Alphadelphi, Inc.

Each year, the U.S. healthcare system spends approximately $1.65 trillion on treating patients with one or more chronic diseases, with expected expenditures potentially reaching $6 trillion by 2050. With chronic disease affecting 133 million Americans (40% of the nation), the need for disease management and prevention is immense (Apixio, 2019).  Healthcare spending is growing at an unsustainable rate, 4 percentage points faster than the economy, representing 18% of gross domestic product (GDP)(Roberts, 2020).  Rife with inefficiencies and waste, the healthcare system in the United States is ripe for change. What if there was a way to predict risk, coordinate complex care, and consolidate patients’ medical records?    

Paul Roberts, an RN case manager with 20 years of experience in the industry, answers this question with Alphadelphi, Inc. and proprietary software, called Pythos.  Pythos is case management software that uses artificial intelligence (AI) and machine learning principles and applies it to patient health records.  Pythos integrates information from the patient’s electronic health record (EHR), family history, current medical status, and genetic information (if available), to predict a patient’s medical risk and outcomes.  Machine learning, which is “a computational technique that uses algorithms to learn from historical datasets and make accurate predictions about the future. These algorithms are trained to look at specific variables, then develop models that predict events or find patterns in new data” (Apixio, 2019).  AI and machine learning takes unstructured data, such as that available in the physician’s notes within the patient’s EHR combined with lab results, vitals, the patient’s medication profile, and provides insights to the healthcare team to guide more effective care management activities and make predictions in the patient’s current and future health status. Machine learning will then advance to deep learning after the first few years, in order to generate more insightful predictions.  

Mr. Roberts, as a registered nurse (RN), certified rehabilitation registered nurse (CRRN) and certified case manager (CCM), is perfectly positioned to fully understand the industry and what improvements are needed.  His vision of having a coordinated healthcare system available for all and advocating for patients is the motivation behind his creation of the Pythos software. 

Using the Pythos software, medical case managers will be able to leverage the capabilities of AI learning to guide a patient’s care according to their individual needs.  The more knowledge case managers have of the patient, the more effective and thus the more cost-efficient they will be ensuring positive outcomes for their patients.  

Machine learning models can be applied to a wide variety of datasets.  For example, it can be “used to predict which hospital inpatients are most likely to be readmitted, flag patients who haven’t received appropriate preventive screenings, or identify patterns in prescribing behaviors within a specific medical system” (Apixio, 2019).  Based on a study from the U.S. Agency for Healthcare Research and Quality (AHRQ), an estimated 4.4 million hospital admissions totaling $30.8 billion could have been prevented. Of that $30.8 billion, nearly half of the costs were attributed to heart disease and diabetes complications – both chronic diseases that affect millions in this country (Apixio, 2019).  Pythos makes identifying these patients easy so that they can be targeted for education and preventive measures that will address their individual illnesses and keep them out of the hospital, ultimately improving the quality of their lives. It is estimated that at least 30% of current healthcare spending will be saved using this system. In the U.S. this equates to a savings of $1 Trillion annually, whereas global savings equates to $2.4 Trillion annually.