Improving Healthcare Operations Using Process Data Mining

Editor's Notes

• #2: Do we know what a drug or diagnosis code means and does it mean the same in different EHRs? Similarly, do we know what an EHR event in an EHR event log means and does it mean the same in different systems. This last will be important for comparing process models, as EHRs are so user- customizable. “Check Meds” in one EHR might be called “Medications” in another. What exactly does “Check Meds” mean? Where, exactly, does it fit in a hierarchy of tasks, such as “checking” other things besides medications or involvement of medications in other activities besides “checking”? Is asking a patient about medications (or retrieving the medication list from online) an example of “Check Meds”? Is there a difference in the ordering and frequency of activities between patients that were treated by either a high- or low-volume surgeon? (control-flow perspective) Is there a difference in resource involvement between patients that were treated by either a high- or low-volume surgeon? (organisational perspective) Is there a difference in time-related performance between patients that were treated by either a high- or low-volume surgeon? (performance perspective) Is there a difference in the ordering and frequency of activities between patients that had surgical continuity and patients that had surgical discontinuity? (control-flow perspective) 2. Is there a difference in resource involvement between patients that had surgical continuity and patients that had surgical discontinuity? (organisational perspective) 3. Is there a difference in time-related performance between patients that had surgical continuity and patients that had surgical discontinuity? (performance perspective) Is there a difference in the ordering and frequency of activities between patients that had a throughput time of 80 and 40 minutes or less in respectively the pre-operative and final postoperative examination and patients with a longer throughput time? Is there a difference in organizational resource involvement between that had a throughput time of 80 and 40 minutes or less in respectively the pre-operative and final postoperative examination and patients with a longer throughput time? Is there a difference in time-related performance between patients that had a throughput time of 80 and 40 minutes or less in respectively the pre-operative and final postoperative examination and patients with a longer throughput time? It is apparent that the business processes in the medical domain are dynamic, ad-hoc, unstructured and multi-disciplinary in nature. he goal of clustering is to obtain homogeneous group of patients.
• #12: Discover actual behavior of people, organization, machines and relate to modeled behavior. Insights showing reality is very different from perceptions, opinions, and beliefs Correlation of Millions of ad-hoc events provide clue for standardization and better prepare to handle ad-hoc events. Different people have different views about a same process. Information about the process mat be incomplete. Discover actual behavior of people, organization, and machines and relate to modeled behavior. Correlate millions of ad-hoc events showing how reality is different from perceptions, opinions, and beliefs. Provide clue for standardization and better prepare to handle ad-hoc events.
• #14: Better use of the capacity to track patient flow through the health care system is a logical application, with potential to improve understanding of patterns of patient demand, provider supply, and bottlenecks to patient flow, and, as a result, improved revenues, hospital performance, and patient care. However, the success of these methods depends on their application simultaneously in every part of an interconnected system rather than being applied piecemeal to distinct individual processes, departments, or service lines. The notion of an integrated approach is a core concept for timely delivery of health care.
• #15: Optimizing performance requires measuring the demand, capacity, and flow into and out of each node within the system, and system-wide assessments and adjustments are required to improve the overall collection of steps, including such steps as consolidating or removing processes in order to streamline patient service flow. Systems strategies in health care delivery involve the use of scientific insights to illuminate the interdependencies of processes and elements and the effects of these interdependencies on health outcomes. Some of the causes of prolonged wait times are inefficiencies in operation, in care coordination, and in health care organizational culture that result in flow disruption, the underuse of resources, and an imbalance between the demand of patients to be seen and the supply of providers, facilities, and alternative strategies to care for them at any given time. Identify and quantify the types of variability in patient flow (demand) and the resources available to different patient groups (supply) he committee also enlisted the leaders of five institutions—Denver Health, Geisinger Health System, Kaiser Permanente, Seattle Children’s Hospital, and ThedaCare Some of the causes of prolonged wait times are inefficiencies in operation, in care coordination, and in health care organizational culture that result in flow disruption, the underuse of resources, and an imbalance between the demand of patients to be seen and the supply of providers, facilities, and alternative strategies to care for them at any given time. development, redesign, implementation, and delivery of such technology-based services. The health care system is a complex collection of interacting elements, each of which affects the others in myriad ways. Effectively dealing with any health care system issue—especially as basic as scheduling and access— requires dealing with the various system dynamics in a coordinated way that takes into account how changes in one area will affect the functions in other areas. That is, it requires systems strategies and approaches. Common to each of these practice areas is the integrative dimension. A systems approach emphasizes integration of all the systems and subsystems involved in a particular outcome. Adjusting each component of a system separately does not lead to an overall improved system. A health information technology infrastructure, including the creation and implementation of electronic health records (EHRs), is designed to generate data that will enhance the quality of patient care. Better use of the capacity to track patient flow through the health care system is a logical application, with potential to improve understanding of patterns of patient demand, provider supply, and bottlenecks to patient flow, and, as a result, improved revenues, hospital performance, and patient care. Several aspects of health care scheduling and access that should be measured and for which standards should be identified include: patient and family experience and satisfaction; care match with patient goals; scheduling practices, patterns, and wait times; cycle times, provision and performance experience for alternative care models (e.g., telehealth and other remote site services); and effective care continuity. analysis of data trends and predictions, and the integration of real-time monitoring of operations. Transparency helps employees understand the relevance and impact of change, informs and motivates their actions (on access, scheduling, or the other important elements of the care process), and helps organizations track the progress that they are making toward the desired new culture. Applied to scheduling and access, transparency about operational processes and their effectiveness can facilitate identification of delays and their causes, and also the progress made to reduce those delays. Finally, transparency facilitates messaging that creates organizational consistency—when everyone hears the same message from their leaders, they are motivated to respond in similar ways, and this behavior change can reinforce culture change.
• #22: A defining characteristic of modern health care is the rapidly accelerating increase in information that is available to assist with the delivery of care and system management. Time oriented data, 2. High diversity, 3. Some data is functional others are event logs generated by machines. Data came from activities which are part of sequential process Data is timestamped Activities are interdependent discrete events Machine data is generated by many different sources within the healthcare IT infrastructure. These sources include healthcare specific data sources such as electronic health record (EHR) systems, HL7 messaging, and connected medical devices. The data sources include core IT systems that support different applications such as desktops, servers, storage and network devices. Finally, they include all the patient facing applications and systems – portals, billing systems, claim management systems. Machine data generated by this infrastructure shares the core characteristics of big data – lot of data (high volume), created rapidly (high velocity), from different sources (variety), and data that changes over time (variability). Getting timely and relevant insight into this data can be a source of huge value for the healthcare ecosystem.
• #23: Subjects, locations, users, different data governance rules and standards that may conflict with each other
• #30: Data Science: validate your assumptions, formulate your hypotheses and test it, find simple principles that may have large impacts and generalized across the population.
• #31: End to End Value stream: Sequential time oriented tasks, resources are dependent on each other, multiple functional disciplines Value each others time and contributions. Any production problems would be quickly detected and corrected.
• #37: Threats follow the steps at the top right -to-to enter an org and exfiltrate data. To spot this you need to connect the dots as they move through this process. To do this you need data from the 4 data source categories on the far left. Examples are to the right. Note – “malware sandbox” includes FireEye and Palo Alto Network’s Wildfire technology which detonates email and web-based payloads and attachments and links in a virtual sandbox to see what they do & if they are malicious. Sometimes this category is also called “payload analysis” or “advanced malware detection”. ETDR is Endpoint Threat Detection and Response, an emerging category of next-gen endpoint technology. Cyvera (now part of Palo Alto Networks), Carbon Black (part of Bit9), RSA ECAT, Bromium, and Mandiant MIR fall into this category. Tell this slide perhaps as a “story” where you start with an alert at top (threat intel) and then pivot and use the other data sources to complete the investigation. See the appendix slide with a sample story.
• #42: One reason for agility is handling of data in scale using parallel data processing techniques. And lastly, we enable operational integration- two ways 1) speed of computations, 2) second is system integration through REST API support.
• #43: Splunk products are being used for data volumes ranging from gigabytes to hundreds of terabytes per day. Splunk software and cloud services reliably collects and indexes machine data, from a single source to tens of thousands of sources. All in real time. Once data is in Splunk Enterprise, you can search, analyze, report on and share insights form your data. The Splunk Enterprise platform is optimized for real-time, low-latency and interactivity, making it easy to explore, analyze and visualize your data. This is described as Operational Intelligence. The insights gained from machine data support a number of use cases and can drive value across your organization. [In North America] Splunk Cloud is available in North America and offers Splunk Enterprise as a cloud-based service – essentially empowering you with Operational Intelligence without any operational effort.
• #53: algorithm=LLB means “bivariate local level”
• #54: Vmware – House of Demos app. VM forest, esx server. Status of VMs when you click on particular one. One of the most useful types of visualizations is a “Sankey diagram”, which is used to describe flows through systems. These can be customer flows through marketing or sales funnels, traffic flows through the actual network, energy flows through a physical system, capital flows through a financial system, etc. It’s a very streamlined form of visualization that cuts out everything unrelated to “flow”. Technically, this is a graph visualization: the nodes are smushed to these bars along the side, and edges are represented by these fat bars connecting nodes. The width of a node is proportional to the volume of flow in and out of the node, and the width of an edge is proportional to the flow from the start node to the end node.
• #55: Customer journey: convert, repeat Mobile Patent Suits Dashed links are resolved suits; green links are licensing. “Thomson Reuters published a rather abysmal infographic showing the "bowl of spaghetti" that is current flurry of patent-related suits in the mobile communications industry. So, inspired by a comment by John Firebaugh, I remade the visualization to better convey the network. That company in the center? Yeah, it's the world's largest, so little wonder it has the most incoming suits.” mbostock’s block #1153292 August 18, 2011 http://bl.ocks.org/mbostock/1153292
• #56: Differentiate normal sequences vs. abnormal sequences or attributions. Reveal normal patterns of patient care by medical condition/ by providers/by drug/by medical equipment and corresponding expenditures. Use the acquired knowledge to correlate current events. Patterns outside these norms receive special attention and require validation by human investigators.
• #60: Case in point: http://www.wolframalpha.com/input/?i=diabetes
• #66: Alerts are triggered when certain conditions are met by the results of the search upon which it is based. Alerts can be based on both historical and real-time searches. When an alert is triggered, it performs an alert action. This action can be the sending of the alert information to a designated set of email addresses, or the posting of the alert information to an RSS feed. Alerts can also be set up to run a custom script when they are triggered. You can base these alerts on a wide range of threshold and trend-based scenarios, including empty shopping carts, brute force firewall attacks, and server system errors.