Analyzing Healthcare Processes with Incremental Process Discovery: Practical Insights from a Real-World Application.

Abstract: Most process mining techniques are primarily automated, meaning that process analysts input information and receive output. As a result, process mining techniques function like black boxes with limited interaction options for analysts, such as simple sliders for filtering infrequent behavior. Recent research tries to break these black boxes by allowing process analysts to provide domain knowledge and guidance to process mining techniques, i.e., hybrid intelligence. Especially, in process discovery-a critical type of process mining-interactive approaches emerged. However, little research has investigated the practical application of such interactive approaches. This paper presents a case study focusing on using incremental and interactive process discovery techniques in the healthcare domain. Though healthcare presents unique challenges, such as high process execution variability and poor data quality, our case study demonstrates that an interactive process mining approach can effectively address these challenges.

An automated materials and processes identification tool for material informatics using deep learning approach.

This article reports a tool that enables Materials Informatics, termed as MatRec, via a deep learning approach. The tool captures data, makes appropriate domain suggestions, extracts various entities such as materials and processes, and helps to establish entity-value relationships. This tool uses keyword extraction, a document similarity index to suggest relevant documents, and a deep learning approach employing Bi-LSTM for entity extraction. For example, materials and processes for electrical charge storage under an electric double layer capacitor (EDLC) mechanism are demonstrated herewith. A knowledge graph approach finds and visualizes different latent knowledge sets from the processed information. The MatRec received an F1 score of 9̃6% for entity extraction, 8̃3% for material-value relationship extraction, and 8̃7% for process-value relationship extraction, respectively. The proposed MatRec could be extended to solve material selection issues for various applications and could be an excellent tool for academia and industry.

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.

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.

How Can Interactive Process Discovery Address Data Quality Issues in Real Business Settings? Evidence from a Case Study in Healthcare.

The focus of this paper is on how data quality can affect business process discovery in real complex environments, which is a major factor determining the success in any data-driven Business Process Management project. Many real-life event logs, especially healthcare ones, can suffer from several data quality issues, some of which cannot be solved by pre-processing or data cleaning techniques, leading to inaccurate results. We take an innovative Process Mining (PM) approach, termed Interactive Process Discovery (IPD), which combines domain knowledge with available data. This approach can overcome the limitations of noisy and incomplete event logs by putting "humans in the loop", leading to improved business process modelling. This is particularly valuable in healthcare, where physicians have a tacit domain knowledge not available in the event log, and, thus, difficult to elicit. We conducted a two-step approach based on a controlled experiment and a case study in an Italian hospital. At each step, we compared IPD with traditional PM techniques to assess the extent to which domain knowledge helps to improve the accuracy of process models. The case study tests the effectiveness of IPD to uncover knowledge-intensive processes extracted from noisy real-life event logs. The evaluation has been carried out by exploiting a real dataset of an Italian hospital, involving the medical staff. IPD can produce an accurate process model that is fully compliant with the clinical guidelines by addressing data quality issues. Accurate and reliable process models can support healthcare organizations in detecting process-related issues and in taking decisions related to capacity planning and process re-design.

Process mining to optimize palliative patient flow in a high-volume radiotherapy department.

INTRODUCTION: In radiotherapy, palliative patients are often suboptimal managed and patients experience long waiting times. Event-logs (recorded local files) of palliative patients, could provide a continuative decision-making system by means of shared guidelines to improve patient flow. Based on an event-log analysis, we aimed to accurately understand how to successively optimize patient flow in palliative care. METHODS: A process mining methodology was applied on palliative patient flow in a high-volume radiotherapy department. Five hundred palliative radiation treatment plans of patients with bone and brain metastases were included in the study, corresponding to 290 patients treated in our department in 2018. Event-logs and the relative attributes were extracted and organized. A process discovery algorithm was applied to describe the real process model, which produced the event-log. Finally, conformance checking was performed to analyze how the acquired event-log database works in a predefined theoretical process model. RESULTS: Based on the process discovery algorithm, 53 (10%) plans had a dose prescription of 8 Gy, 249 (49.8%) plans had a dose prescription of 20 Gy and 159 (31.8%) plans had a dose prescription of 30 Gy. The remaining 39 (7.8%) plans had different dose prescriptions. Considering a median value, conformance checking demonstrated that event-logs work in the theoretical model. CONCLUSIONS: The obtained results partially validate and support the palliative patient care guideline implemented in our department. Process mining can be used to provide new insights, which facilitate the improvement of existing palliative patient care flows.

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.

Scalable process discovery and conformance checking.

Considerable amounts of data, including process events, are collected and stored by organisations nowadays. Discovering a process model from such event data and verification of the quality of discovered models are important steps in process mining. Many discovery techniques have been proposed, but none of them combines scalability with strong quality guarantees. We would like such techniques to handle billions of events or thousands of activities, to produce sound models (without deadlocks and other anomalies), and to guarantee that the underlying process can be rediscovered when sufficient information is available. In this paper, we introduce a framework for process discovery that ensures these properties while passing over the log only once and introduce three algorithms using the framework. To measure the quality of discovered models for such large logs, we introduce a model-model and model-log comparison framework that applies a divide-and-conquer strategy to measure recall, fitness, and precision. We experimentally show that these discovery and measuring techniques sacrifice little compared to other algorithms, while gaining the ability to cope with event logs of 100,000,000 traces and processes of 10,000 activities on a standard computer.

Process modeling and bottleneck mining in online peer-review systems.

This paper is divided into three main parts. In the first part of the study, we captured, collected and formatted an event log describing the handling of reviews for proceedings of an international conference in Thailand. In the second part, we used several process mining techniques in order to discover process models, social, organizational, and hierarchical structures from the proceeding's event log. In the third part, we detected the deviations and bottlenecks of the peer review process by comparing the observed events (i.e., authentic dataset) with a pre-defined model (i.e., master map). Finally, we investigated the performance information as well as the total waiting time in order to improve the effectiveness and efficiency of the online submission and peer review system for the prospective conferences and seminars. Consequently, the main goals of the study were as follows: (1) to convert the collected event log into the appropriate format supported by process mining analysis tools, (2) to discover process models and to construct social networks based on the collected event log, and (3) to find deviations, discrepancies and bottlenecks between the collected event log and the master pre-defined model. The results showed that although each paper was initially sent to three different reviewers; it was not always possible to make a decision after the first round of reviewing; therefore, additional reviewers were invited. In total, all the accepted and rejected manuscripts were reviewed by an average of 3.9 and 3.2 expert reviewers, respectively. Moreover, obvious violations of the rules and regulations relating to careless or inappropriate peer review of a manuscript-committed by the editorial board and other staff-were identified. Nine blocks of activity in the authentic dataset were not completely compatible with the activities defined in the master model. Also, five of the activity traces were not correctly enabled, and seven activities were missed within the online submission system. On the other hand, dealing with the feedback (comments) received from the first and the third reviewers; the conference committee members and the organizers did not attend to those feedback/comments in a timely manner.