Temporal Phenotyping Research Articles

SWoTTeD: an extension of tensor decomposition to temporal phenotyping

SWoTTeD: an extension of tensor decomposition to temporal phenotyping

Using Natural Language Processing and Patient Journey Clustering for Temporal Phenotyping of Antimicrobial Therapies for Cat Bite Abscesses

BackgroundTemporal phenotyping of patient journeys, which capture the common sequence patterns of interventions in the treatment of a specific condition, is useful to support understanding of antimicrobial usage in veterinary patients. Identifying and describing these phenotypes can inform antimicrobial stewardship programs designed to fight antimicrobial resistance, a major health crisis affecting both humans and animals, in which veterinarians have an important role to play. ObjectiveThis research proposes a framework for extracting temporal phenotypes of patient journeys from clinical practice data through the application of natural language processing (NLP) and unsupervised machine learning (ML) techniques, using cat bite abscesses as a model condition. By constructing temporal phenotypes from key events, the relationship between antimicrobial administration and surgical interventions can be described, and similar treatment patterns can be grouped together to describe outcomes associated with specific antimicrobial selection. MethodsCases identified as having a cat bite abscess as a diagnosis were extracted from VetCompass Australia, a database of veterinary clinical records. A classifier was trained and used to label the most clinically relevant event features in each record as chosen by a group of veterinarians. The labeled records were processed into coded character strings, where each letter represents a summary of specific types of treatments performed at a given visit. The sequences of letters representing the cases were clustered based on weighted Levenshtein edit distances with KMeans++ to identify the main variations of the patient treatment journeys, including the antimicrobials used and their duration of administration. ResultsA total of 13,744 records that met the selection criteria was extracted and grouped into 8,436 cases. There were 9 clinically distinct event sequence patterns (temporal phenotypes) of patient journeys identified, representing the main sequences in which surgery and antimicrobial interventions are performed. Patients receiving amoxicillin and surgery had the shortest duration of antimicrobial administration (median of 3.4 days) and patients receiving cefovecin with no surgical intervention had the longest antimicrobial treatment duration (median of 27 days). ConclusionOur study demonstrates methods to extract and provide an overview of temporal phenotypes of patient journeys, which can be applied to text-based clinical records for multiple species or clinical conditions. We demonstrate the effectiveness of this approach to derive real-world evidence of treatment impacts using cat bite abscesses as a model condition to describe patterns of antimicrobial therapy prescriptions and their outcomes.

Temporal Phenotyping for End-Stage Renal Disease Using Longitudinal Electronic Health Records.

End Stage Renal Disease (ESRD) is a highly heterogeneous disease with significant differences in prevalence, mortality, complications, and treatment modalities across age, sex, race, and ethnicity. An improved knowledge of disease characteristics results from the use of a data-driven phenotypic classification strategy to identify patients of different subtypes and expose the clinical traits of different subtypes. This study used topic models and process mining techniques to perform subtyping of ESRD patients on hemodialysis based on real-world longitudinal electronic health record data. The mined subtypes are interpretable and clinically significant, and they can reflect differences in the progression of the disease state and clinical outcomes.

Assessing treatment outcomes in CLAD: The Hannover-extracorporeal photopheresis model.

Chronic lung allograft dysfunction (CLAD) is a leading cause of graft loss in lung transplantation. Despite this, convincing treatment data is lacking, and protocols vary widely between centers. CLAD phenotypes exist, but phenotype transitioning has increased the challenge of designing clinically relevant studies. Extracorporeal photopheresis (ECP) has long been a suggested salvage treatment, but efficacy appears unpredictable. This study describes our experiences with photopheresis, using novel temporal phenotyping to illustrate the clinical course. Retrospective analysis of patients completing ≥3 months of ECP for CLAD between 2007 and 2022 was performed. A latent class analysis employing a mixed-effects model was performed, deriving patient subgroups based on spirometry trajectory over the 12 months prior to photopheresis until graft loss or 4 years post photopheresis initiation. The resulting temporal phenotypes were compared in terms of treatment response and survival outcomes. Linear discriminatory analysis was used to assess phenotype predictability, relying solely on data available at photopheresis initiation. Data from 5,169 outpatient attendances in 373 patients was used to construct the model. Five trajectories were identified, with uniform spirometry changes evident following 6 months of photopheresis. Outcomes were poorest in Fulminant patients (N=25, 7%) with median survival of 1 year. In the remainder, poorer lung function at initiation led to poorer outcomes. The analysis revealed important confounders, affecting both decision-making and outcome interpretation. Temporal phenotyping provided novel insights into ECP treatment response in CLAD, particularly the importance of timely intervention. Limitations in % Baseline values in guiding treatment decisions warrant further analysis. Photopheresis may have a more uniform effect than previously thought. Predicting survival at ECP initiation appears feasible.

Analyzing treatment patterns and time to the next treatment in chronic lymphocytic leukemia real-world data using automated temporal phenotyping.

e19512 Background: Targeted therapy is an important treatment for chronic lymphocytic leukemia (CLL). However, optimal strategies for deploying small molecule inhibitors or antibody therapies in the real world are not well understood, largely due to a lack of outcomes data. We implemented a novel temporal phenotyping algorithm pipeline to derive lines of therapy (LOT) and disease progression in CLL patients. Here, the CLL treatment pattern and time to the next treatment (TTNT) were analyzed in real-world data (RWD) using patient electronic health records. Methods: We identified a CLL cohort with LOT from the Mount Sinai Data Warehouse (2003-2020). Each LOT consisted of either a single agent or combinations defined by NCCN CLL guidelines. We developed a natural language processing (NLP)-based temporal phenotyping approach to automatically identify the number of lines and therapeutic regimens. The sequence of treatment and time interval for each patient were derived from the systematic treatment data. Time to event analysis and multivariate (i.e., age, gender, race, other treatment patterns) Cox proportional hazard (CoxPH) models were used to analyze the patterns and predictors of TTNT. Results: Four hundred eleven CLL patients received 1 to 7 LOTs. Ibrutinib was the predominant 1st LOT (40.8% of patients) followed by anti-CD20-based antibody therapies and chemotherapy in 30.6 and 19.2% of patients, respectively, followed by Acalabrutinib, Venetoclax, and Idelalisib in 3.4, 2.7, and 0.7% of patients, respectively (Table 1). The 2nd to 5th LOT showed the same or similar trends. We next analyzed the TTNT in the 1st line of each therapeutic class. Acalabrutinib resulted in a longer median TTNT than Ibrutinib. Both Acalabrutinib and Ibrutinib showed longer TTNT compared to Venetoclax (median TTNTs were 742 and 598 vs. 373 days: HR = 0.23, p=0.015 and HR = 0.48, p=0.03, respectively). In addition, patients with age equal to or older than 65 showed longer TNNT (HR=0.16, p=0.016). Conclusions: Our result shows the potential of RWD usage in clinical decision making as real-world evidence reported here is consistent with results derived from clinical trial data. Linking this study to genetic data and other covariates affecting treatment outcomes may provide additional insights into the optimal sequences of the targeted therapies in CLL. Table 1: Therapeutic class and patient numbers (%) in each line.[Table: see text]

Outcome-Oriented Deep Temporal Phenotyping of Disease Progression.

Chronic diseases evolve slowly throughout a patient's lifetime creating heterogeneous progression patterns that make clinical outcomes remarkably varied across individual patients. A tool capable of identifying temporal phenotypes based on the patients different progression patterns and clinical outcomes would allow clinicians to better forecast disease progression by recognizing a group of similar past patients, and to better design treatment guidelines that are tailored to specific phenotypes. To build such a tool, we propose a deep learning approach, which we refer to as outcome-oriented deep temporal phenotyping (ODTP), to identify temporal phenotypes of disease progression considering what type of clinical outcomes will occur and when based on the longitudinal observations. More specifically, we model clinical outcomes throughout a patient's longitudinal observations via time-to-event (TTE) processes whose conditional intensity functions are estimated as non-linear functions using a recurrent neural network. Temporal phenotyping of disease progression is carried out by our novel loss function that is specifically designed to learn discrete latent representations that best characterize the underlying TTE processes. The key insight here is that learning such discrete representations groups progression patterns considering the similarity in expected clinical outcomes, and thus naturally provides outcome-oriented temporal phenotypes. We demonstrate the power of ODTPby applying it to a real-world heterogeneous cohort of 11779 stage III breast cancer patients from the U.K. National Cancer Registration and Analysis Service. The experiments show that ODTPidentifies temporal phenotypes that are strongly associated with the future clinical outcomes and achieves significant gain on the homogeneity and heterogeneity measures over existing methods. Furthermore, we are able to identify the key driving factors that lead to transitions between phenotypes which can be translated into actionable information to support better clinical decision-making.

Temporal Design Patterns for Digital Phenotype Cohort Selection in Critical Care: Systematic Literature Assessment and Qualitative Synthesis.

BackgroundInclusion criteria for observational studies frequently contain temporal entities and relations. The use of digital phenotypes to create cohorts in electronic health record–based observational studies requires rich functionality to capture these temporal entities and relations. However, such functionality is not usually available or requires complex database queries and specialized expertise to build them.ObjectiveThe purpose of this study is to systematically assess observational studies reported in critical care literature to capture design requirements and functionalities for a graphical temporal abstraction-based digital phenotyping tool.MethodsWe iteratively extracted attributes describing patients, interventions, and clinical outcomes. We qualitatively synthesized studies, identifying all temporal and nontemporal entities and relations.ResultsWe extracted data from 28 primary studies and 367 temporal and nontemporal entities. We generated a synthesis of entities, relations, and design patterns.ConclusionsWe report on the observed types of clinical temporal entities and their relations as well as design requirements for a temporal abstraction-based digital phenotyping system. The results can be used to inform the development of such a system.

Learning multimorbidity patterns from electronic health records using Non-negative Matrix Factorisation

Multimorbidity, or the presence of several medical conditions in the same individual, has been increasing in the population — both in absolute and relative terms. Nevertheless, multimorbidity remains poorly understood, and the evidence from existing research to describe its burden, determinants and consequences has been limited. Previous studies attempting to understand multimorbidity patterns are often cross-sectional and do not explicitly account for multimorbidity patterns’ evolution over time; some of them are based on small datasets and/or use arbitrary and narrow age ranges; and those that employed advanced models, usually lack appropriate benchmarking and validations. In this study, we (1) introduce a novel approach for using Non-negative Matrix Factorisation (NMF) for temporal phenotyping (i.e., simultaneously mining disease clusters and their trajectories); (2) provide quantitative metrics for the evaluation of these clusters and trajectories; and (3) demonstrate how the temporal characteristics of the disease clusters that result from our model can help mine multimorbidity networks and generate new hypotheses for the emergence of various multimorbidity patterns over time. We trained and evaluated our models on one of the world’s largest electronic health records (EHR) datasets, containing more than 7 million patients, from which over 2 million where relevant to, and hence included in this study.

Using topological data analysis and pseudo time series to infer temporal phenotypes from electronic health records.

Temporal phenotyping enables clinicians to better understand observable characteristics of a disease as it progresses. Modelling disease progression that captures interactions between phenotypes is inherently challenging. Temporal models that capture change in disease over time can identify the key features that characterize disease subtypes that underpin these trajectories. These models will enable clinicians to identify early warning signs of progression in specific sub-types and therefore to make informed decisions tailored to individual patients. In this paper, we explore two approaches to building temporal phenotypes based on the topology of data: topological data analysis and pseudo time-series. Using type 2 diabetes data, we show that the topological data analysis approach is able to identify disease trajectories and that pseudo time-series can infer a state space model characterized by transitions between hidden states that represent distinct temporal phenotypes. Both approaches highlight lipid profiles as key factors in distinguishing the phenotypes.

Temporal phenotyping for transitional disease progress: An application to epilepsy and Alzheimer's disease.

Complicated multifactorial diseases deteriorate from one disease to other diseases. For example, existing studies consider Alzheimer's disease (AD) a comorbidity of epilepsy, but also recognize epilepsy to occur more frequently in patients with AD than those without. It is important to understand the progress of disease that deteriorates to severe diseases. To this end, we develop a transitional phenotyping method based on both longitudinal and cross-sectional relationships between diseases and/or medications. For a cross-sectional approach, we utilized a skip-gram model to represent co-occurred disease or medication. For a longitudinal approach, we represented each patient as a transition probability between medical events and used supervised tensor factorization to decompose into groups of medical events that develop together. Then we harmonized both information to derive high-risk transitional patterns. We applied our method to disease progress from epilepsy to AD. An epilepsy-AD cohort of 600,000 patients were extracted from Cerner Health Facts data. Our experimental results suggested a causal relationship between epilepsy and later onset of AD, and also identified five epilepsy subgroups with distinct phenotypic patterns leading to AD. While such findings are preliminary, the proposed method combining representation learning with tensor factorization seems to be an effective approach for risk factor analysis.

Temporal phenotyping by mining healthcare data to derive lines of therapy for cancer.

Lines of therapy (LOT) derived from real-world healthcare data not only depict real-world cancer treatment sequences, but also help define patient phenotypes along the course of disease progression and therapeutic interventions. The sequence of prescribed anticancer therapies can be defined as temporal phenotyping resulting from changes in morphological (tumor staging), biochemical (biomarker testing), physiological (disease progression), and behavioral (physician prescribing and patient adherence) parameters. We introduce a novel methodology that is a two-part approach: 1) create an algorithm to derive patient-level LOT and 2) aggregate LOT information via clustering to derive temporal phenotypes, in conjunction with visualization techniques, within a large insurance claims dataset. We demonstrated the methodology using two examples: metastatic non-small cell lung cancer and metastatic melanoma. First, we generated a longitudinal patient cohort for each cancer type and applied a set of rules to derive patient-level LOT. Then the LOT algorithm outputs for each cancer type were visualized using Sankey plots and K-means clusters based on durations of LOT and of gaps in therapy between LOT. We found differential distribution of temporal phenotypes across clusters. Our approach to identify temporal patient phenotypes can increase the quality and utility of analyses conducted using claims datasets, with the potential for application to multiple oncology disease areas across diverse healthcare data sources. The understanding of LOT as defining patients' temporal phenotypes can contribute to continuous health learning of disease progression and its interaction with different treatment pathways; in addition, this understanding can provide new insights that can be applied by tailoring treatment sequences for the patient phenotypes who will benefit.

A method for the graphical modeling of relative temporal constraints.

Searching for patient cohorts in electronic patient data often requires the definition of temporal constraints between the selection criteria. However, beyond a certain degree of temporal complexity, the non-graphical, form-based approaches implemented in current translational research platforms may be limited when modeling such constraints. In our opinion, there is a need for an easily accessible and implementable, fully graphical method for creating temporal queries. We aim to respond to this challenge with a new graphical notation. Based on Allen's time interval algebra, it allows for modeling temporal queries by arranging simple horizontal bars depicting symbolic time intervals. To make our approach applicable to complex temporal patterns, we apply two extensions: with duration intervals, we enable the inference about relative temporal distances between patient events, and with time interval modifiers, we support counting and excluding patient events, as well as constraining numeric values. We describe how to generate database queries from this notation. We provide a prototypical implementation, consisting of a temporal query modeling frontend and an experimental backend that connects to an i2b2 system. We evaluate our modeling approach on the MIMIC-III database to demonstrate that it can be used for modeling typical temporal phenotyping queries.

Identifying emerging phenomenon in long temporal phenotyping experiments.

The rapid improvement of phenotyping capability, accuracy and throughput have greatly increased the volume and diversity of phenomics data. A remaining challenge is an efficient way to identify phenotypic patterns to improve our understanding of the quantitative variation of complex phenotypes, and to attribute gene functions. To address this challenge, we developed a new algorithm to identify emerging phenomena from large-scale temporal plant phenotyping experiments. An emerging phenomenon is defined as a group of genotypes who exhibit a coherent phenotype pattern during a relatively short time. Emerging phenomena are highly transient and diverse, and are dependent in complex ways on both environmental conditions and development. Identifying emerging phenomena may help biologists to examine potential relationships among phenotypes and genotypes in a genetically diverse population and to associate such relationships with the change of environments or development. We present an emerging phenomenon identification tool called Temporal Emerging Phenomenon Finder (TEP-Finder). Using large-scale longitudinal phenomics data as input, TEP-Finder first encodes the complicated phenotypic patterns into a dynamic phenotype network. Then, emerging phenomena in different temporal scales are identified from dynamic phenotype network using a maximal clique based approach. Meanwhile, a directed acyclic network of emerging phenomena is composed to model the relationships among the emerging phenomena. The experiment that compares TEP-Finder with two state-of-art algorithms shows that the emerging phenomena identified by TEP-Finder are more functionally specific, robust and biologically significant. The source code, manual and sample data of TEP-Finder are all available at: http://phenomics.uky.edu/TEP-Finder/. Supplementary data are available at Bioinformatics online.

Temporal phenotyping of medically complex children via PARAFAC2 tensor factorization.

Our aim is to extract clinically-meaningful phenotypes from longitudinal electronic health records (EHRs) of medically-complex children. This is a fragile set of patients consuming a disproportionate amount of pediatric care resources but who often end up with sub-optimal clinical outcome. The rise in available electronic health records (EHRs) provide a rich data source that can be used to disentangle their complex clinical conditions into concise, clinically-meaningful groups of characteristics. We aim at identifying those phenotypes and their temporal evolution in a scalable, computational manner, which avoids the time-consuming manual chart review. We analyze longitudinal EHRs from Children's Healthcare of Atlanta including 1045 medically complex patients with a total of 59,948 encounters over 2 years. We apply a tensor factorization method called PARAFAC2 to extract: (a) clinically-meaningful groups of features (b) concise patient representations indicating the presence of a phenotype for each patient, and (c) temporal signatures indicating the evolution of those phenotypes over time for each patient. We identified four medically complex phenotypes, namely gastrointestinal disorders, oncological conditions, blood-related disorders, and neurological system disorders, which have distinct clinical characterizations among patients. We demonstrate the utility of patient representations produced by PARAFAC2, towards identifying groups of patients with significant survival variations. Finally, we showcase representative examples of the temporal phenotypic trends extracted for different patients. Unsupervised temporal phenotyping is an important task since it minimizes the burden on behalf of clinical experts, by relegating their involvement in the output phenotypes' validation. PARAFAC2 enjoys several compelling properties towards temporal computational phenotyping: (a) it is able to handle high-dimensional data and variable numbers of encounters across patients, (b) it has an intuitive interpretation and (c) it is free from ad-hoc parameter choices. Computational phenotypes, such as the ones computed by our approach, have multiple applications; we highlight three of them which are particularly useful for medically complex children: (1) integration into clinical decision support systems, (2) interpretable mortality prediction and 3) clinical trial recruitment. PARAFAC2 can be applied to unsupervised temporal phenotyping tasks where precise definitions of different phenotypes are absent, and lengths of patient records are varying.

COPA: Constrained PARAFAC2 for Sparse & Large Datasets.

PARAFAC2 has demonstrated success in modeling irregular tensors, where the tensor dimensions vary across one of the modes. An example scenario is modeling treatments across a set of patients with the varying number of medical encounters over time. Despite recent improvements on unconstrained PARAFAC2, its model factors are usually dense and sensitive to noise which limits their interpretability. As a result, the following open challenges remain: a) various modeling constraints, such as temporal smoothness, sparsity and non-negativity, are needed to be imposed for interpretable temporal modeling and b) a scalable approach is required to support those constraints efficiently for large datasets. To tackle these challenges, we propose a COnstrained PARAFAC2 (COPA) method, which carefully incorporates optimization constraints such as temporal smoothness, sparsity, and non-negativity in the resulting factors. To efficiently support all those constraints, COPA adopts a hybrid optimization framework using alternating optimization and alternating direction method of multiplier (AO-ADMM). As evaluated on large electronic health record (EHR) datasets with hundreds of thousands of patients, COPA achieves significant speedups (up to 36× faster) over prior PARAFAC2 approaches that only attempt to handle a subset of the constraints that COPA enables. Overall, our method outperforms all the baselines attempting to handle a subset of the constraints in terms of speed, while achieving the same level of accuracy. Through a case study on temporal phenotyping of medically complex children, we demonstrate how the constraints imposed by COPA reveal concise phenotypes and meaningful temporal profiles of patients. The clinical interpretation of both the phenotypes and the temporal profiles was confirmed by a medical expert.

Temporal phenotyping of circulating microparticles after trauma: a prospective cohort study

BackgroundAfter severe polytrauma the dynamic process of coagulation may deteriorate towards a trauma-induced coagulopathy (TIC) promoting a dramatic increase in morbidity and mortality. Recent evidence suggests that microparticles (MPs) play a pivotal role at the interface between cellular and plasmatic coagulation systems. However, the impact of MPs on functional coagulation has not been clarified yet in the setting of traumatic injuries. We assessed the temporal patterns of circulating MP concentrations including their cellular origin in the context of clinical presentation and global coagulation assays.MethodsBlood samples from 22 consecutive polytrauma patients (ISS ≥16) from 2015 were collected at hospital admission, after 24 and 72 h and compared to those from healthy individuals and minor injured patients with isolated extremity fractures. Flow cytometry (BD Accuri C6; Heidelberg/Germany) was used to determine MP concentrations and cellular origin using cell-specific markers (platelet derived (PDMP): CD42b+, CD61+, CD62p+; endothelial cell derived (EDMP): CD144+, CD62e+, CD144+/62e+). Results were correlated with clinical data and results from viscoelastic testing (ROTEM).ResultsTwenty two polytrauma patients (17 males, agemedian 60 yrs) with a median ISS 26.5 (IQR 14.5) were assessed. PDMP and EDMP concentrations increased significantly in polytrauma patients as compared to healthy individuals and minor injured patients. MP concentrations correlated with injury severity (CD144+: ρsp = 0.79, p < 0.001; CD42b+: ρsp = 0.61, p < 0.001). EDMP displayed a negative correlation with aPTT (CD144/62e+, ρsp = − 0.55, p < 0.05), INR (CD144/62e+, ρsp = − 0.61, p < 0.05) and ROTEM-INTEM CT (CD144/62e+, ρsp = − 0.68, p < 0.05) reflecting increased dynamics of clot formation and an overall procoagulative effect. Additionally, EDMP showed a negative association with FIBTEM values (10 min amplitude, maximum clot firmness) indicating a fibrinolytic potential.DiscussionIn a small cohort, analysing most severly injured patients, the association of increased MP levels and altered coagulation parameters could be demonstrated. However, these findings are based on correlation analysis, which do not enable causel evidence. Therefore, further in-vitro studies are needed analysing the underlying pathomechanisms.ConclusionIn conclusion, this study could demonstrate that PDMP and EDMP levels increase significantly following polytrauma correlating with injury severity. Although severe coagulopathy was not observed, EDMP levels were associated with improved coagulation parameters suggesting their essential role for regulating blood coagulation after trauma.