Feature Engineering and Process Mining to Enable Hazard Detection in Health Information Technology.

In this work, we aim to enhance the reliability of health information technology (HIT) systems by detection of plausible HIT hazards in clinical order transactions. In the absence of well-defined event logs in corporate data warehouses, our proposed approach identifies relevant timestamped data fields that could indicate transactions in the clinical order life cycle generating raw event sequences. Subsequently, we adopt state transitions of the OASIS Human Task standard to map the raw event sequences and simplify the complex process that clinical radiology orders go through. We describe how the current approach provides the potential to investigate areas of improvement and potential hazards in HIT systems using process mining. The discussion concludes with a use case and opportunities for future applications.

Understanding barriers and facilitators to the use of Clinical Information Systems for intensive care units and Anesthesia Record Keeping: A rapid ethnography.

OBJECTIVE: This study evaluated the current use of commercial-off-the-shelf Clinical Information Systems (CIS) for intensive care units (ICUs) and Anesthesia Record Keeping (ARK) for operating rooms and post-anesthesia care recovery settings at three Veterans Affairs Medical Centers (VAMCs). Clinicians and administrative staff use these applications at bedside workstations, in operating rooms, at nursing stations, in physician's rooms, and in other various settings. The intention of a CIS or an ARK system is to facilitate creation of electronic records of data, assessments, and procedures from multiple medical devices. The US Department of Veterans Affairs (VA) Office of the Chief of Nursing Informatics sought to understand usage barriers and facilitators to optimize these systems in the future. Therefore, a human factors study was carried out to observe the CIS and ARK systems in use at three VAMCs in order to identify best practices and suggested improvements to currently implemented CIS and ARK systems. METHODS: We conducted a rapid ethnographic study of clinical end-users interacting with the CIS and ARK systems in the critical care and anesthesia care areas in each of three geographically distributed VAMCs. Two observers recorded interactions and/or interview responses from 88 CIS and ARK end-users. We coded and sorted into logical categories field notes from 69 shadowed participants. The team transcribed and combined data from key informant interviews with 19 additional participants with the observation data. We then integrated findings across observations into meaningful patterns and abstracted the data into themes, which translated directly to barriers to effective adoption and optimization of the CIS and ARK systems. RESULTS: Effective optimization of the CIS and ARK systems was impeded by: (1) integration issues with other software systems; (2) poor usability; (3) software challenges; (4) hardware challenges; (5) training concerns; (6) unclear roles and lack of coordination among stakeholders; and (7) insufficient technical support. Many of these barriers are multi-faceted and have associated sub-barriers, which are described in detail along with relevant quotes from participants. In addition, regionalized purchases of different CIS and ARK systems, as opposed to enterprise level purchases, contributed to some of the identified barriers. Facilitators to system use included (1) automation and (2) a dedicated facility-level CIS-ARK Coordinator. CONCLUSIONS: We identified barriers that explain some of the challenges with the optimization of the CIS and ARK commercial systems across the Veterans Health Administration (VHA). To help address these barriers, and evolve them into facilitators, we categorized report findings as (1) interface and system-level changes that vendors or VA healthcare systems can implement; (2) implementation factors under VA control and not under VA control; and (3) factors that may be used to inform future application purchases. We outline several recommendations for improved adoption of CIS and ARK systems and further recommend that human factors engineering and usability requirements become an integral part of VA health information technology (HIT) application procurement, customization, and implementation in order to help eliminate or mitigate some of the barriers of use identified in this study. Human factors engineering methods can be utilized to apply a user-centered approach to application requirements specification, application evaluation, system integration, and application implementation.

An analysis of electronic health record-related patient safety concerns.

OBJECTIVE: A recent Institute of Medicine report called for attention to safety issues related to electronic health records (EHRs). We analyzed EHR-related safety concerns reported within a large, integrated healthcare system. METHODS: The Informatics Patient Safety Office of the Veterans Health Administration (VA) maintains a non-punitive, voluntary reporting system to collect and investigate EHR-related safety concerns (ie, adverse events, potential events, and near misses). We analyzed completed investigations using an eight-dimension sociotechnical conceptual model that accounted for both technical and non-technical dimensions of safety. Using the framework analysis approach to qualitative data, we identified emergent and recurring safety concerns common to multiple reports. RESULTS: We extracted 100 consecutive, unique, closed investigations between August 2009 and May 2013 from 344 reported incidents. Seventy-four involved unsafe technology and 25 involved unsafe use of technology. A majority (70%) involved two or more model dimensions. Most often, non-technical dimensions such as workflow, policies, and personnel interacted in a complex fashion with technical dimensions such as software/hardware, content, and user interface to produce safety concerns. Most (94%) safety concerns related to either unmet data-display needs in the EHR (ie, displayed information available to the end user failed to reduce uncertainty or led to increased potential for patient harm), software upgrades or modifications, data transmission between components of the EHR, or 'hidden dependencies' within the EHR. DISCUSSION: EHR-related safety concerns involving both unsafe technology and unsafe use of technology persist long after 'go-live' and despite the sophisticated EHR infrastructure represented in our data source. Currently, few healthcare institutions have reporting and analysis capabilities similar to the VA. CONCLUSIONS: Because EHR-related safety concerns have complex sociotechnical origins, institutions with long-standing as well as recent EHR implementations should build a robust infrastructure to monitor and learn from them.