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

Toward an Interdisciplinary Approach to Constructing Care Delivery Pathways From Electronic Health Care Databases to Support Integrated Care in Chronic Conditions: Systematic Review of Quantification and Visualization Methods

BACKGROUND

Electronic health care databases are increasingly used for informing clinical decision-making. In long-term care, linking and accessing information on health care delivered by different providers could improve coordination and health outcomes. Several methods for quantifying and visualizing this information into data-driven care delivery pathways (CDPs) have been proposed. To be integrated effectively and sustainably into routine care, these methods need to meet a range of prerequisites covering 3 broad domains: clinical, technological, and behavioral. Although advances have been made, development to date lacks a comprehensive interdisciplinary approach. As the field expands, it would benefit from developing common standards of development and reporting that integrate clinical, technological, and behavioral aspects.

OBJECTIVE

We aimed to describe the content and development of long-term CDP quantification and visualization methods and to propose recommendations for future work.

METHODS

We conducted a systematic review following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. We searched peer-reviewed publications in English and reported the CDP methods by using the following data in the included studies: long-term care data and extracted data on clinical information and aims, technological development and characteristics, and user behaviors. The data are summarized in tables and presented narratively.

RESULTS

Of the 2921 records identified, 14 studies were included, of which 13 (93%) were descriptive reports and 1 (7%) was a validation study. Clinical aims focused primarily on treatment decision-making (n=6, 43%) and care coordination (n=7, 50%). Technological development followed a similar process from scope definition to tool validation, with various levels of detail in reporting. User behaviors (n=3, 21%) referred to accessing CDPs, planning care, adjusting treatment, or supporting adherence.

CONCLUSIONS

The use of electronic health care databases for quantifying and visualizing CDPs in long-term care is an emerging field. Detailed and standardized reporting of clinical and technological aspects is needed. Early consideration of how CDPs would be used, validated, and implemented in clinical practice would likely facilitate further development and adoption.

TRIAL REGISTRATION

PROSPERO CRD42019140494; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=140494.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1136/bmjopen-2019-033573.

Inferring actual treatment pathways from patient records

OBJECTIVE

Treatment pathways are step-by-step plans outlining the recommended medical care for specific diseases; they get revised when different treatments are found to improve patient outcomes. Examining health records is an important part of this revision process, but inferring patients' actual treatments from health data is challenging due to complex event-coding schemes and the absence of pathway-related annotations. The objective of this study is to develop a method for inferring actual treatment steps for a particular patient group from administrative health records - a common form of tabular healthcare data - and address several technique- and methodology-based gaps in treatment pathway-inference research.

METHODS

We introduce Defrag, a method for examining health records to infer the real-world treatment steps for a particular patient group. Defrag learns the semantic and temporal meaning of healthcare event sequences, allowing it to reliably infer treatment steps from complex healthcare data. To our knowledge, Defrag is the first pathway-inference method to utilise a neural network (NN), an approach made possible by a novel, self-supervised learning objective. We also developed a testing and validation framework for pathway inference, which we use to characterise and evaluate Defrag's pathway inference ability, establish benchmarks, and compare against baselines.

RESULTS

We demonstrate Defrag's effectiveness by identifying best-practice pathway fragments for breast cancer, lung cancer, and melanoma in public healthcare records. Additionally, we use synthetic data experiments to demonstrate the characteristics of the Defrag inference method, and to compare Defrag to several baselines, where it significantly outperforms non-NN-based methods.

CONCLUSIONS

Defrag offers an innovative and effective approach for inferring treatment pathways from complex health data. Defrag significantly outperforms several existing pathway-inference methods, but computationally-derived treatment pathways are still difficult to compare against clinical guidelines. Furthermore, the open-source code for Defrag and the testing framework are provided to encourage further research in this area.

Leveraging process mining for modeling progression trajectories in amyotrophic lateral sclerosis

BACKGROUND

Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease whose spreading and progression mechanisms are still unclear. The ability to predict ALS prognosis would improve the patients' quality of life and support clinicians in planning treatments. In this paper, we investigate ALS evolution trajectories using Process Mining (PM) techniques enriched to both easily mine processes and automatically reveal how the pathways differentiate according to patients' characteristics.

METHODS

We consider data collected in two distinct data sources, namely the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) dataset and a real-world clinical register (ALS-BS) including data of patients followed up in two tertiary clinical centers of Brescia (Italy). With a focus on the functional abilities progressively impaired as the disease progresses, we use two Process Discovery methods, namely the Directly-Follows Graph and the CareFlow Miner, to mine the population disease trajectories on the PRO-ACT dataset. We characterize the impairment trajectories in terms of patterns, timing, and probabilities, and investigate the effect of some patients' characteristics at onset on the followed paths. Finally, we perform a comparative study of the impairment trajectories mined in PRO-ACT versus ALS-BS.

RESULTS

We delineate the progression pathways on PRO-ACT, identifying the predominant disabilities at different stages of the disease: for instance, 85% of patients enter the trials without disabilities, and 48% of them experience the impairment of Walking/Self-care abilities first. We then test how a spinal onset increases the risk of experiencing the loss of Walking/Self-care ability as first impairment (52% vs. 27% of patients develop it as the first impairment in the spinal vs. the bulbar cohorts, respectively), as well as how an older age at onset corresponds to a more rapid progression to death. When compared, the PRO-ACT and the ALS-BS patient populations present some similarities in terms of natural progression of the disease, as well as some differences in terms of observed trajectories plausibly due to the trial scheduling and recruitment criteria.

CONCLUSIONS

We exploited PM to provide an overview of the evolution scenarios of an ALS trial population and to preliminary compare it to the progression observed in a clinical cohort. Future work will focus on further improving the understanding of the disease progression mechanisms, by including additional real-world subjects as well as by extending the set of events considered in the impairment trajectories.

Maternal, infant, and environmental risk factors for sudden unexpected infant deaths: results from a large, administrative cohort

OBJECTIVES

Many studies of sudden unexpected infant death (SUID) have focused on individual domains of risk factors (maternal, infant, and environmental), resulting in limited capture of this multifactorial outcome. The objective of this study was to examine the geographic distribution of SUID in San Diego County, and assess maternal, infant, and environmental risk factors from a large, administrative research platform.

STUDY DESIGN

Births in California between 2005 and 2017 were linked to hospital discharge summaries and death files. From this retrospective birth cohort, cases of SUID were identified from infant death files in San Diego County. We estimated adjusted hazard ratios (aHRs) for infant, maternal, and environmental factors and SUID in multivariable Cox regression analysis. Models were adjusted for maternal sociodemographic characteristics and prenatal nicotine exposure.

RESULTS

There were 211 (44/100,000 live births; absolute risk 0.04%) infants with a SUID among 484,905 live births. There was heterogeneity in geographic distribution of cases. Multiparity (0.05%; aHR 1.4, 95% confidence interval (CI) 1.1, 1.9), maternal depression (0.11%; aHR 1.8, 95% CI 1.0, 3.4), substance-related diagnoses (0.27%; aHR 2.3, 95% CI 1.3, 3.8), cannabis-related diagnosis (0.35%; aHR 2.7, 95% CI 1.5, 5.0), prenatal nicotine use (0.23%; aHR 2.5, 95% CI 1.5, 4.2), preexisting hypertension (0.11%; aHR 2.3, 95% CI 1.2, 4.3), preterm delivery (0.09%; aHR 2.1, 95% CI 1.5, 3.0), infant with a major malformation (0.09%; aHR 2.0, 95% CI 1.1, 3.6), respiratory distress syndrome (0.12%; aHR 2.6, 95% CI 1.5, 4.6), and select environmental factors were all associated with SUID.

CONCLUSIONS

Multiple risk factors were confirmed and expanded upon, and the geographic distribution for SUID in San Diego County was identified. Through this approach, prevention efforts can be targeted to geographies that would benefit the most.

Development of a workflow process mapping protocol to inform the implementation of regional patient navigation programs in breast oncology

BACKGROUND

Implementing city-wide patient navigation processes that support patients across the continuum of cancer care is impeded by a lack of standardized tools to integrate workflows and reduce gaps in care. The authors present an actionable workflow process mapping protocol for navigation process planning and improvement based on methods developed for the Translating Research Into Practice study.

METHODS

Key stakeholders at each study site were identified through existing community partnerships, and data on each site's navigation processes were collected using mixed methods through a series of team meetings. The authors used Health Quality Ontario's Quality Improvement Guide, service design principles, and key stakeholder input to map the collected data onto a template structured according to the case-management model.

RESULTS

Data collection and process mapping exercises resulted in a 10-step protocol that includes: 1) workflow mapping procedures to guide data collection on the series of activities performed by health care personnel that comprise a patient's navigation experience, 2) a site survey to assess program characteristics, 3) a semistructured interview guide to assess care coordination workflows, 4) a site-level swim lane workflow process mapping template, and 5) a regional high-level process mapping template to aggregate data from multiple site-level process maps.

CONCLUSIONS

This iterative, participatory approach to data collection and process mapping can be used by improvement teams to streamline care coordination, ultimately improving the design and delivery of an evidence-based navigation model that spans multiple treatment modalities and multiple health systems in a metropolitan area. This protocol is presented as an actionable toolkit so the work may be replicated to support other quality-improvement initiatives and efforts to design truly patient-centered breast cancer treatment experiences.

LAY SUMMARY

Evidence-based patient navigation in breast cancer care requires the integration of services through each phase of cancer treatment. The Translating Research Into Practice study aims to implement patient navigation for patients with breast cancer who are at risk for delays and are seeking care across 6 health systems in Boston, Massachusetts. The authors designed a 10-step protocol outlining procedures and tools that support a systematic assessment for health systems that want to implement breast cancer patient navigation services for patients who are at risk for treatment delays.

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.

Construction of Empirical Care Pathways Process Models From Multiple Real-World Datasets

Care pathways (CPWs) are "multidisciplinary care plans that detail essential care steps for patients with specific clinical problems." While CPWs impact on health or cost outcomes is vastly studied, an in-depth analysis of the real-world implementation of the CPWs is an area that still remains underexplored. The present work describes how to apply an existing process mining methodology to construct the empirical CPW process models. These process models are a unique piece of information for health services research: for example to evaluate their conformance against the theoretical CPW described on clinical guidelines or to evaluate the impact of the process in health outcomes. To this purpose, this work relies on the design and implementation of a solution that a) synthesizes the expert knowledge on how health care is delivered within and across providers as an activity log, and b) constructs the CPW process model from that activity log using process mining techniques. Unlike previous research based on ad hoc data captures, current approach is built on the linkage of various heterogeneous real-world data (RWD) sets that share a minimum semantic linkage. RWD, defined as secondary use of routinely collected data as opposite to ad hoc data extractions, is a unique source of information for the CPW analysis due to its coverage of the caregiving activities and its wide availability. The viability of the solution is demonstrated by constructing the CPW process model of Code Stroke (Acute Stroke CPW) in the Aragon region (Spain).