Predict Hospital-Acquired Conditions and Infections

It’s natural to expect that when a patient is admitted to the hospital, they will get better, not sicker. But patients can develop hospital-acquired conditions (HACs)—undesirable complications or medical conditions that were not present on admission and developed during their hospital stay. Unfortunately, HACs are common and costly. Approximately 2.5 million HACs occur annually in the U.S. among all inpatients over the age of 18 (1). Each year, Medicare levies substantial penalties on hospitals under the Hospital-Acquired Conditions Reduction Program—estimated at approximately $360 million (2).

Hospital-acquired infections (HAIs) represent a significant portion of all HACs and are among the leading causes of death in the United States (3). At any given time, one in every 31 hospitalized patients has a HAI, there are approximately 680,000 HAIs in U.S. acute care hospitals annually, and nearly 70,000 of these patients will die during their hospitalization (4,5). HAIs are also extremely costly and are responsible for between $28 and $33 billion in potentially preventable healthcare expenditures annually (3).

Size of the Problem

• 11% of patients with HAIs die during their hospitalization (5).
• 2.5 million HACs occur annually in the U.S. in inpatients over the age of 18 (1).
• 774 hospitals will face Medicare payment cuts in fiscal year 2021 under the HACRP (9).
• $30 billion is the potentially preventable annual expenditure attributed to HAIs (3).

‍

Patients with HAIs are also at increased risk for sepsis—the leading cause of both inpatient death and readmissions (6). Each year, at least 1.7 million adults in America develop sepsis, and nearly 270,000 die as a result (7). The AHRQ lists sepsis as the most expensive condition treated in the U.S., and the HHS recently estimated that healthcare costs associated with sepsis total more than $60 billion annually (8).

1. Targeted Prevention Strategies: Utilizing predictive analytics to identify high-risk patients can enable hospitals to deploy targeted interventions such as enhanced sanitization, specific patient education, and rigorous antimicrobial stewardship. This approach not only prevents the occurrence of HACs and HAIs but also reduces the associated healthcare costs.
2. Continuous Monitoring and Real-Time Analysis: By continuously monitoring patients' vital signs and other health indicators with AI, hospitals can detect early signs of complications. This real-time analysis facilitates immediate medical response, potentially preventing the escalation of conditions into more severe complications.
3. Predictive Model for Hospital-Acquired Conditions: We have developed a predictive model that uses a dataset to determine the likelihood that a patient will develop hospital-acquired conditions during their stay. This model incorporates key variables such as age, length of hospital stay, type of admission, comorbidities, and ICU stay to assess the risk of HACs. The primary goal of this model is to identify patients at high risk for HACs, allowing healthcare providers to implement preventive measures to reduce these risks and improve patient outcomes. By anticipating and addressing these risks, the model helps reduce the overall incidence of HACs, saving lives and minimizing unnecessary healthcare costs.

• Electronic Health Records: EHR data with comprehensive patient histories of vital signs and symptoms, problem lists and chief complaints, tests results, diagnoses and procedures, and prescriptions.
• Medical Claims: Data extracted from health insurance medical claims with details about dates and place of service, diagnosis codes, key procedures, use of medical equipment, and provider specialties.
• Social Needs Assessments: Self-reported data that identify an individual's specific needs and the acute social and economic challenges they are experiencing.

‍