Agenda

Mike will address the topic of the observed effect of the COVID-19 public policies that have reduced the mobility of countries around the world. With global mobility data joined to case data he will quantify when and by how much the lock-downs have mitigated the spread of this novel disease. The original rationale for social distancing was to mitigate peak loads on health care service delivery and buy time for the development of treatments. While the early reductions in mobility had some of their intended effect, the evidence of mitigating the COVID-19 spread shortly before and then beyond the peak has dropped to zero. The drivers of this phenomenon and public health policy implications will be discussed.

Healthcare organizations make significant investments in care interventions (e.g., care management) but are often unable to determine if the intervention had an impact on cost and utilization metrics (e.g., PMPM, admissions). This is due to an inability to perform an analysis that captures the true effect of an intervention. Front Health developed an Impact Tracker using propensity score matching and pretest-posttest cohort analysis to measure the significance of the effect that clinical interventions had on patient outcomes. We’ll discuss how the Impact Tracker measured the impact of Annual Wellness Visits on patient outcomes in a Medicare Shared Savings Program.

Join Vickie Rice, VP of Strategic Analytics for CareATC, to learn how this employer-sponsored primary care company
is using cognitive machine learning to shape its response to COVID-19.  From predicting where resources will be needed and finding the best locations to establish pop-up testing sites to identifying those in their population that are most at risk for mortality
and morbidity if infected, CareATC is relying on AI to make key decisions in shaping its response to this healthcare crisis.  In this session, we’ll review the predictive models utilized and learn about the practical applications that turned this science into
true life-saving measures.

Predictive Analytic tools and techniques have revolutionized and improved outcomes in multiple industries. Yet, within the Healthcare industry there can be multiple barriers to overcome.

Technical barriers can slow model deployment, cultural barriers can impede communication of results, and rare events can make it difficult to show significant improvement over a typical pilot project timeframe. Learn how the University of Virginia Health System has developed a real-time predictive analytics visualization platform, used interpretable machine learning techniques to communication results, and developed a novel upstream improvement metric to speed process improvement.

Blood, platelets and other transferable fluids are critical for patient health –particularly during trauma treatment, surgery and chemotherapy. Every day OneBlood collects, processes and delivers thousands of units of blood and blood products; keeping hospitals throughout the Southeastern US ready to provide life-saving healthcare. OneBlood is using predictive modeling to better understand and to shape donor behavior. Additionally, by forecasting hospital blood product needs, OneBlood is able to anticipate demand and modify donor recruitment and the processing of blood products. This ensures that hospitals have the right blood products in the right amounts at the right time.

In-hospital and out-of-hospital mortality and readmission prediction models have been extensively covered in literature intended for scientists and practitioners. Adaptive development that feeds real-time performance data back into model calibration has received much less attention. This presentation shows how operational decisions influence the structure of the developed framework and how models are affected by implementation decisions. Aligning the operational and predictive analytics functions helps create a unified scalable multi-purpose prescriptive analytics framework within the organization. The data science function can help solve the operational challenges arising from such implementation by using additional analysis obtained through continuous monitoring of live data.

Many diseases and cancers produce cell metabolites that accumulate in body tissues and fluids beyond normal ranges. These metabolites, which include various volatile organic compounds (VOCs), can be considered biomarkers for disease. These volatiles can be analyzed in blood plasma, and some studies have shown particular VOCs to correlate with the presence of various cancers and diseases.

VOCs dissolved in plasma samples of a group of normal people and cancer patients were analyzed for constituency with a gas chromatograph-mass spectrometer (GCMS). The GCMS output data were modeled with machine learning technology. Analysis outputs were preprocessed with a Python script to identify the peaks of interest. Output data were normalized to account for systematic error in the GCMS operation, and input to a KNIME workflow for prototype modeling. A model was trained on ion count peak data from an equal number of lung and pancreatic patients, plus an equal number of normal patients. Final data preparation logic was completed and the model was trained in the KNIME Platform. The workflow was converted to Python and used to predict cancer presence in the plasma samples through a Random Forest algorithm found in the scikit-learn (sklearn) library. The model predicted the correct cancer status of a plasma sample 93% of the time.

This case study confirms many reports in the literature that VOCs can be correlated with cancer presence. These correlations may one day be considered as basis of a diagnosis, but for now they could be used as the basis for ordering further tests and biopsies to make a diagnosis.

A disease detection system is being developed by Volatile Analysis Corporation as a commercial application for VOC’s in a machine learning environment.

Clinicians, and especially doctors, train for many years to develop expertise in the diagnosis and care of patients. Further intuition and experience gained from years of practice makes them particularly effective at diagnosing and treating patients where there is a clear diagnosis and a well-defined and accepted course of treatment. Artificial intelligence and predictive models promise to provide guidance where there is ambiguity and uncertainty. But, following a course of treatment that is guided by data analysis and machine learning can feel like “cookbook medicine” for some clinicians, whose first reaction is to push back against it. There are also legal, ethical, and philosophical considerations that come into play with use of an impersonal system that affects health care decision making.

The expert panel will explore the current state and trends in the adoption of machine learning among doctors and other clinicians. The panel will debate obstacles to the adoption of artificial intelligence and consider ways in which the wisdom of clinicians gained from years of training and practice can be combined with predictive modeling to achieve better outcomes for patients.
There will be ample time to ask questions of the panel members.

This talk overviews Quantopo's efforts to understand the anatomy of an Ebola outbreak and predict how an outbreak will change under different responses. This work extends previous work on the 2014 West African Ebola outbreak and operational support in Mali. Results presented in this talk were used to support disaster response ground operations in the Democratic Republic of the Congo and position workers in areas likely to be hit the hardest in the weeks after the analysis. Regrettably, operational support was stymied by violence against aid workers and lack of international funding for a swift response.

Algorithms are used in many high-stakes decisions that affect our daily lives. As we develop AI systems that automate decisions in healthcare, how do we ensure trust and fairness? In this talk, we will discuss how to address algorithmic bias in building trusted AI systems. We will start with an introduction of various components of trust: fairness, accountability, transparency, and ethics. We will discuss various case studies to illustrate how fairness sneaks into algorithms. We will then focus on the tools & techniques that practitioners can use to detect, mitigate and monitor bias in AI applications.

Given the vast amount of unstructured data available to health care payers in various forms –ranging from clinical records to audio recordings –the need to build out and apply a natural language processing (NLP) platform is essential. This session will discuss the foundational strategy and components being developed at CDPHP, a mid-size health care payer in New York’s Capital Region. Real-world use cases will be discussed, focusing on increasing efficiency and accuracy, all while reducing error. There will also be discussion of applications focused on member insights and experience. Practical examples will be taken from HEDIS reporting, risk revenue, and member engagement.