Patrick Tighe

Autonomously Monitors Patients, Enabling More Timely Interventions While Reducing Caretakers’ Workload

This intelligent patient monitoring system uses an array of wearable sensors and cameras combined with machine-learning platforms to conduct autonomous, continuous observation and analysis of patient status and environmental conditions in the intensive care unit (ICU) or assisted living facility. The market for patient monitoring systems should exceed $25 billion by 2023. In critical care environments, patients require extensive monitoring of their physiological state to inform treatment decisions and ensure proper recovery. While much of a patient’s assessment in the ICU happens automatically through various bedside devices, available monitoring systems do not automatically quantify certain relevant environmental factors, such as noise or light levels, frequency of sleep-disrupting visitations, and patient delirium. Other aspects of ICU care, such as assessing pain or physical functionality, require manual evaluations, which are quite subjective, lack precision and increase the already overburdened hospital staff workload. Additionally, the intermittent nature of manual observations can inhibit medical interventions at critical times.

Researchers at the University of Florida have developed an autonomous ICU monitoring system that captures important patient information and environmental conditions and characterizes the physiological state of patients. The system uses a network of sensors and visual criteria to monitor and automatically analyze data such as a patient’s facial expressions, visitation frequency, and the room’s light and noise levels, providing continuous and automatic quantification of ICU factors for more timely medical interventions.

Application

Autonomous ICU patient monitoring system that continuously collects and analyzes pervasive input and physiological information in real-time

Advantages

• Continuously monitors an ICU patient’s physiological functionality, enabling automatic and granular assessment to enable more rapid medical interventions
• Analyzes a patient’s ICU environment, quantifying environmental factors
• Applies pervasive sensing and machine learning to patient monitoring, facilitating high-precision, objective evaluation of a patient’s physiological state
• Integrates with the infrastructure of conventional ICUs and other long-term care facilities, augmenting patient observation capabilities while reducing nurse workload

Technology

This autonomous patient monitoring system employs pervasive sensing and machine learning procedures to evaluate an ICU patient’s environment and physiological status. A network of wearable sensors, room light and noise sensors, and high-resolution cameras continuously capture data on a patients and their environment in the ICU. Machine learning and statistical software analyzes the visual information, such as patient posture, expressions, and physical movements. In conjunction with the gathered environmental conditions and with reference to the patient’s vital signs and electronic health record, this automated analysis enables the system to evaluate the physiological state of a patient, including quantifying pain levels or identifying conditions such as delirium.

Improves Efficiency in Staffing and Clinic Offerings in Healthcare Operations

This web application is an operations management system for hospitals and other healthcare providers, improving efficiency in staffing and clinic offerings based on relative value units. An estimated fifth of all money spent on hospital expenses is wasted due to over-staffing and other inefficiencies. Researchers at the University of Florida have developed a web app that allows hospitals and other healthcare providers to input variables about their current services and management operations to better staff their facilities and tailor their offerings. Such simulations further allow demonstration of projections for opportunity costs and revenue across multiple payor mixtures.

Application

Web app utilizing given inputs to uncover the optimal patient offerings and staffing for healthcare providers

Advantages

• Allows for more specific inputs than available operations management software, producing more useful outputs

Technology

This application runs hospital inputs through an algorithm to determine the most efficient offerings for a hospital or healthcare service provider. Coded to demonstrate the economics of an acute pain service, the web app allows users to input custom mixtures of nerve block/rounding encounter types, the relative value units generated per event, and the payor mixture of reimbursement per relative value unit. The app demonstrates changes in relative value unit/reimbursement based on increasing numbers of blocks/encounters using the inputted information. This algorithm-based web app, which permits calculation and demonstration of opportunity costs in the face of both direct and indirect sources of value, is applicable to numerous aspects of healthcare.

Optimizes Healthcare Staffing and Lowers Hospital Operating Costs

This web application enables efficient management of healthcare provider staffing in academic hospitals. Increasing healthcare costs are a driving force behind change in the medical goods and services industry, which has estimated costs above $2.8 trillion per year in the United States. Approximately 30 percent of hospital expenses – over $700 per inpatient per day – may be wasted funds associated with poorly managed provider staffing and other inefficiencies. The ability of a hospital department to accurately assess its staffing needs, using resource-based reimbursement parameters, is likely to be especially important in efforts to control spending and limit waste. Employing an anesthesiologist staffing model, researchers at the University of Florida have developed a web app that uses relative value units (RVUs) to predict changes in provider staffing needs for user-selected mixtures of medical services. This software will help academic anesthesia departments optimize faculty utilization and may be adapted to enable efficient staffing procedures in other healthcare environments in which RVUs are routinely used.

Application

Web app that determines the most optimal staffing of healthcare providers in a variety of treatment contexts

Advantages

• Aids in proper staffing of healthcare providers, closely linking departmental cost structure with standard fee reimbursement schedules
• Utilizes a variety of user-selected medical encounters as input, allowing administrators to predict staffing needs for a broad range of patient care scenarios
• Demonstrates effectiveness using a model of anesthesia departments, but can be adapted to enable efficient staffing in other healthcare environments where RVUs are used

Technology

This web application is coded to demonstrate the impact of several financial variables on the staffing of academic anesthesiology departments. The web app inputs custom mixtures of nerve block/rounding encounter types, RVUs generated per event, and payer mixture of reimbursement per RVU. The web app then demonstrates changes in RVU/reimbursement based upon increasing numbers of blocks/encounters, utilizing the user-selected information. This allows a department to highlight areas of increased institutional support needs, as well as to determine whether the department is overstaffed or understaffed at any time.