Using Predictive Analytic Tools to Improve Care Transitions

Using Predictive Analytic Tools to Improve Care Transitions

Summary

Tenet hospitals use predictive analytic tools to support patient transitions from hospital to community care services. This article will provide an overview of the tools used, how the need for the tools was identified, how they were implemented, and lessons learned.

Background

Long gone are the days when hospital care coordinators assessed patient discharge needs using a combination of chart review, knowledge of payer benefits and community resources, plus their own years of care coordination experience, to magically come up with a post-hospital plan. Foundational tools today include structured assessments with core content conducted via patient/caregiver interviews and dialogue to address patient goals and preferences. But are those enough? Some level of mystery remains in the black box when moving from assessment and evaluation to plan for transition from the hospital to community setting.

"The probabilities are not meant to be prescriptive but rather provide a reference point for how often similar patients were discharged with a given disposition"

Tenet Health is a community built on care, which means that we want to do everything we can to partner with patients, caregivers and providers to identify and support successful transition from the hospital to the next care setting. We sought a more reliable way to guide care coordinators and patients as they planned for the most appropriate level of care when transitioning from the hospital. Our goal was to augment and guide the care coordinator assessment process with predictive analytics that utilize multiple data sources and encounters to inform the decision-making process with objective data.

The Tool

Tenet data scientists created a Readmission Risk Report (RaR) which aggregates data from the electronic medical record as well as administrative and financial systems. The objective of the RaR Report is to take a broad set of patient information and distill it down to a score depicting potential for an extended length of stay and readmission risk. The report also provides important contextual information related to a patient’s Emergency Department and Hospital utilization within the prior 90 days.

The RaR Report includes a Discharge Planning Probability indicator for each patient that gives an estimate of how often patients with characteristics similar to the subject patient are discharged to a Skilled Nursing Facility (SNF) or Rehabilitation (RHB) facility (Rehab/SNF Probability), discharged with home health (Home Health Probability), or discharged home without additional services (Home Probability). These estimates are derived from a machine learning model that emerged after considering over 100 patient variables and developed using more than 300,000 previous inpatient discharges. The scores are then presented along with contextual information that helps clinicians provide targeted interventions for the patient. Broadly these variables can be classified into nine categories including: Diagnoses, Procedures, Labs, Vitals, Medications, Social Determinants, Nursing Assessment, Current Admission and Past Encounters.

 

The probabilities are not meant to be prescriptive but rather provide a reference point for how often similar patients were discharged with a given disposition.

Hospital directors download the report each day and share it with the hospital care coordinators each morning before staff begins rounds on their assigned patients. Nurses and social work staff responsible for transition assessment and planning use the report daily to guide their discussions with patients, caregivers and the interdisciplinary care team. The information in the report is a valuable source of actionable information that is integrated into the daily interdisciplinary huddle, allowing the team to proactively work to optimize post-hospital recovery and mitigate risk of readmission using the Discharge Planning Probability as a guide. The hospital care coordinators use the information at daily huddles and in patient conferences to:

• Discuss the expected length of stay and target discharge date based on the Working Diagnostic Related Group (WDRG)
• Identify patient risk for an extended length of stay or readmission after discharge
• Assess patient progress and barriers to discharge by the target discharge date
• Identify the patient’s functional abilities, services and/or equipment needed for post-hospital care
• Discuss the Discharge Planning Probability with the patient, caregivers and physician(s) involved in the patient’s care
• Integrate patient/caregiver goals and preferences for the transition plan and make referrals to post-acute providers if needed
• Provide education regarding care needs, post-hospital caregiver expectations, and health plan benefits

Lessons Learned

Implementation

The report is housed on Tenet’s internal business analytics site. Access is granted via internal security approval process to protect patient health information. The report methodology, content and utilization was shared with Tenet hospital Directors of Case Management and Directors of Clinical Quality Improvement via online education sessions. The sessions outlined methods used to create the report as well as guidance on how to use the information. Hospital participants were provided with a copy of the educational presentation and a user guide that they could share with staff who would be accessing and using the report.

The Readmission Risk (RaR) report with the Discharge Planning Probability has been in use across Tenet hospitals for three years. There are three main lessons learned for us in the change optimization of this tool that can be grouped under user adoption, user education and user reinforcement.

• User Adoption – We originally educated and made the report available to Director level staff at the hospital only, the Director of Case Management and the Director of Clinical Quality Improvement. The rationale was that due to the confidential patient information included on the report we needed to limit access. When we monitored report utilization we saw some hospitals were high adopters and some had not used the report at all.

Since the intended users were the nurse and social work staff that were responsible for patient transition assessment and planning, we needed to find a way to get the report in to the hands of the users. So we rescheduled education sessions to include frontline staff and expanded access to grant staff ability to access and download the report. We still required access to be granted through security request process but expanded the approval to include the nurse and social work care coordinators for whom the tools were relevant to their patient service role.

• User Education – As noted above we originally included the key hospital director-level staff. And then we expanded to the care coordination staff. Once the nurse and social work staff started integrating the information in to the daily huddles we realized the need to educate the rest of the care team, specifically nurses and physicians, on the report content and use in guiding the plan for discharge. The concept of “Discharge Probability” is difficult for some to grasp without the full background on the methodology used to make the determination. The information was integrated into the education for the daily interdisciplinary team huddle. The reality is that the Discharge Planning Probability is mostly used by the care coordinators but the care team needs to have some understanding of the concept to assist in planning the best patient pathway post-discharge.

• User Reinforcement – Monitoring and management of both leading and lagging indicators are critical to driving performance improvement. Tenet manages several leading indicators related to the transition planning process. An example of a leading indicator is the initial Transition Assessment (aka discharge plan) which includes identification of patient goals and preferences as well as the initial plan for post hospital care. Tenet monitors timeliness of completion within 24 and 48 hours of patient admission. An example of a lagging indicator is the monitoring of readmission rates within Tenet hospitals as well as publicly reported data for all readmissions. Managing leading indicators and monitoring lagging indicators are critical to driving performance improvement.

Check out: Top Healthcare Analytics Companies

Read Also

Artificial Intelligence and the Lost Art of Auscultation

Artificial Intelligence and the Lost Art of Auscultation

Edward Kersh, Medical Director, Sutter Care
Optimal Healthcare Strategy Design in The Digital Era

Optimal Healthcare Strategy Design in The Digital Era

Ingrid Vasiliu-Feltes, Chief Quality and Innovation Officer, MEDNAX
Proactively Engaging Patients Post Discharge

Proactively Engaging Patients Post Discharge

David Collins, MHA Telehealth Practice Administrator, VCU Health and Vimal Mishra, MD Medical Director, VCU Health
Mobile Health Applications Enable Data-Driven Diabetes Care

Mobile Health Applications Enable Data-Driven Diabetes Care

Osama Hamdy, MD, PhD, Medical Director of Obesity Clinical Program and Inpatient Diabetes Program, Joslin Diabetes Center, Harvard Medical School Sahar Ashrafzadeh, AB, Researcher, Department of Clinical and Behavioral Research, Joslin Diabetes Center
Sitting is The New Smoking, As Mobile Fundamentally Disrupts Health Care... Again

Sitting is The New Smoking, As Mobile Fundamentally Disrupts Health Care... Again

Geoff McCleary, VP, Group Director, Mobile Strategy & Innovation, Digitas Health Lifebrands