thereby inform prevention and intervention strategies tailored to the needs of elderly DM patients. Here, we conceptualize multimorbidity as typical temporal progression patterns of multiple diseases, so-called trajectories, and develop a framework to perform a matched and sex-specific comparison between DM and non-diabetic patients. We find that these disease trajectories can be organized into a multi-level hierarchy in which DM patients progress from relatively healthy states with low mortality to high-mortality states characterized by cardiovascular diseases, chronic lower respiratory diseases, renal failure, and different combinations thereof. The same disease trajectories can be observed in non-diabetic patients, however, we find that DM patients typically progress at much higher rates along their trajectories. Comparing male and female DM patients, we find a general tendency that females progress faster toward high multimorbidity states than males, in particular along trajectories that involve obesity. Males, on the other hand, appear to progress faster in trajectories that combine heart diseases with cerebrovascular diseases. Our results show that prevention and efficient management of DM are key to achieve a compression of morbidity into higher patient ages. Multidisciplinary efforts involving clinicians as well as experts in machine learning and data visualization are needed to better understand the identified disease trajectories and thereby contribute to solving the current multimorbidity crisis in healthcare.

How Specialist Aftercare Impacts Long-Term Readmission Risks in Elderly Patients With Metabolic, Cardiac, and Chronic Obstructive Pulmonary Diseases: Cohort Study Using Administrative Data

BACKGROUND

The health state of elderly patients is typically characterized by multiple co-occurring diseases requiring the involvement of several types of health care providers.

OBJECTIVE

We aimed to quantify the benefit for multimorbid patients from seeking specialist care in terms of long-term readmission risks.

METHODS

From an administrative database, we identified 225,238 elderly patients with 97 different diagnosis (ICD-10 codes) from hospital stays and contact with 13 medical specialties. For each diagnosis associated with the first hospital stay, we used multiple logistic regression analysis to quantify the sex-specific and age-adjusted long-term all-cause readmission risk (hospitalizations occurring between 3 months and 3 years after the first admission) and how specialist contact impacts these risks.

RESULTS

Men have a higher readmission risk than women (mean difference over all first diagnoses 1.9%, P<.001), but similar reduction in readmission risk after receiving specialist care. Specialist care can reduce readmission risk by almost 50%. We found the greatest reductions in risk when the first hospital stay was associated with diagnoses corresponding to complex chronic diseases such as acute myocardial infarction (57.6% reduction in readmission risk, SE 7.6% for men [m]; 55.9% reduction, SE 9.8% for women [w]), diabetic and other retinopathies (m: 62.3%, SE 8.0; w: 60.1%, SE 8.4%), chronic obstructive pulmonary disease (m: 63.9%, SE 7.8%; w: 58.1%, SE 7.5%), disorders of lipoprotein metabolism (m: 64.7%, SE 3.7%; w: 63.8%, SE 4.0%), and chronic ischemic heart diseases (m: 63.6%, SE 3.1%; w: 65.4%, SE 3.0%).

CONCLUSIONS

Specialist care can greatly reduce long-term readmission risk for patients with chronic and multimorbid diseases. Further research is needed to identify the specific reasons for these findings and to understand the detected sex-specific differences.

Unveiling new disease, pathway, and gene associations via multi-scale neural network

Diseases involve complex modifications to the cellular machinery. The gene expression profile of the affected cells contains characteristic patterns linked to a disease. Hence, new biological knowledge about a disease can be extracted from these profiles, improving our ability to diagnose and assess disease risks. This knowledge can be used for drug re-purposing, or by physicians to evaluate a patient’s condition and co-morbidity risk. Here, we consider differential gene expressions obtained by microarray technology for patients diagnosed with various diseases. Based on these data and cellular multi-scale organization, we aim at uncovering disease–disease, disease–gene and disease–pathway associations. We propose a neural network with structure based on the multi-scale organization of proteins in a cell into biological pathways. We show that this model is able to correctly predict the diagnosis for the majority of patients. Through the analysis of the trained model, we predict disease–disease, disease–pathway, and disease–gene associations and validate the predictions by comparisons to known interactions and literature search, proposing putative explanations for the predictions.

High-risk multimorbidity patterns on the road to cardiovascular mortality

BACKGROUND

Multimorbidity, the co-occurrence of two or more diseases in one patient, is a frequent phenomenon. Understanding how different diseases condition each other over the lifetime of a patient could significantly contribute to personalised prevention efforts. However, most of our current knowledge on the long-term development of the health of patients (their disease trajectories) is either confined to narrow time spans or specific (sets of) diseases. Here, we aim to identify decisive events that potentially determine the future disease progression of patients.

METHODS

Health states of patients are described by algorithmically identified multimorbidity patterns (groups of included or excluded diseases) in a population-wide analysis of 9,000,000 patient histories of hospital diagnoses observed over 17 years. Over time, patients might acquire new diagnoses that change their health state; they describe a disease trajectory. We measure the age- and sex-specific risks for patients that they will acquire certain sets of diseases in the future depending on their current health state.

RESULTS

In the present analysis, the population is described by a set of 132 different multimorbidity patterns. For elderly patients, we find 3 groups of multimorbidity patterns associated with low (yearly in-hospital mortality of 0.2-0.3%), medium (0.3-1%) and high in-hospital mortality (2-11%). We identify combinations of diseases that significantly increase the risk to reach the high-mortality health states in later life. For instance, in men (women) aged 50-59 diagnosed with diabetes and hypertension, the risk for moving into the high-mortality region within 1 year is increased by the factor of 1.96 ± 0.11 (2.60 ± 0.18) compared with all patients of the same age and sex, respectively, and by the factor of 2.09 ± 0.12 (3.04 ± 0.18) if additionally diagnosed with metabolic disorders.

CONCLUSIONS

Our approach can be used both to forecast future disease burdens, as well as to identify the critical events in the careers of patients which strongly determine their disease progression, therefore constituting targets for efficient prevention measures. We show that the risk for cardiovascular diseases increases significantly more in females than in males when diagnosed with diabetes, hypertension and metabolic disorders.

Association networks in a matched case-control design - Co-occurrence patterns of preexisting chronic medical conditions in patients with major depression versus their matched controls

OBJECTIVE

We present a method for comparing association networks in a matched case-control design, which provides a high-level comparison of co-occurrence patterns of features after adjusting for confounding factors. We demonstrate this approach by examining the differential distribution of chronic medical conditions in patients with major depressive disorder (MDD) compared to the distribution of these conditions in their matched controls.

MATERIALS AND METHODS

Newly diagnosed MDD patients were matched to controls based on their demographic characteristics, socioeconomic status, place of residence, and healthcare service utilization in the Korean National Health Insurance Service's National Sample Cohort. Differences in the networks of chronic medical conditions in newly diagnosed MDD cases treated with antidepressants, and their matched controls, were prioritized with a permutation test accounting for the false discovery rate. Sensitivity analyses for the associations between prioritized pairs of chronic medical conditions and new MDD diagnosis were performed with regression modeling.

RESULTS

By comparing the association networks of chronic medical conditions in newly diagnosed depression patients and their matched controls, five pairs of such conditions were prioritized among 105 possible pairs after controlling the false discovery rate at 5%. In sensitivity analyses using regression modeling, four out of the five prioritized pairs were statistically significant for the interaction terms.

CONCLUSION

Association networks in a matched case-control design can provide a high-level comparison of comorbid features after adjusting for confounding factors, thereby supplementing traditional clinical study approaches. We demonstrate the differential co-occurrence pattern of chronic medical conditions in patients with MDD and prioritize the chronic conditions that have statistically significant interactions in regression models for depression.

Predictive Modeling of the Progression of Alzheimer's Disease with Recurrent Neural Networks

The number of service visits of Alzheimer's disease (AD) patients is different from each other and their visit time intervals are non-uniform. Although the literature has revealed many approaches in disease progression modeling, they fail to leverage these time-relevant part of patients' medical records in predicting disease's future status. This paper investigates how to predict the AD progression for a patient's next medical visit through leveraging heterogeneous medical data. Data provided by the National Alzheimer's Coordinating Center includes 5432 patients with probable AD from August 31, 2005 to May 25, 2017. Long short-term memory recurrent neural networks (RNN) are adopted. The approach relies on an enhanced "many-to-one" RNN architecture to support the shift of time steps. Hence, the approach can deal with patients' various numbers of visits and uneven time intervals. The results show that the proposed approach can be utilized to predict patients' AD progressions on their next visits with over 99% accuracy, significantly outperforming classic baseline methods. This study confirms that RNN can effectively solve the AD progression prediction problem by fully leveraging the inherent temporal and medical patterns derived from patients' historical visits. More promisingly, the approach can be customarily applied to other chronic disease progression problems.

Risk and temporal order of disease diagnosis of comorbidities in patients with COPD: a population health perspective

Introduction

Comorbidities in patients with chronic obstructive pulmonary disease (COPD) generate a major burden on healthcare. Identification of cost-effective strategies aiming at preventing and enhancing management of comorbid conditions in patients with COPD requires deeper knowledge on epidemiological patterns and on shared biological pathways explaining co-occurrence of diseases.

Methods

The study assesses the co-occurrence of several chronic conditions in patients with COPD using two different datasets: Catalan Healthcare Surveillance System (CHSS) (ES, 1.4 million registries) and Medicare (USA, 13 million registries). Temporal order of disease diagnosis was analysed in the CHSS dataset.

Results

The results demonstrate higher prevalence of most of the diseases, as comorbid conditions, in elderly (>65) patients with COPD compared with non-COPD subjects, an effect observed in both CHSS and Medicare datasets. Analysis of temporal order of disease diagnosis showed that comorbid conditions in elderly patients with COPD tend to appear after the diagnosis of the obstructive disease, rather than before it.

Conclusion

The results provide a population health perspective of the comorbidity challenge in patients with COPD, indicating the increased risk of developing comorbid conditions in these patients. The research reinforces the need for novel approaches in the prevention and management of comorbidities in patients with COPD to effectively reduce the overall burden of the disease on these patients.

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

Objective

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

Materials and Methods

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

Results

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

Discussion

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

From comorbidities of chronic obstructive pulmonary disease to identification of shared molecular mechanisms by data integration

Background

Deep mining of healthcare data has provided maps of comorbidity relationships between diseases. In parallel, integrative multi-omics investigations have generated high-resolution molecular maps of putative relevance for understanding disease initiation and progression. Yet, it is unclear how to advance an observation of comorbidity relations (one disease to others) to a molecular understanding of the driver processes and associated biomarkers.

Results

Since Chronic Obstructive Pulmonary disease (COPD) has emerged as a central hub in temporal comorbidity networks, we developed a systematic integrative data-driven framework to identify shared disease-associated genes and pathways, as a proxy for the underlying generative mechanisms inducing comorbidity. We integrated records from approximately 13 M patients from the Medicare database with disease-gene maps that we derived from several resources including a semantic-derived knowledge-base. Using rank-based statistics we not only recovered known comorbidities but also discovered a novel association between COPD and digestive diseases. Furthermore, our analysis provides the first set of COPD co-morbidity candidate biomarkers, including IL15, TNF and JUP, and characterizes their association to aging and life-style conditions, such as smoking and physical activity.

Conclusions

The developed framework provides novel insights in COPD and especially COPD co-morbidity associated mechanisms. The methodology could be used to discover and decipher the molecular underpinning of other comorbidity relationships and furthermore, allow the identification of candidate co-morbidity biomarkers.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1291-3) contains supplementary material, which is available to authorized users.