Predictive Analytics enabled by Medical Device Integration

How can medical device integration enhance prediction?

Data are the heart of decision making. The old adage “what cannot be measured cannot be controlled” is apt here. Historically, clinically quantifiable benefits of connected medical devices within the healthcare enterprise have been measured in terms of time-in-motion studies and workflow relating to time saving associated with accomplish a specific task or end goal. These are valid measures. Yet, the question remains as to whether there is something more tangible clinically that can be used as a measure of effectiveness related to medical device integration. The analysis of data made available from these sources is temporal in nature (i.e., time-varying and collected over time), is multidimensional (i.e., is a vector and represents the patient cardiovascular and respiratory system evolution over time), and is objective if collected automatically from the bedside.

Are Data Access is Key to Improved Prediction and Predictive Analytics?

The attached white paper captures some of the references and measures for improvement relative to medical device integration. Prediction of patient clinical outcome has been the subject of much research and many papers over the years. The difference between large scale data mining and predictive analytics in this context is that data from medical devices are multidimensional time series. Hence, temporal trends in behavior as measured by patient state changes over time provide the ability to track how a patient is “evolving” with time.

The figure below is from a presentation (“FDA Regulatory Submission Prototype Use Case”) I gave at the 2nd Annual Medical Connectivity Conference (San Diego). The figure depicts multiple sources of medical device data, from physiologic monitors to mechanical ventilators to infusion pumps and laboratory systems. The data from each of these medical devices are brought forward to an integrator, whereupon the data can be combined, processed, analyzed and then the output of which can be individual indices, measures, or time predictions. These outputs are, in ensemble, the objective measures of the patient, time-based, and comparative. The scope of the analysis is limited only by the needs and imagination of the researcher and the clinical end user.

What types of algorithms can be fed using data from these sources?

  • Weaning algorithms (i.e., weaning from post-operative mechanical ventilation)
  • Sepsis algorithms (i.e., modified early warning scores combining vital signs, laboratory and visual observations)
  • Respiratory sufficiency assessments and ventilator acquired events (e.g.: ARDS, COPD, PCA management, Extubation Criteria, VAP, etc.)

Many other methods and analysis can be performed, as well, to provide predictive assessments of the patient while in-situ in the critical care, medical surgical, or operating room.

Autonomic Heart Controller Device Concept

What is an Autonomic Heart Rate Controller?

The idea for extending the performance of left-ventricular assist devices (LVADs) occurred to me more than 15 years ago. The idea led me to write a white paper at that time which has been maintained and archived on this web site.

Discussions regarding heart rate variability (HRV) caused me to research a conceptual controller for autonomic, chemoreceptor-based sinoatrial heart control. As HRV is affected by sympathetic and parasympathetic control, this fact reminded me of a paper (unpublished) which I had written 14 years ago. While I included a web-adaptation of this paper very early in the history of the web log, I never included the actual paper itself. Much has transpired over the years in the regard to medical device integration, control and research into physiologic monitoring. Yet, I have not seen any writing in particular associated or closely related to the topic at hand.

Heart Rate Autonomic Control White Paper

Originally written in August 2002, the attached white paper presents a concept for a mechanism to automatically controller for heart rate pacing and contractile force (stroke volume) of either an artificial left ventricular assist device (LVAD) or a patient’s own heart who has experienced degenerative performance of the Sinoatrial node.

Autonomic control is based on the hormonal action of concentrations of catecholamines within the blood stream. These, in turn, influence the sinoatrial node through uptake. The concept laid out in the attached paper “operates” by analyzing the chemical nature of the epinephrine, norepinephrine, and dopamine content of the return blood flow through the superior vena cava and then using this information via cyclic voltammetry, neural network control, and feedback to the pacing device to control the heart rate of the assist device.

Why Autonomic Control is Potentially Interesting?

The basic premise of left ventricular assist devices (LVAD) and in heart pacing in general is to provide enough contractile force to move blood throughout the system. Most systems these days rely upon vasodilation, which is related to hormones as well as work. Yet, heart contractility is also related to emotion and release of hormones which are unrelated to direct movement or action of the human body. Hence, the idea was to accommodate a more “realistic” concept that took into account not only the contractile or vasodilation / vasoconstriction aspects of the arteries and veins, but also the hormonal changes measured through catecholamine changes in the blood stream. It is recognized that the attached paper is very raw and, clinically, it is somewhat naive. Yet, the objective was to present the idea as a potential starting point for research and, eventually, a product that could extend the performance of existing LVADs to support more human-like, natural behavior of artificial hearts.

Update on measurement of blood enzymes to support autonomic control:

Recently, a team at Ecole Polytechnique Federale de Lausanne (EPFL) in Switzerland developed an implant to monitor chemicals in the blood. This implant, according to this recent article is reportedly the world’s smallest at 14 mm and measures a maximum of 5 indicators to include troponin, lactase, glucose, ATP, to show whether a heart attack has occurred or to track (in the case of diabetic patients) blood enzymes and protein levels. The information can subsequently be transmitted via Bluetooth to a smartphone for online tracking.

This work is encouraging as it lays the foundation for real-time sensing, data collection and analysis at a level that is necessary for more accurate modeling and monitoring of cardiovascular systems. Such work can lead to earlier detection and more accurate prostheses — particularly, artificial hearts utilizing autonomic control to augment heart rate pacing– as well as more accurate clinical decision support methods that can determine whether patients have experienced critical events. I can see applications to earlier stroke detection where time-is-brain. Such real-time autonomic methods, when integrated with mobile technology and health information technology, can lead to great advances in patient care management through early warning resulting in early intervention.