Improving the Patient Payment Experience
For a patient, paying for care is hard enough by itself, it shouldn’t also be complicated to understand the bill and make a payment. Billing and payment should be able to take the form of what works best for each patient. For the health system, leveraging technology allows increased flexibility to offer different ways to pay for the patient—improving satisfaction as well as the amount of money that can be collected.
$14M the amount of cost savings we expect to receive in the first year alone
5,000 hours the amount of time annually spent by staff to process credit card transactions
30% average drop in patient satisfaction from post-discharge through the billing process
Non Emergent Medical Transportation
Patients without access to reliable transportation may have to wait hours for transportation after a visit to the hospital, especially if they have complex needs such as a wheelchair or oxygen. In some cases, inability to get to regular checkups at the doctor or the pharmacy can negatively affect care.
We are identifying a transportation broker that will use software to match transportation with the patients who need it, when they need it, and according to their specific needs.
16,000 rides are provided annually across the BJC system
25% expected decrease in costs with the efficiency gained from using a broker
6 different modes of transportation, according to need.
Detecting Stress and Delivering Therapy with Smartwatches
Surgeries are often life changing events. Patients facing complex surgeries face mental health concerns such as chronic stress, anxiety and depression. Such mental health stressors affect the post-surgical recovery causing persistent post-surgical pain, related opioid dependence, cognitive and functional declines.
For this Big Idea, we propose to develop a comprehensive infrastructure for concomitant stress detection and mindfulness therapy delivery using commercial smartwatches.
No. of surgical procedures performed worldwide every year
Percentage of US adults affected by anxiety disorders every year.
Percentage of US adults owning a smartwatch
Connecting Clinicians with Supply Inventory Management via Alexa
Clinician time is extremely valuable. Non-productive tasks, such as gathering supplies, consume time better spent with the patient. Each division carries highly variable supply inventories in the supply room. Thus, clinicians must search for needed supplies to care for patients, which is particularly stressful in urgent situations with supplies used less frequently.
This project will test the feasibility of streamlining the supply retrieval process through the use of voice assistance, Alexa. The clinician will be able to ask Alexa the location of the supply and be directed immediately to the correct location.
Minutes every 12 hours spent by nurses on supply retrieval.
Safety Events related to Inadequate Supplies at BJH in 2018.
Safety Events related to Inadequate Supplies across BJC in 2018.
Remote Telemonitoring of Pancreas Surgery Patients
This clinical trial leverages remote telemonitoring in conjunction with machine learning to improve outcomes among patients undergoing pancreas surgery. Using wearables for remote tracking of activity and heart rate our goals are to: (1) improve prehabilitation before surgery, (2) guide our Enhanced Recovery After Surgery (ERAS) progressive mobility efforts in the postoperative inpatient period, and (3) detect impending complications after discharge from the hospital. This project will lead to improved patient outcomes and reduced cost to the health care system.
Rate of complications in pancreas surgery patients
Average increase in cost to the hospital when a pancreas surgery patient develops complications
Accuracy of predicting impending complications in a preliminary trial of patients with congestive heart failure
Machine Learning Augmented Handoff Report
In efforts to adhere to the National Patient Safety Goals (NSPG) for handoff standardization, EHR-based handoff templates are designed as a “one-size fits-all” solution. However, these rigid tools fail to: (a) address the handoff needs and workflows unique to the different healthcare disciplines in the various settings, (b) tailor to patient cases and related risks; (c) foster the core functions of handoffs such as information processing, distributed cognition, common ground, and anticipatory management.
We propose to address these failures within the context of postoperative handoffs (operating room to intensive care unit). In this study, our goal is three-fold: First, use machine learning (ML) techniques to predict postoperative patient risks by harnessing preoperative and intraoperative real-time data from EHR. Second, adopt a user-centered design approach to develop a flexibly-standardized, user-friendly handoff report. Third, incorporate features in the handoff report that supports the core functions of handoffs.
Of surgical patient handoffs are vulnerable to errors
Of medical errors due to handoff failures
Medical errors are the third leading cause of death in the U.S
Artificial intelligence to predict life-threatening infections
Sepsis is the body’s dysregulated response to a severe infection that can result in multi-organ failure and death. The cornerstone of treatment is early and effective antimicrobial therapy.
Using cutting-edge advancements in machine learning and artificial intelligence, this project will develop an algorithm to predict sepsis before patients even meet traditional diagnostic criteria.
mortality increase for every 1-hour delay in treatment.
of all hospital deaths are attributable to sepsis.
are spent each year treating sepsis in the US.
Developing a High Quality Palliative Care Screening Instrument
Palliative care is one of the few health care interventions that has been consistently shown to improve patient outcomes and quality of life while reducing unnecessary utilization and total cost of care. Unfortunately, providers often fail to identify the patients most likely to benefit until it is too late.
Combining real time information obtained directly from the medical chart with key administrative data using advanced neural networks, we will be better able to identify appropriate patients and enhance support for our patients and families.
Americans live with serious illness
Savings per patient associated with inpatient palliative care referral
of BJH inpatient admissions are referred to palliative care
Public Health Dashboard: Data for Health
The Public Health Dashboard project originated from a partnership between the Institute for Public Health, the Health Systems Innovation Lab, and the Institute for Informatics to leverage and visually display clinical, environmental, behavioral, public health, genomic, and other sources of data to offer a complete picture of health for the St. Louis Region. Stakeholder discussions have illuminated the need to better understand the context of individuals in our region with certain conditions as well as to provide them with relevant resources for managing and treating their condition.
Image reflects chlamydia rates per 100,000 persons by zip code (darker color indicates a higher rate)
St. Louis ranks 9th nationally in its rate of gonorrhea and 16th in its rate of chlamydia. Many patients utilize the emergency department for diagnosis and treatment of these infections.
40% of these patients are self-pay (indicating that high-risk underserved patients go to the emergency department for their care).
Nurses’ time allocation of nursing activities and their stress
Electronic health records (EHR) system adoption rose from 10% to 80% in the United States. Studies found increased documentation time for nurses as well as stress and burnout.
We are conducting a time-motion study to observe and record nursing activities including EHR usage, as well as their stress. The study will quantify and visualize nurses’ time allocation on communication, hands-on tasks, and locations, and discover nurses’ stress related to particular nursing activities.
Earlier work found that nurses spend 30% of their time in the electronic health record (EHR) system.
In an American Nurses Association survey, 74% of nurses voted stress as their number one concern.