This paper addresses the problem of process discovery from large and complex event logs. We depart from the existing literature and formulate the problem of optimal process discovery. A formal mathematical programming model is given based on a novel hierarchical structuration of the event logs. Desired properties of event trace score functions are described, and the properties of optimal process models are proved. A combination of Monte Carlo optimization and tabu search is proposed to overcome the complexity related to the huge size of the event logs and the combinatorial solution space. Numerical results show that our approach is suitable for large event logs and that it performs better than the state-of-the-art approaches. We also demonstrate the applicability of our method on a real case study in health care. This paper illustrates the benefits of combining techniques from the operational research and the process mining fields.

Process mining is a suitable method for knowledge extraction from patient pathways. Structured in event logs, medical events are complex, often described using various medical codes. An efficient labeling of these events before applying process mining analysis is challenging. This paper presents an innovative methodology to handle the complexity of events in medical event logs. Based on autoencoding, accurate labels are created by clustering similar events in latent space. Moreover, the explanation of created labels is provided by the decoding of its corresponding events. Tested on synthetic events, the method is able to find hidden clusters on sparse binary data, as well as accurately explain created labels. A case study on real healthcare data is performed. Results confirm the suitability of the method to extract knowledge from complex event logs representing patient pathways.

Objective: The "Bow-tie" optimal pathway discovery analysis uses large clinical event datasets to map clinical pathways and to visualize risks (improvement opportunities) before, and outcomes after, a specific clinical event. This proof-of-concept study assesses the use of NHS Hospital Episode Statistics (HES) in England as a potential clinical event dataset for this pathway discovery analysis approach. Materials and Methods: A metaheuristic optimization algorithm was used to perform the "bow-tie" analysis on HES event log data for sepsis (ICD-10 A40/A41) in 2016. Analysis of hospital episodes across inpatient and outpatient departments was performed for the period 730 days before and 365 days after the index sepsis hospitalization event. Results: HES data captured a sepsis event for 76 523 individuals (>13 years), relating to 580 000 coded events (across 220 sepsis and non-sepsis event classes). The "bow-tie" analysis identified several diagnoses that most frequently preceded hospitalization for sepsis, in line with the expectation that sepsis most frequently occurs in vulnerable populations. A diagnosis of pneumonia (5 290 patients) and urinary tract infections (UTIs; 2 057 patients) most often preceded the sepsis event, with recurrent UTIs acting as a potential indicative risk factor for sepsis. Discussion: This proof-of-concept study demonstrates that a "bow-tie" pathway discovery analysis of the HES database can be undertaken and provides clinical insights that, with further study, could help improve the identification and management of sepsis. The algorithm can now be more widely applied to HES data to undertake targeted clinical pathway analysis across multiple healthcare conditions.

PURPOSE: Immune checkpoint inhibitors substantially changed advanced non–small-cell lung cancer (aNSCLC) management and can lead to long-term survival. The aims of this study were (1) to use a machine learning method to establish a typology of treatment sequences on patients with aNSCLC who were alive 2 years after initiating a treatment with anti–programmed death-ligand 1 monoclonal antibody nivolumab and (2) to describe the patients' characteristics according to the typology of treatment sequences. MATERIALS AND METHODS: This retrospective observational study was based on data from the comprehensive French hospital discharge database for all patients with lung cancer with at least one line of platinum-based chemotherapy, starting nivolumab between January 1, 2015, and December 31, 2016, and alive 2 years after nivolumab treatment initiation. Patients were followed until December 31, 2018. A typology of most common treatment sequences was established using hierarchical clustering with time sequence analysis. RESULTS: Two thousand two hundred twelve study patients were, on average, 63.0 years old, 69.9% of them were men, and 61.9% had a nonsquamous cell carcinoma. During the 2 years after nivolumab treatment initiation, clusters of patients with four basic types of treatment sequences were identified: (1) almost continuous nivolumab treatment (44% of patients); (2) nivolumab most of the time followed by a treatment-free interval or a chemotherapy (15% of patients); and a short or medium nivolumab treatment, followed by (3) a long systemic treatment-free interval (17% of patients) or (4) a long chemotherapy (23% of patients). CONCLUSION: This machine learning approach enabled the identification of a typology of four representative treatment sequences observed in long-term survival. It was noted that most long-term survivors were treated with nivolumab for well over 1 year.