A process mining-based investigation of adverse events in care processes.

Summarizing clinical pathways from event logs

An increased need for efficiency and effectiveness in today’s healthcare system urges professionals to improve the organization of care. Care pathways are an important tool to achieve this. The overall aim of this study was to analyze if care pathways lead to better organization of care processes. For this, the Care Process Self-Evaluation tool (CPSET) was used to evaluate how healthcare professionals perceive the organization of care processes. Based on information from 2692 health care professionals gathered between November 2007 and October 2011 we audited 261 care processes in 108 organizations. Multilevel analysis was used to compare care processes without and with care pathways and analyze if care pathways led to better organization of care processes. A significant difference between care processes with and without care pathways was found. A care pathway in use led to significant better scores on the overall CPSET scale (p<0.001) and its subscales, “coordination of care” (p<0.001) and “follow-up of care” (p<0.001). Physicians had the highest score on the overall CPSET scale and the five subscales. Care processes organized by care pathways had a 2.6 times higher probability that the care process was well-organized. In around 75% of the cases a care pathway led to better organized care processes. Care processes supported by care pathways were better organized, but not all care pathways were well-organized. Managers can use care pathways to make healthcare professionals more aware of their role in the organization of the care process.

Restorative neurostimulation for multifidus muscle is a novel therapy for chronic low back pain (CLBP). Optimal outcomes require interdisciplinary follow-up. We describe a clinical care pathway (CPW) for this therapy and report patient compliance, clinical outcomes, and patient satisfaction with the CPW. This study aimed to develop, at a single center, a CPW with derivation, practical basis, description, and evolution. Included in the study were audits of 1) patient compliance with attendance over 24 months, 2) medical and paramedical attendance at the clinic, 3) clinical outcomes in terms of reductions in both patient and cohort disability (Oswestry Disability Index, ODI) and CLBP numeric rating score (NRS), and 4) adverse events; and a prospective cross-sectional survey of patient satisfaction with the CPW. A CPW that involved both preoperative and postoperative education and integrated interdisciplinary care was developed and incorporated into the clinical service with a dedicated clinic. In the two years under study, 172 patients attended the education session, and 92 proceeded to restorative neurostimulation for multifidus muscle therapy; 15 patients who had this therapy before the CPW also were incorporated into the CPW. Patient compliance with the pathway was 88% (95% CI 79%-94%) at 12 months. Attendance at the dedicated CPW clinic by the various subspeciality clinicians ranged between 74% and 100%. There were serial reductions in both ODI (38.9 [95% CI 35.9-41.9] to 30.0 (95% CI 26.7-33.8) and CLBP NRS (6.3 [95% CI 6.0-6.7] to 3.3 (95% 2.7-3.9) after 12 months; 76 of the 99 patients assessable (77%: 95% CI 67%-85%) had a minimally important clinical difference reduction in either ODI or pain NRS, whereas eight were unassessable. Patient satisfaction with the CPW was very high (mean 26.9; median 27, maximum 28). The CPW facilitated clinical management and optimized outcomes in patients having restorative neurostimulation. Its design and delivery were very well accepted by patients.

Fatigue is a frequent and burdensome symptom in patients with advanced disease in palliative care. However, it is under-assessed and undertreated in clinical practice, even though many treatment options have been identified in systematic reviews. Care pathways with defined and standardised steps have been recommended for effective management in the clinical setting. This paper describes a care pathway for managing fatigue in palliative care patients. This study aims to develop a care pathway with detailed guidance for screening, assessment, diagnosis, and treatment of fatigue in palliative care patients. A collaborative effort of multidisciplinary clinicians participated in constructing the care pathway. The care pathway was developed using the following steps: (a) Developing an intervention; (b) piloting and feasibility; (c) evaluating the intervention; (d) reporting; and (e) implementation. This paper covers the first step, which includes the evidence base identification, theory identification/development, and process/outcomes modeling. A literature search was conducted to understand the extent of the fatigue problem in the palliative care setting and identify existing guidelines and strategies for managing fatigue. Consistent recommendations emanating from the included papers were then contributed to a care pathway. Patient representatives and palliative care professionals provided feedback on the draft. The care pathway address the following care processes: (1) Screening for the presence of fatigue; (2) assessment to evaluate the severity of fatigue; (3) diagnostic procedure, including history, physical examination, and laboratory finding; (4) therapeutic management pathway for clinical decision-making; and (5) valuation of treatment effect, using questionnaires, diaries and physical activity monitoring with body-worn sensors. The development of a care pathway will help to implement regular and structured assessment, diagnosis, and treatment of fatigue for healthcare professionals treating palliative care patients. Reviewing the pathway with a multidisciplinary expert group and field testing the pathway will be the next steps toward implementation.

A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text

Improving Patient Outcomes by Standardizing Care

Background: Care pathways, also known as clinical pathways, are used all over the world to implement and monitor patient-centered care processes in a transparent way. Care pathways are defined as a complex intervention, but there is a lack of information on how to design care pathways.Method: Based on the experience of the Belgian Dutch Clinical Pathway Network, a 7-phase method to develop, implement, evaluate and continuously follow up a care pathway was designed. An international expert panel of the European Pathway Association validated this method.Findings: The 7-phase method can be useful for in-hospital, primary care and cross boundary projects to improve the quality of healthcare processes. This 7-phase method includes a screening phase, a project management phase, a diagnostic- and objectification phase, a development phase, an implementation phase, an evaluation phase and a continuous follow-up phase.Conclusion: This method can offer support to multidisciplinary teams (re)designing and implementing safe, efficient, effective, person-centered, timely, equitable, continuous and integrated care processes. However, the method is no guarantee to success. The key to success is the collaboration and critical attitude of the entire multidisciplinary team when implementing pathways.Originality: This paper is the first publication defining the detailed steps to design care pathways. The content is based on international experience and discussions within an expert panel. The method can support clinicians and healthcare managers in re-designing their processes of care.

Patients suffering from multiple diseases (multi-morbid patients) often have complex clinical pathways. They are diagnosed and treated by different specialties and undergo other clinical actions related to various diagnoses. Coordination of care for these patients is often challenging, and it would be of great benefit to get better insight into how the clinical pathways develop in reality. Discovering these pathways using traditional process mining techniques and standard event logs may be difficult because the patient is involved in several highly independent clinical processes. Our objective is to explore the potential of analyzing these pathways using an event log representation reflecting the independent clinical processes. Our main research question is: How can we identify valuable insights by using a multi-entity event data representation for clinical pathways of multi-morbid patients? Our method was built on the idea to represent multiple entities in event logs as event graphs. The MIMIC-III dataset was used to evaluate the feasibility of this approach. Several clinical entities were identified and then mapped into an event graph. Finally, multi-entity directly follows graphs were discovered by querying the event graph visualizing them. Our result shows that paths involving multiple entities include traditional process mining concepts not for one clinical process but all involved processes. In addition, the relationship between activities of different clinical processes, which was not recognizable in traditional models, is visible in the event graph representation.

Efforts to safely reduce length of stay for emergency department patients with symptoms suggestive of acute coronary syndrome (ACS) have had mixed success. Few system-wide efforts affecting multiple hospital emergency departments have ever been evaluated. We evaluated the effectiveness of a nationwide implementation of clinical pathways for potential ACS in disparate hospitals. This was a multicenter pragmatic stepped-wedge before-and-after trial in 7 New Zealand acute care hospitals with 31 332 patients investigated for suspected ACS with serial troponin measurements. The implementation was a clinical pathway for the assessment of patients with suspected ACS that included a clinical pathway document in paper or electronic format, structured risk stratification, specified time points for electrocardiographic and serial troponin testing within 3 hours of arrival, and directions for combining risk stratification and electrocardiographic and troponin testing in an accelerated diagnostic protocol. Implementation was monitored for >4 months and compared with usual care over the preceding 6 months. The main outcome measure was the odds of discharge within 6 hours of presentation RESULTS: There were 11 529 participants in the preimplementation phase (range, 284-3465) and 19 803 in the postimplementation phase (range, 395-5039). Overall, the mean 6-hour discharge rate increased from 8.3% (range, 2.7%-37.7%) to 18.4% (6.8%-43.8%). The odds of being discharged within 6 hours increased after clinical pathway implementation. The odds ratio was 2.4 (95% confidence interval, 2.3-2.6). In patients without ACS, the median length of hospital stays decreased by 2.9 hours (95% confidence interval, 2.4-3.4). For patients discharged within 6 hours, there was no change in 30-day major adverse cardiac event rates (0.52% versus 0.44%; P=0.96). In these patients, no adverse event occurred when clinical pathways were correctly followed. Implementation of clinical pathways for suspected ACS reduced the length of stay and increased the proportions of patients safely discharged within 6 hours. URL: https://www.anzctr.org.au/ (Australian and New Zealand Clinical Trials Registry). Unique identifier: ACTRN12617000381381.

Process mining is the discipline of discovering processes from event logs, checking the conformance of real world events to idealized processes, and ultimately finding ways to improve those processes. It was originally applied to business processes and has recently been applied to healthcare. It can reveal insights into clinical care pathways and inform the redesign of healthcare services. We reviewed the literature on process mining, to investigate the extent to which process mining has been applied to primary care, and to identify specific challenges that may arise in this setting. We identified 143 relevant papers, of which only a small minority (n=7) focused on primary care settings. Reported challenges included data quality (consistency and completeness of routinely collected data); selection of appropriate algorithms and tools; presentation of results; and utilization of results in real-world applications.

Clinical pathway (CP) is a tool to improve service quality and efficiency of the medical institutions. However, most of the clinical pathways designed with the traditional methods are static and non-adaptive. Recently, the process mining techniques are receiving increasing attentions. It can not only help the clinical pathways designers to discover the sequence of activities, but also provide execution information for analyzing variances and correcting design errors. In this article, first, a literature review is presented. In the analysis of 37 studies from the period 2004–2013, three research aspects (process discovery for clinical pathways design, variants analysis and control, continuous evaluation and improvement) are explored, and the weaknesses of the methods are analyzed. It is found that the mining algorithms developed are not efficient enough to deal with the unstructured processes, the models obtained cannot give a good explanation of the variants, and the lack of systemic thinking makes the improvement process of CP very tedious. Based on the analysis, finally, four key trends are identified: (1) further analysis of the variants, (2) integrated process management, (3) customization and (4) self-learning improvement of the clinical pathway.

Clinical pathways used today are paper-based, although many different kinds of clinical pathway are used in clinical practice. However, in the development of software for clinical pathway, it is difficult to achieve cooperation between medical experts, who are not used to expressing their ideas and work in words, and system-developers whose medical knowledge is limited. As a consequence, the current situation is that medical practitioners make their own software and use it in their practice. While this may work, it is less than ideal because refinements that may make the software most effective through engineering expertise is not used. Thus, in our research team, the nurse researchers and the engineering researchers cooperated and developed a clinical pathway system. In this paper, the present conditions, problems, and future direction of the server-controlled CP system development in the psychiatric hospitals, is discussed from viewpoint of nursing as a user.

Objectives: Although Clinical Pathway (CP) standardizes the patient care, poor compliance remains. The consistency of the expert’s opinion on the CPs significance to the pattern of Clinical Pathway completeness was explored. Methods/Statistical Analysis: Mixed method and data triangulation were used in this study. Two types of data were collected from one hospital for STEMI (St Elevation Myocardial Infarction) patients. Primary (Survey) and secondary (CP filled documents) data were collected. Clinical Pathway content analyses with descriptive statistics were conducted using SPSS version 22. The influence of design on the completeness of the document was investigated. Findings: The content analysis revealed four main care processes in STEMI Clinical Pathway (Medical assessment and nursing, Medication therapy and treatment, Education nutrition and rehabilitation and outcome variance). We found differences in the design of the documents. Most of the experts (58%) agreed on the importance of time to treatment, while 35% of the respondents have a strong agreement on the importance of fast action to treatment and nothing should delay the intervention. CP1 was holding the highest ratio of documents completeness despite the fact that CP2 and CP3 are the improved version of CP1. Application/Improvements: The variance of the expert opinion from the real Clinical Pathway performance indicated inconsistency between the knowledge and practice. Further explanation for the phenomenon is recommended.

PurposeThe purpose of this paper is to define a clinical pathway for total joint replacement (TJR) surgery, estimate the effect of delays between steps of the pathway on wait time for surgery and to identify factors contributing to more efficient operations and challenges to their implementation.Design/methodology/approachThis is a case study with a mixed methods approach. The authors conducted interviews with hospital staff. Data collected in the interviews and through on-site observation were analyzed to map the TJR process and identify the steps of the care pathway. The authors extracted and analyzed data (time stamps) from 60 hospital patient records for each step in the pathway and ran a regression on the duration of the whole trajectory.FindingsThere were wide variations in the delays observed between the seven steps identified. The delay between Step 1 and Step 2 was the only significant variable in predicting the total wait time to surgery. In one hospital, one delay explained 50 percent of the variation. There was misalignment between findings from the qualitative data in terms of strategies implemented to increase efficiency of the clinical pathway to the quantitative data on delays between the steps.Research limitations/implicationsThe study identified the clinical pathway from the consultation with an orthopaedic surgeon to the surgery. However, it did not go beyond the surgery. Future research could investigate the relationship between specific processes and delays between steps of the process and patient outcomes, including length of stay, mobilization and functionality in activities of daily living, as well as potential complications from surgery, readmission and the services required after the patient was discharged.Practical implicationsWait times can be addressed by implementing strategies at the health system level or at the organizational level. The authors found and discuss areas where there could be efficiency gains for health care organizations.Social implicationsStakeholders in care processes are diverse and they each have their preferences in how they practice (in the case of providers) and how they perceive and wish to respond adequately to patients’ needs in contexts that have different norms and approaches. The approach in this study enables a better understanding of the processes, the organizational culture and how these may affect each other.Originality/valueOur mixed methods enabled a process mapping and the identification of factors that significantly affected the efficiency of the TJR surgery process. It combines methods from process engineering with health services and management research. To some extent, this study demonstrates that although managers can define and enforce processes, organizational culture and practices are harder to influence.

Clinical Pathways (CPs) are evidence-based recommendation for treating a diagnosis and an effective instrument to decrease undesired practice variability and improve clinician performance. Deviations from CPs might just as well reduce quality of care. Moreover they can be associated to possible adverse events. In this perspective, we developed and tested a system for comparing a patient trajectory (PT) with the corresponding CP in order to recognize significant variations. To measure adherence, a Clinical Pathway Deviation Index (CPDI) was constructed as the weighted-sum of five indicators. To build the indicators three different tools for CPs modeling have been tested. Only two of them proved suitable for our system. A preliminary analysis has been carried out using data of 24 real PTs. The aim of this paper is to present the system and to characterize CPDI performances.