Temporal electronic phenotyping by mining careflows of breast cancer patients

A novel method leveraging time series data to improve subphenotyping and application in critically ill patients with COVID-19

Computational subphenotyping, a data-driven approach to understanding disease subtypes, is a prominent topic in medical research. Numerous ongoing studies are dedicated to developing advanced computational subphenotyping methods for cross-sectional data. However, the potential of time-series data has been underexplored until now. Here, we propose a Multivariate Levenshtein Distance (MLD) that can account for address correlation in multiple discrete features over time-series data. Our algorithm has two distinct components: it integrates an optimal threshold score to enhance the sensitivity in discriminating between pairs of instances, and the MLD itself. We have applied the proposed distance metrics on the k-means clustering algorithm to derive temporal subphenotypes from time-series data of biomarkers and treatment administrations from 1039 critically ill patients with COVID-19 and compare its effectiveness to standard methods. In conclusion, the Multivariate Levenshtein Distance metric is a novel method to quantify the distance from multiple discrete features over time-series data and demonstrates superior clustering performance among competing time-series distance metrics.

Is it possible to automate the discovery of process maps for the time-driven activity-based costing method? A systematic review

OBJECTIVES

The main objective of this manuscript was to identify the methods used to create process maps for care pathways that utilized the time-driven activity-based costing method.

METHODS

This is a systematic mapping review. Searches were performed in the Embase, PubMed, CINAHL, Scopus, and Web of Science electronic literature databases from 2004 to September 25, 2022. The included studies reported practical cases from healthcare institutions in all medical fields as long as the time-driven activity-based costing method was employed. We used the time-driven activity-based costing method and analyzed the created process maps and a qualitative approach to identify the main fields.

RESULTS

A total of 412 studies were retrieved, and 70 articles were included. Most of the articles are related to the fields of orthopedics and childbirth-related to hospital surgical procedures. We also identified various studies in the field of oncology and telemedicine services. The main methods for creating the process maps were direct observational practices, complemented by the involvement of multidisciplinary teams through surveys and interviews. Only 33% of the studies used hospital documents or healthcare data records to integrate with the process maps, and in 67% of the studies, the created maps were not validated by specialists.

CONCLUSIONS

The application of process mining techniques effectively automates models generated through clinical pathways. They are applied to the time-driven activity-based costing method, making the process more agile and contributing to the visualization of high degrees of variations encountered in processes, thereby making it possible to enhance and achieve continual improvements in processes.

Analytical methods for identifying sequences of utilization in health data: a scoping review

BACKGROUND

Healthcare, as with other sectors, has undergone progressive digitalization, generating an ever-increasing wealth of data that enables research and the analysis of patient movement. This can help to evaluate treatment processes and outcomes, and in turn improve the quality of care. This scoping review provides an overview of the algorithms and methods that have been used to identify care pathways from healthcare utilization data.

METHOD

This review was conducted according to the methodology of the Joanna Briggs Institute and the Preferred Reporting Items for Systematic Reviews Extension for Scoping Reviews (PRISMA-ScR) Checklist. The PubMed, Web of Science, Scopus, and EconLit databases were searched and studies published in English between 2000 and 2021 considered. The search strategy used keywords divided into three categories: the method of data analysis, the requirement profile for the data, and the intended presentation of results. Criteria for inclusion were that health data were analyzed, the methodology used was described and that the chronology of care events was considered. In a two-stage review process, records were reviewed by two researchers independently for inclusion. Results were synthesized narratively.

RESULTS

The literature search yielded 2,865 entries; 51 studies met the inclusion criteria. Health data from different countries ([Formula: see text]) and of different types of disease ([Formula: see text]) were analyzed with respect to different care events. Applied methods can be divided into those identifying subsequences of care and those describing full care trajectories. Variants of pattern mining or Markov models were mostly used to extract subsequences, with clustering often applied to find care trajectories. Statistical algorithms such as rule mining, probability-based machine learning algorithms or a combination of methods were also applied. Clustering methods were sometimes used for data preparation or result compression. Further characteristics of the included studies are presented.

CONCLUSION

Various data mining methods are already being applied to gain insight from health data. The great heterogeneity of the methods used shows the need for a scoping review. We performed a narrative review and found that clustering methods currently dominate the literature for identifying complete care trajectories, while variants of pattern mining dominate for identifying subsequences of limited length.

A process mining approach for clinical guidelines compliance: real-world application in rectal cancer

In the era of evidence-based medicine, several clinical guidelines were developed, supporting cancer management from diagnosis to treatment and aiming to optimize patient care and hospital resources. Nevertheless, individual patient characteristics and organizational factors may lead to deviations from these standard recommendations during clinical practice. In this context, process mining in healthcare constitutes a valid tool to evaluate conformance of real treatment pathways, extracted from hospital data warehouses as event log, to standard clinical guidelines, translated into computer-interpretable formats. In this study we translate the European Society of Medical Oncology guidelines for rectal cancer treatment into a computer-interpretable format using Pseudo-Workflow formalism (PWF), a language already employed in pMineR software library for Process Mining in Healthcare. We investigate the adherence of a real-world cohort of rectal cancer patients treated at Fondazione Policlinico Universitario A. Gemelli IRCCS, data associated with cancer diagnosis and treatment are extracted from hospital databases in 453 patients diagnosed with rectal cancer. PWF enables the easy implementation of guidelines in a computer-interpretable format and visualizations that can improve understandability and interpretability of physicians. Results of the conformance checking analysis on our cohort identify a subgroup of patients receiving a long course treatment that deviates from guidelines due to a moderate increase in radiotherapy dose and an addition of oxaliplatin during chemotherapy treatment. This study demonstrates the importance of PWF to evaluate clinical guidelines adherence and to identify reasons of deviations during a treatment process in a real-world and multidisciplinary setting.

A Bayesian method for the automatic extraction of meaningful clinical sequences from large clinical databases

BACKGROUND

Clinical event recognition can have several applications, such as the examination of clinical stories that can be associated with negative hospital outcomes, or its use in clinical education to assist medical students recognize frequent clinical events.

OBJECTIVE

The purpose of this study is to develop a non-annotated Bayes-based algorithm to extract useful clinical events from medical data.

MATERIALS AND METHODS

We used subsets of MIMIC and CMS LDS datasets that include respiratory diagnoses to calculate two-itemset rules(one item in antecedent and one in consequent) which were used as building blocks for the construction of clinical event sequence order. The main condition for the event sequence is a sequential increase in the conditional probability of two-itemset rules having positive certainty factor, when they are studied together.A clinical event in our framework is defined to be a collection of several blocks of events that meet the aforementioned condition, when considered together. The correctness of our clinical sequences has been validated by two physicians.

RESULTS

Our results showed that medical experts scored the rules of this algorithm better than random Apriori rules. A GUI was designed that can be used to examine the association of each clinical event with the clinical outcomes of the length of stay, inpatient mortality, and hospital charges.

CONCLUSION

The present work provides a new approach on how we can improve extraction of clinical event sequences automatically, without user annotation. Our algorithm can successfully find, in several cases, blocks of rules which can tell correct clinical event stories.

Discovering interpretable medical process models: A case study in trauma resuscitation

Understanding the actual work (i.e., "work-as-done") rather than theorized work (i.e., "work-as-imagined") during complex medical processes is critical for developing approaches that improve patient outcomes. Although process mining has been used to discover process models from medical activity logs, it often omits critical steps or produces cluttered and unreadable models. In this paper, we introduce a TraceAlignment-based ProcessDiscovery method called TAD Miner to build interpretable process models for complex medical processes. TAD Miner creates simple linear process models using a threshold metric that optimizes the consensus sequence to represent the backbone process, and then identifies both concurrent activities and uncommon-but-critical activities to represent the side branches. TAD Miner also identifies the locations of repeated activities, an essential feature for representing medical treatment steps. We conducted a study using activity logs of 308 pediatric trauma resuscitations to develop and evaluate TAD Miner. TAD Miner was used to discover process models for five resuscitation goals, including establishing intravenous (IV) access, administering non-invasive oxygenation, performing back assessment, administering blood transfusion, and performing intubation. We quantitively evaluated the process models with several complexity and accuracy metrics, and performed qualitative evaluation with four medical experts to assess the accuracy and interpretability of the discovered models. Through these evaluations, we compared the performance of our method to that of two state-of-the-art process discovery algorithms: Inductive Miner and Split Miner. The process models discovered by TAD Miner had lower complexity and better interpretability than the state-of-the-art methods, and the fitness and precision of the models were comparable. We used the TAD process models to identify (1) the errors and (2)the best locations for the tentative steps in knowledge-driven expert models. The knowledge-driven models were revised based on the modifications suggested by the discovered models. The improved modeling using TAD Miner may enhance understanding of complex medical processes.

A Process Mining Pipeline to Characterize COVID-19 Patients' Trajectories and Identify Relevant Temporal Phenotypes From EHR Data

The impact of the COVID-19 pandemic involved the disruption of the processes of care and the need for immediately effective re-organizational procedures. In the context of digital health, it is of paramount importance to determine how a specific patients' population reflects into the healthcare dynamics of the hospital, to investigate how patients' sub-group/strata respond to the different care processes, in order to generate novel hypotheses regarding the most effective healthcare strategies. We present an analysis pipeline based on the heterogeneous collected data aimed at identifying the most frequent healthcare processes patterns, jointly analyzing them with demographic and physiological disease trajectories, and stratify the observed cohort on the basis of the mined patterns. This is a process-oriented pipeline which integrates process mining algorithms, and trajectory mining by topological data analyses and pseudo time approaches. Data was collected for 1,179 COVID-19 positive patients, hospitalized at the Italian Hospital “Istituti Clinici Salvatore Maugeri” in Lombardy, integrating different sources including text admission letters, EHR and hospital infrastructure data. We identified five temporal phenotypes, from laboratory values trajectories, which are characterized by statistically significant different death risk estimates. The process mining algorithms allowed splitting the data in sub-cohorts as function of the pandemic waves and of the temporal trajectories showing statistically significant differences in terms of events characteristics.

Clinical and operational insights from data-driven care pathway mapping: a systematic review

Background

Accumulated electronic data from a wide variety of clinical settings has been processed using a range of informatics methods to determine the sequence of care activities experienced by patients. The “as is” or “de facto” care pathways derived can be analysed together with other data to yield clinical and operational information. It seems likely that the needs of both health systems and patients will lead to increasing application of such analyses. A comprehensive review of the literature is presented, with a focus on the study context, types of analysis undertaken, and the utility of the information gained.

Methods

A systematic review was conducted of literature abstracting sequential patient care activities (“de facto” care pathways) from care records. Broad coverage was achieved by initial screening of a Scopus search term, followed by screening of citations (forward snowball) and references (backwards snowball). Previous reviews of related topics were also considered. Studies were initially classified according to the perspective captured in the derived pathways. Concept matrices were then derived, classifying studies according to additional data used and subsequent analysis undertaken, with regard for the clinical domain examined and the knowledge gleaned.

Results

254 publications were identified. The majority (n = 217) of these studies derived care pathways from data of an administrative/clinical type. 80% (n = 173) applied further analytical techniques, while 60% (n = 131) combined care pathways with enhancing data to gain insight into care processes.

Discussion

Classification of the objectives, analyses and complementary data used in data-driven care pathway mapping illustrates areas of greater and lesser focus in the literature. The increasing tendency for these methods to find practical application in service redesign is explored across the variety of contexts and research questions identified. A limitation of our approach is that the topic is broad, limiting discussion of methodological issues.

Conclusion

This review indicates that methods utilising data-driven determination of de facto patient care pathways can provide empirical information relevant to healthcare planning, management, and practice. It is clear that despite the number of publications found the topic reviewed is still in its infancy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01756-2.

A differential process mining analysis of COVID-19 management for cancer patients

During the acute phase of the COVID-19 pandemic, hospitals faced a challenge to manage patients, especially those with other comorbidities and medical needs, such as cancer patients. Here, we use Process Mining to analyze real-world therapeutic pathways in a cohort of 1182 cancer patients of the Lausanne University Hospital following COVID-19 infection. The algorithm builds trees representing sequences of coarse-grained events such as Home, Hospitalization, Intensive Care and Death. The same trees can also show probability of death or time-to-event statistics in each node. We introduce a new tool, called Differential Process Mining, which enables comparison of two patient strata in each node of the tree, in terms of hits and death rate, together with a statistical significance test. We thus compare management of COVID-19 patients with an active cancer in the first vs. second COVID-19 waves to quantify hospital adaptation to the pandemic. We also compare patients having undergone systemic therapy within 1 year to the rest of the cohort to understand the impact of an active cancer and/or its treatment on COVID-19 outcome. This study demonstrates the value of Process Mining to analyze complex event-based real-world data and generate hypotheses on hospital resource management or on clinical patient care.

Modified Needleman-Wunsch algorithm for clinical pathway clustering

Clinical pathways are used to guide clinicians to provide a standardised delivery of care. Because of their standardisation, the aim of clinical pathways is to reduce variation in both care process and patient outcomes. When learning clinical pathways from data through data mining, it is common practice to represent each patient pathway as a string corresponding to their movements through activities. Clustering techniques are popular methods for pathway mining, and therefore this paper focuses on distance metrics applied to string data for k-medoids clustering. The two main aims are to firstly, develop a technique that seamlessly integrates expert information with data and secondly, to develop a string distance metric for the purpose of process data. The overall goal was to allow for more meaningful clustering results to be found by adding context into the string similarity calculation. Eight common distance metrics and their applicability are discussed. These distance metrics prove to give an arbitrary distance, without consideration for context, and each produce different results. As a result, this paper describes the development of a new distance metric, the modified Needleman-Wunsch algorithm, that allows for expert interaction with the calculation by assigning groupings and rankings to activities, which provide context to the strings. This algorithm has been developed in partnership with UK's National Health Service (NHS) with the focus on a lung cancer pathway, however the handling of the data and algorithm allows for application to any disease type. This method is contained within Sim.Pro.Flow, a publicly available decision support tool.

Visual Analytics for Electronic Health Records: A Review

The increasing use of electronic health record (EHR)-based systems has led to the generation of clinical data at an unprecedented rate, which produces an untapped resource for healthcare experts to improve the quality of care. Despite the growing demand for adopting EHRs, the large amount of clinical data has made some analytical and cognitive processes more challenging. The emergence of a type of computational system called visual analytics has the potential to handle information overload challenges in EHRs by integrating analytics techniques with interactive visualizations. In recent years, several EHR-based visual analytics systems have been developed to fulfill healthcare experts’ computational and cognitive demands. In this paper, we conduct a systematic literature review to present the research papers that describe the design of EHR-based visual analytics systems and provide a brief overview of 22 systems that met the selection criteria. We identify and explain the key dimensions of the EHR-based visual analytics design space, including visual analytics tasks, analytics, visualizations, and interactions. We evaluate the systems using the selected dimensions and identify the gaps and areas with little prior work.

PASCAL: a pseudo cascade learning framework for breast cancer treatment entity normalization in Chinese clinical text

Backgrounds

Knowledge discovery from breast cancer treatment records has promoted downstream clinical studies such as careflow mining and therapy analysis. However, the clinical treatment text from electronic health data might be recorded by different doctors under their hospital guidelines, making the final data rich in author- and domain-specific idiosyncrasies. Therefore, breast cancer treatment entity normalization becomes an essential task for the above downstream clinical studies. The latest studies have demonstrated the superiority of deep learning methods in named entity normalization tasks. Fundamentally, most existing approaches adopt pipeline implementations that treat it as an independent process after named entity recognition, which can propagate errors to later tasks. In addition, despite its importance in clinical and translational research, few studies directly deal with the normalization task in Chinese clinical text due to the complexity of composition forms.

Methods

To address these issues, we propose PASCAL, an end-to-end and accurate framework for breast cancer treatment entity normalization (TEN). PASCAL leverages a gated convolutional neural network to obtain a representation vector that can capture contextual features and long-term dependencies. Additionally, it treats treatment entity recognition (TER) as an auxiliary task that can provide meaningful information to the primary TEN task and as a particular regularization to further optimize the shared parameters. Finally, by concatenating the context-aware vector and probabilistic distribution vector from TEN, we utilize the conditional random field layer (CRF) to model the normalization sequence and predict the TEN sequential results.

Results

To evaluate the effectiveness of the proposed framework, we employ the three latest sequential models as baselines and build the model in single- and multitask on a real-world database. Experimental results show that our method achieves better accuracy and efficiency than state-of-the-art approaches.

Conclusions

The effectiveness and efficiency of the presented pseudo cascade learning framework were validated for breast cancer treatment normalization in clinical text. We believe the predominant performance lies in its ability to extract valuable information from unstructured text data, which will significantly contribute to downstream tasks, such as treatment recommendations, breast cancer staging and careflow mining.

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

•

Topological Data and Pseudo Time Series to discover Type 2 Diabetes temporal phenotypes.

•

Temporal phenotypes inferred from state-space model based on hidden-states transitions.

•

Study of states continuous transitions visually delivered in an easily explainable way.

•

Mined phenotypes characterized by significant differences in disease deterioration.

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.

Mining post-surgical care processes in breast cancer patients

In this work we describe the application of a careflow mining algorithm to detect the most frequent patterns of care in a cohort of 3000 breast cancer patients. The applied method relies on longitudinal data extracted from electronic health records, recorded from the first surgical procedure after a breast cancer diagnosis. Careflows are mined from events data recorded for administrative purposes, including procedures from ICD9 - CM billing codes and chemotherapy treatments. Events data have been pre-processed with Topic Modelling to create composite events based on concurrent procedures. The results of the careflow mining algorithm allow the discovery of electronic temporal phenotypes across the studied population. These phenotypes are further characterized on the basis of clinical traits and tumour histopathology, as well as in terms of relapses, metastasis occurrence and 5-year survival rates. Results are highly significant from a clinical perspective, since phenotypes describe well characterized pathology classes, and the careflows are well matched with existing clinical guidelines. The analysis thus facilitates deriving real-world evidence that can inform clinicians as well as hospital decision makers.

Towards standardisation of evidence-based clinical care process specifications

There is a strong push towards standardisation of treatment approaches, care processes and documentation of clinical practice. However, confusion persists regarding terminology and description of many clinical care process specifications which this research seeks to resolve by developing a taxonomic characterisation of clinical care process specifications. Literature on clinical care process specifications was analysed, creating the starting point for identifying common characteristics and how each is constructed and used in the clinical setting. A taxonomy for clinical care process specifications is presented. The De Bleser approach to limited clinical care process specifications characterisation was extended and each clinical care process specification is successfully characterised in terms of purpose, core elements and relationship to the other clinical care process specification types. A case study on the diagnosis and treatment of Type 2 Diabetes in the United Kingdom was used to evaluate the taxonomy and demonstrate how the characterisation framework applies. Standardising clinical care process specifications ensures that the format and content are consistent with expectations, can be read more quickly and high-quality information can be recorded about the patient. Standardisation also enables computer interpretability, which is important in integrating Learning Health Systems into the modern clinical environment. The approach presented allows terminologies for clinical care process specifications that were widely used interchangeably to be easily distinguished, thus, eliminating the existing confusion.

Towards the Use of Standardized Terms in Clinical Case Studies for Process Mining in Healthcare

Process mining can provide greater insight into medical treatment processes and organizational processes in healthcare. To enhance comparability between processes, the quality of the labelled-data is essential. A literature review of the clinical case studies by Rojas et al. in 2016 identified several common aspects for comparison, which include methodologies, algorithms or techniques, medical fields, and healthcare specialty. However, clinical aspects are not reported in a uniform way and do not follow a standard clinical coding scheme. Further, technical aspects such as details of the event log data are not always described. In this paper, we identified 38 clinically-relevant case studies of process mining in healthcare published from 2016 to 2018 that described the tools, algorithms and techniques utilized, and details on the event log data. We then correlated the clinical aspects of patient encounter environment, clinical specialty and medical diagnoses using the standard clinical coding schemes SNOMED CT and ICD-10. The potential outcomes of adopting a standard approach for describing event log data and classifying medical terminology using standard clinical coding schemes are further discussed. A checklist template for the reporting of case studies is provided in the Appendix A to the article.

A dashboard-based system for supporting diabetes care

Objective

To describe the development, as part of the European Union MOSAIC (Models and Simulation Techniques for Discovering Diabetes Influence Factors) project, of a dashboard-based system for the management of type 2 diabetes and assess its impact on clinical practice.

Methods

The MOSAIC dashboard system is based on predictive modeling, longitudinal data analytics, and the reuse and integration of data from hospitals and public health repositories. Data are merged into an i2b2 data warehouse, which feeds a set of advanced temporal analytic models, including temporal abstractions, care-flow mining, drug exposure pattern detection, and risk-prediction models for type 2 diabetes complications. The dashboard has 2 components, designed for (1) clinical decision support during follow-up consultations and (2) outcome assessment on populations of interest. To assess the impact of the clinical decision support component, a pre-post study was conducted considering visit duration, number of screening examinations, and lifestyle interventions. A pilot sample of 700 Italian patients was investigated. Judgments on the outcome assessment component were obtained via focus groups with clinicians and health care managers.

Results

The use of the decision support component in clinical activities produced a reduction in visit duration (P ≪ .01) and an increase in the number of screening exams for complications (P < .01). We also observed a relevant, although nonstatistically significant, increase in the proportion of patients receiving lifestyle interventions (from 69% to 77%). Regarding the outcome assessment component, focus groups highlighted the system's capability of identifying and understanding the characteristics of patient subgroups treated at the center.

Conclusion

Our study demonstrates that decision support tools based on the integration of multiple-source data and visual and predictive analytics do improve the management of a chronic disease such as type 2 diabetes by enacting a successful implementation of the learning health care system cycle.

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 tale of three subspecialties: Diagnosis recording patterns are internally consistent but Specialty-Dependent

BACKGROUND

Structured diagnosis (DX) are crucial for secondary use of electronic health record (EHR) data. However, they are often suboptimally recorded. Our previous work showed initial evidence of variable DX recording patterns in oncology charts even after biopsy records are available.

OBJECTIVE

We verified this finding's internal and external validity. We hypothesized that this recording pattern would be preserved in a larger cohort of patients for the same disease. We also hypothesized that this effect would vary across subspecialties.

METHODS

We extracted DX data from EHRs of patients treated for brain, lung, and pancreatic neoplasms, identified through clinician-led chart reviews. We used statistical methods (i.e., binomial and mixed model regressions) to test our hypotheses.

RESULTS

We found variable recording patterns in brain neoplasm DX (i.e., larger number of distinct DX-OR = 2.2, P < 0.0001, higher descriptive specificity scores-OR = 1.4, P < 0.0001-and much higher entropy after the BX-OR = 3.8 P = 0.004 and OR = 8.0, P < 0.0001), confirming our initial findings. We also found strikingly different patterns for lung and pancreas DX. Although both seemed to have much lower DX sequence entropy after the BX-OR = 0.198, P = 0.015 and OR = 0.099, P = 0.015, respectively compared to OR = 3.8 P = 0.004). We also found statistically significant differences between the brain dataset and both the lung (P < 0.0001) and pancreas (0.009

CONCLUSION

Our results suggest that disease-specific DX entry patterns exist and are established differently by clinical subspecialty. These differences should be accounted for during clinical data reuse and data quality assessments but also during EHR entry system design to maximize accurate, precise and consistent data entry likelihood.

Collapse

Key Words

• clinical data management
• data quality
• electronic health records
• learning healthcare system
• secondary use of clinical data

Collapse

MESH Headings Collapse

Grants

• K12 GM102773 NIGMS NIH HHS
• UL1 TR001420 NCATS NIH HHS

Collapse

Affiliation(s)

Jose-Franck Diaz-Garelli Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Roy Strowd Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Tamjeed Ahmed Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Brian J Wells Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Rebecca Merrill Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Javier Laurini Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Boris Pasche Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA
Umit Topaloglu Wake Forest Baptist Medical Center, Winston Salem, North Carolina, USA

Collapse

Temporal phenotyping of medically complex children via PARAFAC2 tensor factorization

OBJECTIVE

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.

MATERIALS AND METHODS

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.

RESULTS

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.

DISCUSSION

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.

CONCLUSION

PARAFAC2 can be applied to unsupervised temporal phenotyping tasks where precise definitions of different phenotypes are absent, and lengths of patient records are varying.

Can process mining automatically describe care pathways of patients with long-term conditions in UK primary care? A study protocol

INTRODUCTION

In the UK, primary care is seen as the optimal context for delivering care to an ageing population with a growing number of long-term conditions. However, if it is to meet these demands effectively and efficiently, a more precise understanding of existing care processes is required to ensure their configuration is based on robust evidence. This need to understand and optimise organisational performance is not unique to healthcare, and in industries such as telecommunications or finance, a methodology known as 'process mining' has become an established and successful method to identify how an organisation can best deploy resources to meet the needs of its clients and customers. Here and for the first time in the UK, we will apply it to primary care settings to gain a greater understanding of how patients with two of the most common chronic conditions are managed.

METHODS AND ANALYSIS

The study will be conducted in three phases; first, we will apply process mining algorithms to the data held on the clinical management system of four practices of varying characteristics in the West Midlands to determine how each interacts with patients with hypertension or type 2 diabetes. Second, we will use traditional process mapping exercises at each practice to manually produce maps of care processes for the selected condition. Third, with the aid of staff and patients at each practice, we will compare and contrast the process models produced by process mining with the process maps produced via manual techniques, review differences and similarities between them and the relative importance of each. The first pilot study will be on hypertension and the second for patients diagnosed with type 2 diabetes.

ETHICS AND DISSEMINATION

Ethical approval has been provided by East Midlands-Leicester South Regional Ethics Committee (REC reference 18/EM/0284). Having refined the automated production of maps of care processes, we can explore pinch points and bottlenecks, process variants and unexpected behaviour, and make informed recommendations to improve the quality and efficiency of care. The results of this study will be submitted for publication in peer-reviewed journals.

Modeling asynchronous event sequences with RNNs

Sequences of events have often been modeled with computational techniques, but typical preprocessing steps and problem settings do not explicitly address the ramifications of timestamped events. Clinical data, such as is found in electronic health records (EHRs), typically comes with timestamp information. In this work, we define event sequences and their properties: synchronicity, evenness, and co-cardinality; we then show how asynchronous, uneven, and multi-cardinal problem settings can support explicit accountings of relative time. Our evaluation uses the temporally sensitive clinical use case of pediatric asthma, which is a chronic disease with symptoms (and lack thereof) evolving over time. We show several approaches to explicitly incorporating relative time into a recurrent neural network (RNN) model that improve the overall classification of patients into those with no asthma, those with persistent asthma, those in long-term remission, and those who have experienced relapse. We also compare and contrast these results with those in an inpatient intensive care setting.

A data-driven framework of typical treatment process extraction and evaluation

BACKGROUND

A clinical pathway (CP) defines a standardized care process for a well-defined patient group that aims to improve patient outcomes and promote patient safety. However, the construction of a new pathway from scratch is a time-consuming task for medical staff because it involves many factors, including objects, multidisciplinary collaboration, sequential design, and outcome measurements. Recently, the rapid development of hospital information systems has allowed the storage of large volumes of electronic medical records (EMRs), and this information constitutes an abundant data resource for building CPs using data-mining methods.

METHODS

We provide an automatic method for extracting typical treatment processes from EMRs that consists of four key steps. First, a novel similarity method is proposed to measure the similarity of two treatment records. Then, we perform an affinity propagation (AP) clustering algorithm to cluster doctor order set sequences (DOSSs). Next, a framework is proposed to extract a high-level description of each treatment cluster. Finally, we evaluate the extracted typical treatment processes by matching the treatment cluster with external information, such as the treatment efficacy, length of stay, and treatment cost.

RESULTS

By experiments on EMRs of 8287 cerebral infarction patients, it is concluded that our proposed method can effectively extract typical treatment processes from treatment records, and also has great potential to improve treatment outcome by personalizing the treatment process for patients with different conditions.

CONCLUSION

The extracted typical treatment processes are intuitive and can provide managerial guidance for CP redesign and optimization. In addition, our work can assist clinicians in clearly understanding their routine treatment processes and recommend optimal treatment pathways for patients.

Careflow Mining Techniques to Explore Type 2 Diabetes Evolution

In this work we describe the application of a careflow mining algorithm to detect the most frequent patterns of care in a type 2 diabetes patients cohort. The applied method enriches the detected patterns with clinical data to define temporal phenotypes across the studied population. Novel phenotypes are discovered from heterogeneous data of 424 Italian patients, and compared in terms of metabolic control and complications. Results show that careflow mining can help to summarize the complex evolution of the disease into meaningful patterns, which are also significant from a clinical point of view.