Healthcare

Actuarial Informatics

Health insurance companies can take two approaches when making decisions. They make actuarial decisions (Based on rules-based statistical analysis), or they can go on their gut feeling. The people in healthcare insurance doing these mathematical and statistical calculations are called actuaries.

AI is making it easier for humans to collect, process, and get useful insights from the massive amounts of data being created in the industry. AI can help find connections in data that a normal person would never be able to make. AI can be used to dig deep into an actuary’s thought processes. It helps make decisions by simulating human reasoning and processing data based on actuarial principles. The improvement in decision-making enables us to start predicting the future. We call this technology “Predictive Analytics.” 

With predictive analytics, healthcare actuaries can now gain more insights from claims, medical records, prescription patterns, patient satisfaction surveys, adherence rates, social determinants of health, clinical data, metadata, customer behavior patterns, and many more. AI can perform automated data analysis, competitor rating reconstruction, intelligent claims handling (which results in faster and deeper analysis and enables the detection of data abnormalities).

One unsupervised data mining technique used to analyze a dataset is called clustering. It is used to partition a set of data into different groups so that objects in the same group cluster are similar while moving other groups outside of the cluster. It is crucial during the exploratory and evaluation phases of data analysis. Researchers try to uncover underlying patterns without previous knowledge of the data and provide actuaries the much-needed insight to make better decisions.

Challenges

Having an outdated technology stack can push actuaries into compliance roles rather than decision-making ones. Actuaries will need to adapt to the modern world, where decision-making is based on automation using AI. They will need to stop relying on human intuition alone. The AI adoption rate is growing rapidly, but many respondents don’t have the knowledge required to keep pace with this trend. It highlights the need for a seamless framework that can they can use to ease themselves into this technology.

Healthcare is an industry where the majority of people only come to when they have a medical problem. As such, these people are not in a position to make independent, well-informed choices regarding the type of care and services that would benefit them the most. Healthcare professionals usually try to guide these customers towards their services.

Health insurance is often what pays for services in the industry, and this keeps customers insulated from the actual costs of the treatments they receive. This makes the demand mostly inelastic and leaves most healthcare providers in a tricky position. They can struggle to improve quality and patient satisfaction while navigating budget pressures, customer interests, new regulations, data/directives to help ease their cost.

Solution Approach

One of our clients, a large healthcare provider, wanted to identify eligible individuals covered based on those who hadn’t done any medical screenings. This could mean that these individuals might get admitted to a hospital, use healthcare services, and claim insurance. It would add to the cost curve for the payer. With proper medical screening in place, misplaced risk calculations, actuarial decisions, and payer/provider cost-efficiency can be improved.

xpressso.ai platform provides out-of-the-box development frameworks.  The project was started with the relevant environments, which were then created automatically. Development images configured based on pre-defined templates were installed on-premises or in a development VM within the xpresso.ai infrastructure. This enabled authentication using LDAP, seamless project setup using Bitbucket, Jenkins, and Docker (ensuring build and deployment without software compatibility issues).  

The platform made available by xpresso.ai leverages the latest ML and DL tools while preparing models. It includes Pachyderm-based data versioning, Kubernetes, Kubeflow, and Spark-based ML and DL. It also includes an Istio-based service mesh-enabled microservice architecture, and ELK-based monitoring capability, contributing to a reduction in latency time.

The diverse healthcare data at our disposal, including patient records, patient claim history, patient demographics, etc., were added as exploratory variables using xpresso.ai libraries. xpresso.ai’s MLOps platform allows establishing high-end Alluxio and Presto-based efficient data connectivity and collecting data from diverse sources. Using xpresso.ai’s data versioning and xpresso.ai connectivity libraries, data versions were easily controlled, stored into an xpresso Data Model (XDM)-enabled data store. This enabled easy retrieval and storage of datasets/files into an internal XDM. 

We used handcrafted Python-based algorithms and SQL to create ML algorithms that were used to design clustering mechanisms.  Business rules, adhering to HEDIS (Healthcare Effectiveness Data and Information Set — a widely used set of performance measures in the managed care industry, developed and maintained by the National Committee for Quality Assurance or NCQA) were incorporated into the algorithms. Clustering algorithms were created using the JavaScript library – D3 and also obtained from xpresso.ai libraries, reducing the time to market.

The attributes obtained were used for categorization (employing Pachyderm-based data versioning) and then performing univariate, bi-variate, and Bag of Words analysis — for both structured and unstructured datasets through xpresso Exploratory Data Analysis (Data and Statistical Analysis).  Different datasets and their different versions were easily controlled and stored into an xpresso Data Model (XDM)-enabled data store that enabled easy retrieval and storage of datasets/ files into internal XDM. This was achieved using two excellent features of xpresso.ai

  1. Data Connectivity Marketplace libraries
  2. Data Versioning

We provided a solution that enabled our client to zero in on individuals who were eligible yet hadn’t used any medical screening. We initially proceed by using clustering algorithms to segregate individuals into relevant groups from the huge healthcare datasets made available to us. The output we generated helped the client segregate individuals into groups so that actuaries could devise a unique strategy for each group. It enabled the client to raise its income by around 35% due to the increased number of medical screenings. The solution also helped them to generate income from Quality Performance Measure (QPM) incentives that are awarded on a PMPM (Per member, per month) basis.

How xpresso.ai can help Healthcare Organizations transform their journey to cognitive AI solutions

xpresso.ai is an AI/ML Application Lifecycle Management Platform.  

xpresso.ai enables complete lifecycle management of AI/ML solutions, addressing the AI transformation journey of enterprises on any cloud platform of choice. xpresso.ai offers functionality essential for building AI/ML solutions – primarily enabling data scientists to rapidly build predictive and prescriptive models. The platform provides a user-friendly interface to develop, deploy, and manage AI/ML solutions at scale. In addition, xpresso.ai supports the incorporation of these solutions into business processes, surrounding infrastructure, products and applications. 

Key benefits of xpresso.ai include: 

  • Empowers data scientists to transform AI/ML research into solutions  
  • Improves the productivity of data scientists by enabling them to focus on the business problem, developing algorithms and rapid experimentation of models  
  • Addresses the shortage of skilled data science resources with automated workflows, toolkits and frameworks  
  • Manages AI transformation journey costs without any wastage of R&D efforts  
  • Provides an enterprise-ready and secure environment for complete lifecycle management of AI/ML applications 
  • Enables at-scale deployment of enterprise AI/ML applications on-premise, cloud (AWS, GCP, Azure), or hybrid environments 

Additional details on xpresso.ai can be found at:  https://xpresso.ai . We can schedule a demo of the platform for anyone interested in learning more.

Have Any Questions?

Need more information about the platform?