Healthcare pathway discovery and probabilistic machine learning

Appendicectomy pathway: Insights from electronic medical records of a local health district in Australia

BACKGROUND

This study aims to identify the common pathways of appendicectomy, the most common emergency surgery in Australia's public hospitals and any variations within a regional public health district in New South Wales, Australia.

METHODS

We analyzed the electronic medical records of 3,943 patients who underwent appendicectomy between January 2014 and July 2020 at 2 hospitals in the Illawarra Shoalhaven Local Health District, New South Wales, Australia, using the PM2 approach for surgical pathway identification and subsequent statistical analyses.

RESULTS

Among 3,943 patients, 3,606 (91.5%) followed an 11-step main pathway: (1) emergency department admission, (2) surgery booking, (3) anesthesia start, (4) operating room entry, (5) surgery start, (6) surgery end, (7) anesthesia end, (8) operating room discharge, (9) postanesthesia care unit admission, (10) postanesthesia care unit discharge, and (11) hospital discharge. The median length of stay was 48.13 hours (interquartile range 32.74). The main pathway differed from either variation 1 (n = 246, 6.2%) or variation 2 (n = 30, 0.8%) only in the timing and location of anesthesia administration or conclusion. Variation 3 (n = 26, 0.7%) included patients who underwent appendicectomy twice, whereas variation 4 (n = 25, 0.6%) included patients booked for surgery before emergency department admission through community doctor referrals. Thirteen exceptional cases experienced combinations of the aforementioned pathways. The length of stay and phase durations varied between the main pathway and these variations.

CONCLUSION

The appendicectomy pathway was largely standardized across the studied hospitals, with the location of anesthesia administration or conclusion affecting specific stages but not the overall length of stay. Only a complex 2-surgery pathway increased length of stay.

Enhancing healthcare process analysis through object-centric process mining: Transforming OMOP common data models into object-centric event logs

OBJECTIVES

This study aims to enhance the analysis of healthcare processes by introducing Object-Centric Process Mining (OCPM). By offering a holistic perspective that accounts for the interactions among various objects, OCPM transcends the constraints of conventional patient-centric process mining approaches, ensuring a more detailed and inclusive understanding of healthcare dynamics.

METHODS

We develop a novel method to transform the Observational Medical Outcomes Partnership Common Data Models (OMOP CDM) into Object-Centric Event Logs (OCELs). First, an OMOP CDM4PM is created from the standard OMOP CDM, focusing on data relevant to generating OCEL and addressing healthcare data's heterogeneity and standardization challenges. Second, this subset is transformed into OCEL based on specified healthcare criteria, including identifying various object types, clinical activities, and their relationships. The methodology is tested on the MIMIC-IV database to evaluate its effectiveness and utility.

RESULTS

Our proposed method effectively produces OCELs when applied to the MIMIC-IV dataset, allowing for the implementation of OCPM in the healthcare industry. We rigorously evaluate the comprehensiveness and level of abstraction to validate our approach's effectiveness. Additionally, we create diverse object-centric process models intricately designed to navigate the complexities inherent in healthcare processes.

CONCLUSION

Our approach introduces a novel perspective by integrating multiple viewpoints simultaneously. To the best of our knowledge, this is the inaugural application of OCPM within the healthcare sector, marking a significant advancement in the field.

Can Machine Learning Correctly Predict Outcomes of Flexible Ureteroscopy with Laser Lithotripsy for Kidney Stone Disease? Results from a Large Endourology University Centre

Background and objective

The integration of machine learning (ML) in health care has garnered significant attention because of its unprecedented opportunities to enhance patient care and outcomes. In this study, we trained ML algorithms for automated prediction of outcomes of ureteroscopic laser lithotripsy (URSL) on the basis of preoperative characteristics.

Methods

Data were retrieved for patients treated with ureteroscopy for urolithiasis by a single experienced surgeon over a 7-yr period. Sixteen ML classification algorithms were trained to investigate correlation between preoperative characteristics and postoperative outcomes. The outcomes assessed were primary stone-free status (SFS, defined as the presence of only stone fragments <2 mm on endoscopic visualisation and at 3-mo imaging) and postoperative complications. An ensemble model was constructed from the best-performing algorithms for prediction of complications and for prediction of SFS. Simultaneous prediction of postoperative characteristics was then investigated using a multitask neural network, and explainable artificial intelligence (AI) was used to demonstrate the predictive power of the best models.

Key findings and limitations

An ensemble ML model achieved accuracy of 93% and precision of 87% for prediction of SFS. Complications were mainly associated with a preoperative positive urine culture (1.44). Logistic regression revealed that SFS was impacted by the total stone burden (0.34), the presence of a preoperative stent (0.106), a positive preoperative urine culture (0.14), and stone location (0.09). Explainable AI results emphasised the key features and their contributions to the output.

Conclusions and clinical implications

Technological advances are helping urologists to overcome the classic limits of ureteroscopy, namely stone size and the risk of complications. ML represents an excellent aid for correct prediction of outcomes after training on pre-existing data sets. Our ML model achieved accuracy of >90% for prediction of SFS and complications, and represents a basis for the development of an accessible predictive model for endourologists and patients in the URSL setting.

Patient summary

We tested the ability of artificial intelligence to predict treatment outcomes for patients with kidney stones. We trained 16 different machine learning tools with data before surgery, such as patient age and the stone characteristics. Our final model was >90% accurate in predicting stone-free status after surgery and the occurrence of complications.

Applying sequence analysis to uncover 'real-world' clinical pathways from routinely collected data: a systematic review

OBJECTIVES

This systematic review aims to elucidate the methodological practices and reporting standards associated with sequence analysis (SA) for the identification of clinical pathways in real-world scenarios, using routinely collected data.

STUDY DESIGN AND SETTING

We conducted a methodological systematic review, searching five medical and health databases: MEDLINE, PsycINFO, CINAHL, EMBASE and Web of Science. The search encompassed articles from the inception of these databases up to February 28, 2023. The search strategy comprised two distinctive sets of search terms, specifically focused on sequence analysis and clinical pathways.

RESULTS

19 studies met the eligibility criteria for this systematic review. Nearly 60% of the included studies were published in or after 2021, with a significant proportion originating from Canada (n = 7) and France (n = 5). 90% of the studies adhered to the fundamental SA steps. The optimal matching (OM) method emerged as the most frequently employed dissimilarity measure (63%), while agglomerative hierarchical clustering using Ward's linkage was the preferred clustering algorithm (53%). However, it is imperative to underline that a majority of the studies inadequately reported key methodological decisions pertaining to SA.

CONCLUSION

This review underscores the necessity for enhanced transparency in reporting both data management procedures and key methodological choices within SA processes. The development of reporting guidelines and a robust appraisal tool tailored to assess the quality of SA would be invaluable for researchers in this field.

Emergent Applications of Machine Learning for Diagnosing and Managing Appendicitis: A State-of-the-Art Review

Background: Appendicitis is an inflammatory condition that requires timely and effective intervention. Despite being one of the most common surgically treated diseases, the condition is difficult to diagnose because of atypical presentations. Ultrasound and computed tomography (CT) imaging improve the sensitivity and specificity of diagnoses, yet these tools bear the drawbacks of high operator dependency and radiation exposure, respectively. However, new artificial intelligence tools (such as machine learning) may be able to address these shortcomings. Methods: We conducted a state-of-the-art review to delineate the various use cases of emerging machine learning algorithms for diagnosing and managing appendicitis in recent literature. The query ("Appendectomy" OR "Appendicitis") AND ("Machine Learning" OR "Artificial Intelligence") was searched across three databases for publications ranging from 2012 to 2022. Upon filtering for duplicates and based on our predefined inclusion criteria, 39 relevant studies were identified. Results: The algorithms used in these studies performed with an average accuracy of 86% (18/39), a sensitivity of 81% (16/39), a specificity of 75% (16/39), and area under the receiver operating characteristic curves (AUROCs) of 0.82 (15/39) where reported. Based on accuracy alone, the optimal model was logistic regression in 18% of studies, an artificial neural network in 15%, a random forest in 13%, and a support vector machine in 10%. Conclusions: The identified studies suggest that machine learning may provide a novel solution for diagnosing appendicitis and preparing for patient-specific post-operative complications. However, further studies are warranted to assess the feasibility and advisability of implementing machine learning-based tools in clinical practice.

Temporal topic model for clinical pathway mining from electronic medical records

BACKGROUND

In recent years, the discovery of clinical pathways (CPs) from electronic medical records (EMRs) data has received increasing attention because it can directly support clinical doctors with explicit treatment knowledge, which is one of the key challenges in the development of intelligent healthcare services. However, the existing work has focused on topic probabilistic models, which usually produce treatment patterns with similar treatment activities, and such discovered treatment patterns do not take into account the temporal process of patient treatment which does not meet the needs of practical medical applications.

METHODS

Based on the assumption that CPs can be derived from the data of EMRs which usually record the treatment process of patients, this paper proposes a new CPs mining method from EMRs, an extended form of the traditional topic model - the temporal topic model (TTM). The method can capture the treatment topics and the corresponding treatment timestamps for each treatment day.

RESULTS

Experimental research conducted on a real-world dataset of patients' hospitalization processes, and the achieved results demonstrate the applicability and usefulness of the proposed methodology for CPs mining. Compared to existing benchmarks, our model shows significant improvement and robustness.

CONCLUSION

Our TTM provides a more competitive way to mine potential CPs considering the temporal features of the EMR data, providing a very prospective tool to support clinical diagnostic decisions.

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.

Mining context-aware resource profiles in the presence of multitasking

Healthcare organisations are becoming increasingly aware of the need to improve their care processes and to manage their scarce resources efficiently to secure high-quality care standards. As these processes are knowledge-intensive and heavily depend on human resources, a comprehensive understanding of the complex relationship between processes and resources is indispensable for efficient resource management. Organisational mining, a subfield of Process Mining, reveals insights into how (human) resources organise their work based on analysing process execution data recorded in Health Information Systems (HIS). This can be used to, e.g., discover resource profiles which are groups of resources performing similar activity instances, providing an extensive overview of resource behaviour within healthcare organisations. Healthcare managers can employ these insights to allocate their resources efficiently, e.g., by improving the scheduling and staffing of nurses. Existing resource profiling algorithms are limited in their ability to apprehend the complex relationship between processes and resources because they do not take into account the context in which activities were executed, particularly in the context of multitasking. Therefore, this paper introduces ResProMin-MT to discover context-aware resource profiles in the presence of multitasking. In contrast to the state-of-the-art, ResProMin-MT is capable of taking into account more complex contextual activity dimensions, such as activity durations and the degree of multitasking by resources. We demonstrate the feasibility of our method within a real-life healthcare context, validated by medical domain experts.

Machine Learning Methods in Health Economics and Outcomes Research-The PALISADE Checklist: A Good Practices Report of an ISPOR Task Force

Advances in machine learning (ML) and artificial intelligence offer tremendous potential benefits to patients. Predictive analytics using ML are already widely used in healthcare operations and care delivery, but how can ML be used for health economics and outcomes research (HEOR)? To answer this question, ISPOR established an emerging good practices task force for the application of ML in HEOR. The task force identified 5 methodological areas where ML could enhance HEOR: (1) cohort selection, identifying samples with greater specificity with respect to inclusion criteria; (2) identification of independent predictors and covariates of health outcomes; (3) predictive analytics of health outcomes, including those that are high cost or life threatening; (4) causal inference through methods, such as targeted maximum likelihood estimation or double-debiased estimation-helping to produce reliable evidence more quickly; and (5) application of ML to the development of economic models to reduce structural, parameter, and sampling uncertainty in cost-effectiveness analysis. Overall, ML facilitates HEOR through the meaningful and efficient analysis of big data. Nevertheless, a lack of transparency on how ML methods deliver solutions to feature selection and predictive analytics, especially in unsupervised circumstances, increases risk to providers and other decision makers in using ML results. To examine whether ML offers a useful and transparent solution to healthcare analytics, the task force developed the PALISADE Checklist. It is a guide for balancing the many potential applications of ML with the need for transparency in methods development and findings.

Process mining based on patient waiting time: an application in health processes

Purpose

Similar to many business processes, waiting times are also essential for health care processes, especially in obstetrics and gynecology outpatient department (GOD), because pregnant women may be affected by long waiting times. Since creating process models manually presents subjective and nonrealistic flows, this study aims to meet the need of an objective and realistic method.

Design/methodology/approach

In this study, the authors investigate time-related bottlenecks in both departments for different doctors by process mining. Process mining is a pragmatic analysis to obtain meaningful insights through event logs. It applies data mining techniques to business process management with more comprehensive perspectives. Process mining in this study enables to automatically create patient flows to compare considering each department and doctor.

Findings

The study concludes that average waiting times in the GOD are higher than obstetrics outpatient department. However, waiting times in departments can change inversely for different doctors.

Research limitations/implications

The event log was created by expert opinions because activities in the processes had just starting timestamp. The ending time of activity was computed by considering the average duration of the corresponding activity under a normal distribution.

Originality/value

This study focuses on administrative (nonclinical) health processes in obstetrics and GOD. It uses a parallel activity log inference algorithm (PALIA) to produce process trees by handling duplicate activities. Infrequent information in health processes can have critical information about the patient. PALIA considers infrequent activities in the event log to extract meaningful information, in contrast to many discovery algorithms.

Definition and conceptualization of the patient-centered care pathway, a proposed integrative framework for consensus: a Concept analysis and systematic review

BACKGROUND

Confusion exists over the definition of the care pathway concept and existing conceptual frameworks contain various inadequacies which have led to implementation difficulties. In the current global context of rapidly changing health care systems, there is great need for a standardized definition and integrative framework that can guide implementation. This study aims to propose an accurate and up-to-date definition of care pathway and an integrative conceptual framework.

METHODS

An innovative hybrid method combining systematic review, concept analysis and bibliometric analysis was undertaken to summarize qualitative, quantitative, and mixed-method studies. Databases searched were PubMed, Embase and ABI/Inform. Methodological quality of included studies was then assessed.

RESULTS

Forty-four studies met the inclusion criteria. Using concept analysis, we developed a fine-grained understanding, an integrative conceptual framework, and an up-to-date definition of patient-centered care pathway by proposing 28 subcategories grouped into seven attributes. This conceptual framework considers both operational and social realities and supports the improvement and sustainable transformation of clinical, administrative, and organizational practices for the benefit of patients and caregivers, while considering professional experience, organizational constraints, and social dynamics. The proposed attributes of a fluid and effective pathway are (i) the centricity of patients and caregivers, (ii) the positioning of professional actors involved in the care pathway, (iii) the operation management through the care delivery process, (iv) the particularities of coordination structures, (v) the structural context of the system and organizations, (vi) the role of the information system and data management and (vii) the advent of the learning system. Antecedents are presented as key success factors of pathway implementation. By using the consequences and empirical referents, such as outcomes and evidence of care pathway interventions, we went beyond the single theoretical aim, proposing the application of the conceptual framework to healthcare management.

CONCLUSIONS

This study has developed an up-to-date definition of patient-centered care pathway and an integrative conceptual framework. Our framework encompasses 28 subcategories grouped into seven attributes that should be considered in complex care pathway intervention. The formulation of these attributes, antecedents as success factors and consequences as potential outcomes, allows the operationalization of this model for any pathway in any context.

Clinical Information Systems Research in the Pandemic Year 2020

Objective: In this synopsis, we give an overview of recent research and propose a selection of best papers published in 2020 in the field of Clinical Information Systems (CIS).

Method: As CIS section editors, we annually apply a systematic process to retrieve articles for the International Medical Informatics Association Yearbook of Medical Informatics. For seven years now, we use the same query to find relevant publications in the CIS field. Each year we retrieve more than 2,400 papers which we categorize in a multi-pass review to distill a preselection of 15 candidate papers. External reviewers and yearbook editors then assess the selected candidate papers. Based on the review results, the IMIA Yearbook editorial board chooses up to four best publications for the section at a selection meeting. To get an overview of the content of the retrieved articles, we use text mining and term co-occurrence mapping techniques.

Results: We carried out the query in mid-January 2021 and retrieved a deduplicated result set of 2,787 articles from 1,135 different journals. We nominated 15 papers as candidates and finally selected four of them as the best papers in the CIS section. As in the previous years, the content analysis of the articles revealed the broad spectrum of topics covered by CIS research. Thus, this year we could observe a significant impact of COVID-19 on CIS research.

Conclusions: The trends in CIS research, as seen in recent years, continue to be observable. What was very visible was the impact of the Corona Virus Disease 2019 (COVID-19) pandemic, which has affected not only our lives but also CIS.

Recommendations for enhancing the usability and understandability of process mining in healthcare

Healthcare organizations are confronted with challenges including the contention between tightening budgets and increased care needs. In the light of these challenges, they are becoming increasingly aware of the need to improve their processes to ensure quality of care for patients. To identify process improvement opportunities, a thorough process analysis is required, which can be based on real-life process execution data captured by health information systems. Process mining is a research field that focuses on the development of techniques to extract process-related insights from process execution data, providing valuable and previously unknown information to instigate evidence-based process improvement in healthcare. However, despite the potential of process mining, its uptake in healthcare organizations outside case studies in a research context is rather limited. This observation was the starting point for an international brainstorm seminar. Based on the seminar's outcomes and with the ambition to stimulate a more widespread use of process mining in healthcare, this paper formulates recommendations to enhance the usability and understandability of process mining in healthcare. These recommendations are mainly targeted towards process mining researchers and the community to consider when developing a new research agenda for process mining in healthcare. Moreover, a limited number of recommendations are directed towards healthcare organizations and health information systems vendors, when shaping an environment to enable the continuous use of process mining.