Healthcare Transformation Using Cognitive Services

Srinivasan Sundararajan

Democratization of AI in Healthcare

Organizations are becoming increasingly digital and Artificial Intelligence is being deployed in many of them. Often small tech-savvy start-ups and large firms with huge funds, like those in technology and finance businesses, are deploying sophisticated forms of AI.

But several other companies are being left behind. They may not know how or where to deploy AI, or they may not have the resources to create their own AI. Cloud technologies are filling this gap. With options from Google, AWS, Microsoft, and plenty of other vendors, companies can begin exploring how AI can help them. The more that AI becomes accessible, the more companies – and users – can leverage it for their benefit. 

Healthcare is often cited as an area that AI can help immensely. The democratization of AI in healthcare, which is being driven by cloud technologies, is leading to greater access and more predictive work in patient monitoring and smarter reactive responses to health issues. 

ML and AI have traditionally been perceived as the domain of experts and specialists with PhDs. While democratization of AI is viewed differently by different organizations, a common theme has been to make AI adoption simpler.

The following are a few democratized AI services available as part of cloud providers (most of the examples are from Microsoft Eco System as a reference, however other providers also have similar services).

Handwriting Recognition

ai-led operations consulting firm in healthcare

With Windows Ink, you can provide your doctors with the digital equivalent of almost any pen-and-paper experience imaginable, from quick, handwritten notes and annotations to whiteboard demos.

The Windows Ink platform, together with a pen device, helps create digital handwritten notes, drawings, and annotations. The platform supports capturing digitizer input as ink data, generating ink data, managing ink data, rendering ink data as ink strokes on the output device, and converting ink to text through handwriting recognition.

There are equivalent options in other platforms like iOS and Android which can be used for making similar applications for doctors.

Optical Character Recognition

ai-led operations management services in healthcare

Azure’s latest OCR technology Computer Vision Read API extracts printed text (in several languages), handwritten text (English only), digits, and currency symbols from images and multi-page PDF documents. It can extract text from text-heavy images and multi-page PDF documents with mixed languages and detect both printed and handwritten text in the same image or document.

Most hospitals have to deal with lot of documents, especially when it involves external parties like insurance companies. Healthcare organizations can increase productivity and cut down on costs by investing in OCR for managing medical documents.

Emotion APIs

The Azure Face service provides AI algorithms that can detect, recognize, and analyze human faces in images. Facial recognition software has varied applications like in security, natural user interface, image content analysis and management, mobile apps, and others.

Using this API, we can detect perceived facial expressions such as anger, contempt, disgust, fear, happiness, neutral, sadness, and more. It is important to note that facial expressions alone do not represent the internal states of people.

Speech Translation

ai-led product engineering services in healthcare

The number of people in the U.S. who speak a language other than English is large and growing. Language barriers have been found to impede access to care, compromise quality, and increase the risk of adverse outcomes. When friends and family interpret, they are prone to omit, add, and substitute information.

The Azure Speech Translation API can translate incoming speech into more than 60 languages. This API enables real-time, multi-language speech-to-speech and speech-to-text translation of audio streams. With the Speech SDK, your applications, tools, and devices have access to source transcriptions and translation outputs for provided audio. Interim transcription and translation results are returned as speech is detected, and results can be converted into synthesized speech.

Health BOTs

AI for Health Cloud Enablement Services

  • Providers have built health bot instances that triage patient issues with a symptom checker, help patients find appropriate care, and look up nearby doctors.
  • Insurers have built health bot instances that give their customers an easy way to look up the status of a claim and ask questions about benefits and services.

Azure Health Bot empowers developers in healthcare organizations to build and deploy AI-powered, compliant, conversational healthcare experiences at scale. Combining a built-in medical database with natural language capabilities to understand clinical terminology, it can be easily customized for various clinical use cases. The service ensures alignment with industry compliance requirements and is privacy protected to HIPAA standards.

Conversational intelligence also adapts dynamically as the health bot instance learns from previous interactions.

Text Analytics for Health

The healthcare industry is overwhelmed with data. They face an incredible challenge in trying to identify and draw insights from all that information. Unlocking insights from this data has massive potential for improving healthcare services and patient outcomes.

The Key Phrase Extraction API evaluates unstructured text, and for each JSON document, returns a list of key phrases.

AI/ML Led Solutions for Life Sciences

The Text Analytics API lets you take unstructured text and returns a list of disambiguated entities, with links to more information on the web. The API supports both Named Entity Recognition (NER) for several entity categories and entity linking.

Text Analytics for health performs NER, relation extraction, entity negation, and entity linking on English-language text to uncover insights in unstructured clinical and biomedical text.

Reinforcement Learning

AI Tools for Digital Transformation in Healthcare Industry

Medical diagnoses essentially involve mapping patients’ medical history, current symptoms, and other information to the correct disease profile. It can be an incredibly complex task representing an enormous burden (in both time and cognitive energy required) for busy clinicians.

Personalizer API uses reinforcement learning to select the single best action, known as reward action ID. Azure Personalizer is a cloud-based service that helps your applications choose the best content item to show your users.

Personalizer currently uses Vowpal Wabbit as the foundation for the machine learning. This framework allows for maximum throughput and lowest latency when making personalization ranks and training the model with all events.

Anomaly Detection

digital transformation in healthcare it consulting

Anomaly detection in medical treatment can be used to discover deviations from regular patterns and determine whether the patient management is unusual. Detecting an anomaly from medical images including mammograms, CT, or PET images is still an ongoing research problem drawing a lot of attention with applications in medical diagnosis.

The Anomaly Detector API enables you to monitor and detect abnormalities in your time series data without having to know machine learning. Using your time-series data, the API determines boundaries for anomaly detection, expected values, and which data points are anomalies.

Detect anomalies in your streaming data by using previously seen data points to determine if your latest one is an anomaly. This operation generates a model using the data points you send and determines if the target point is an anomaly.

Conclusion

Healthcare transformation requires a great amount of AI integration and implementation.

However, most healthcare organizations don’t have enough resources and bandwidth to work on AI development and deployment. Also, AI Involvement by its very nature is iterative and more concentration is required on involving the stakeholders and arriving at a consensus. Remember, the success of AI depends on the richness of data which is the main responsibility of healthcare organizations, while implementation of AI can be taken care of by these cognitive services.

About the Author –

Srini is the Technology Advisor for GAVS. He is currently focused on Healthcare Data Management Solutions for the post-pandemic Healthcare era, using the combination of Multi-Modal databases, Blockchain, and Data Mining. The solutions aim at Patient data sharing within Hospitals as well as across Hospitals (Healthcare Interoprability), while bringing more trust and transparency into the healthcare process using patient consent management, credentialing and zero-knowledge proofs.

Healthcare at GAVS

Kushboo Goel

GAVS is not new to Healthcare services, and yet a Healthcare vertical is new at GAVS. GAVS acquired its first Healthcare client BronxCare Health System over 10 years ago in 2010. For 10 years, GAVS has been the go-to technology partner at BronxCare. From managed infrastructure services, data migration, application support, security and storage, and most recently virtual desktop solution during the COVID-19 pandemic, GAVS has not only earned deals at BronxCare as a solution partner but earned a relationship that led to several other healthcare clients such as the Jewish Board Behaviour Health centre. In a span of 10 years, the number of healthcare clients at GAVS has grown significantly to today contributing over 55% to our overall revenue.

ai-led operations consulting firm in healthcare

The unintended focus on healthcare was further strengthened when we launched Long80, a joint venture with Premier Inc. that has a network of 4000+ hospitals in the US. While BronxCare lead us to the backwaters of the healthcare industry, Premier has led us to the ocean. At GAVS we are determined to maximize this opportunity, but that means we must trade our boat for a ship!

This process has been ongoing at GAVS for the last 4-6 months. These efforts have included bringing on healthcare domain experts, having multiple conversations with our existing healthcare clients to understand the key pain points they face, gaining an industry perspective through conversations with multiple healthcare analysts to name a few. Perhaps our commitment to building a healthcare vertical is most evident through the setting up of the GAVS Healthcare Technology Institute, with the prestigious IIT Madras as our teaching partner. Through the institute, GAVS will empower its workforce with deep knowledge in the Healthcare domain in areas like Population Health Management, Revenue Cycle Management, Health informatics to name a few. In addition, courses will cover AI/ML methodologies with a focus on application to healthcare use cases.

To start this journey, we began by refreshing our existing healthcare offerings. Previously we offered mostly horizontal solutions to our healthcare customers. These included infrastructure services, app development and management, cloud migration, offshore product development and most recently cybersecurity. While integral to the provider and payer operations, most of these services were not consumed by front-line workers and did not directly influence delivery of care. Now, with a revamp of our healthcare services, GAVS offers three news offerings directly influencing quality of care delivery and clinical outcomes.

The first is Business Process Automation. Healthcare, a highly regulated industry is plagued with multiple administrative processes. These processes are low-hanging fruits for automation and cost reduction. By partnering with automation partners GAVS has successfully automated processes for existing clients and is in the process of identifying additional use cases for process automation with our existing clients.

The second is Data Modernization. Any given healthcare provider has between 20-50 applications running in their hospital. This includes Electronic Health Records, Radiology Imaging Systems, Billing Systems, Payroll, Scheduling, etc. In addition to the data residing on these systems, patients now generate healthcare data on their mobile devices through fitness apps or wearable devices. This growth in IoT has led to data in healthcare doubling every 24 months. This presents an unprecedented opportunity for GAVS to help healthcare providers and payers to integrate and manage data effectively to create a single source to truth, and allow for interoperability, giving patients and providers a holistic view of their care. 

The third, is Advanced Analytics. The increased access to healthcare data combined with rising cost pressures has been the driver for healthcare organizations to focus on ‘wellness care’ instead of ‘sick care’. Through predictive analytics, AI/ML-driven solutions, providers and payers use historic data to predict future outcomes such as the risk of certain diseases.  GAVS currently leverages its data scientists and developers to offer these services to a handful of clients. The immediate focus moving forward is to find additional use cases in both the operational and the clinical space to further expand this capability.

Now, to deliver the new services at GAVS, we must build a pipeline of skilled technologists with knowledge of the healthcare domain. Enter GAVS Healthcare Technology Institute. The Technology Institute is designed to offer three levels healthcare courses introducing participants to the healthcare industry, AI/ML methodology, and application of these methodologies to their projects. The goal is for every employee at GAVS to have an introductory knowledge of healthcare and AI/ML concepts to align with GAVS’s healthcare focus. Our partnership with IIT Madras bring to the institute the best in class faculty and curriculum. The first level of certifications went live on March 22. We aim to create a proficient, domain-ready workforce and hope they enjoy the healthcare journey!

2020 was undoubtedly a challenging year for the healthcare industry, and we proudly supported our clients through these challenges. As we look forward, our goal is to further enable healthcare organizations in managing their strategic priorities and save lives!

About the Author –

Kushboo brings with her 9+ years of experience in Management Consulting and IT Consulting in Healthcare and Financial Services. Within healthcare, she has worked at University of Chicago Hospitals, Johns Hopkins, Advisory Board Company and Apollo Hospitals. She is especially experienced in managing and supporting large transformation programs. She has worked on several process optimization and cost optimization projects contributing to FTE and dollar savings for her clients.

Introducing Jane Aboyoun, CIO, SCO Family of Services

Jane Aboyoun

1. Tell us something about your childhood. What values had been instilled in you that helped you excel later in your life?

My parents are first generation Americans – both their parents were born elsewhere and emigrated to the US.  My mother is in her 80s now and she was amongst the first of her generation to go to college and work full time while raising a family. My mom loved her job as an elementary school teacher, and she taught me that helping others is the key to finding joy in a career.  My father grew up poor and in a foster home, but he managed to earn a full academic scholarship to college.  He went on to have a successful career in sales management.  In my family, education was highly prized and through my parents’ example, I learned that life-long learning and hard work was a way to advance oneself.  I was raised to be independent, to rely on myself, to value being able to support myself, to work hard, to focus, to be proactive and to always say “yes, we can”.  

2. When did you discover your passion for technology?

I found my passion for technology in my first job as a production planner at Nestle Foods.  Production planning is all about efficiency and process.  Computers are essential in delivering that and it was impossible to do my job without them. While studying engineering in college, I had to take a programming class.  Of all the courses that I took, that one was the most challenging for me and I barely passed the course. I vowed to never go near a computer and that stood until I was faced with tracking millions of dollars in WIP (work-in-process) inventory in one of Nestle’s production facilities. To do that, I developed a barcode data collection system to track inventory as it moved around the production floor.  The system was so successful that Corporate noticed and asked me to join their Information Systems team.  I started writing code for an MRP system and all at once, with practical application in real life, it suddenly made sense. My career in IT was launched.

3. What have been some of the biggest challenges in your life and how that has shaped you?

I always wanted to have both a career and have a family, and that is a tough balancing act.  Early in my career, I found working in a global C-suite job and raising young children at the same time to be extremely challenging. I’ve had to create boundaries in order to give 100% to each.  It is much easier now that my children are older, and as a result of my experience, I have huge respect for working parents who are trying to make it all happen. It’s not easy!

4. Tell us something about the social causes that you support.

I am passionate about fighting for equality and equity, protecting the environment, and animal welfare. We have so many challenges at this time in human history and how we navigate the next ten years together will be critical in so many ways.  

5. How would you define success?

What I have learned through my life experience is that success is a journey, rather than an end game, as the world is of course a dynamic place and the bar is always being raised.  Good ideas can come from anywhere and it’s critical to stay flexible and open-minded.  As a leader success is measured by the impact one has on others, and it’s often found in tiny actions that multiply across a team to impact an organization – the butterfly effect at work.  

6. How would you describe your leadership style?

I would liken it to a conductor of an orchestra…having a vision for what could be, selecting the players, empowering the musicians, directing the various piece parts so that together, we achieve an incredible outcome.  The fun part though, is that we are playing jazz music rather than the classics and sometimes the players just need to jam, and trust that we’ve got this, as there isn’t always a playbook for what’s next.

7. Looking back on your journey and knowing what you know now, what is one piece of advice you would have given yourself along the way?

To not lose sight of the big picture. In the rough and tumble of the day-to-day work, it is easy to get distracted and buried in the details.  It takes discipline to stay focused on the end game and keep your eyes above the tree-line.  This is where I feel I provide most value to the team, as in my role, I have the opportunity to see many pieces of the puzzle and how they fit together. I can help bring that insight back to the team, so that we can recalibrate if necessary and link those day-to-day tasks to achieving business objectives.

8. What advice would you give those who want to pursue a career in STEM?

There has never been a better time to pursue a career in STEM.  As I mentioned, the next few decades are critical to the future of the planet.  There are numerous exciting new fields emerging that can help address the issues in the world today.  These solutions are no doubt rooted in science, technology, engineering, and math.  I would encourage those interested to move forward earnestly. I believe the reward would be a satisfying and worthy career that might just change the world!

About Jane Aboyoun –

Jane Aboyoun is the Chief Information Officer at SCO Family of Services, a non-profit agency that helps New Yorkers build a strong foundation for the future. In this role, Jane is responsible for leading SCO’s technology strategy, and managing the agency’s technology services to support business applications, architecture, data, engineering, and computing infrastructure.

As an accomplished CIO / CTO, Jane has spent 20 years in the C-suite in a variety of senior technology leadership roles for global, world-class brands such as Nestlé Foods, KPMG, Estēe Lauder Companies, Walt Disney Company, and the New York Public Library.