This community is in archive. Visit community.xprize.org for the current XPRIZE Community.

Use cases for AI and ML in healthcare

We are exploring future use cases for AI and ML in healthcare. Imagine all things are possible.
  • What are some of the future use cases for AI and ML in healthcare?
  • How can AI/ML be leveraged for population health management?
  • How can Al/ML be leveraged for personal health?
  • How can AI/ML be used to evaluate health programs?

Comments

  • ShashiShashi Posts: 596 admin
    Hi @jonc101, @ajchenx, @acowlagi, @reubenwenisch, @nastyahaut, @elekaja, @MachineGenes, @ymedan, @joshnesbit, @addy_kulkarni - What are your thoughts on future use cases of AI and ML in healthcare?
  • ymedanymedan Posts: 127 ✭✭✭
    AI/ML is currently addressess the needs of the Health/SickCare system professionals. Yet, I believe that in the future, AI/ML will empower us, individuals, to stay in a healthy state and defer onset of (chronic) disease to as late as possible. It will do it by way of "nudges" related to unhealthy lifestyle routines. AI/ML will embedd heakth wisdom in our pocket via immediately available health virtual assistants. Staying healthy is the only sustainable model for a heath nation. Spending 20% of national GDP on illness is not a sustainable strategy that serves the wellbeing and wealth of citizens. COVID-19 hilghts the deficiencies of the current system.
  • ajchenxajchenx Posts: 15 ✭✭
    We are working these use cases:
    1. Use AI/ML to study patient journey from EHR data, build doctor referral and symptom checking AI model, test automatic doctor referral in big hospital workflow. Goal: improve hospital patient navigation efficiency and accuracy.
    2. Use the doctor referral AI tool in rural clinical to enable rural doctors to refer patient to the right specialties. Goal: reduce health care disparities in rural areas.
    3. Use AI/ML to automate guideline recommendation, patient matching and patient education for enabling real-time clinical collaboration cross hospitals. Goal: reduce health care disparities in developing countries.
    4. Use AI/ML to discover digital biomarkers for preventive screening for cancers, neurological diseases to improve population health.
  • ShashiShashi Posts: 596 admin
    Thanks @ymedan and @ajchenx for sharing experience on AI/ML use cases. Do you know of any case wherein AI is used for evaluating health programs?

    Hi @jda, @aassif_lg, @meallen3, @fbaothman, @scveena, @synhodo, @mashizaq, @Sujana, @dzera and @skornik - We look forward to your thoughts on future use cases for AI and ML in healthcare.
  • ShashiShashi Posts: 596 admin
    Hi @Nvargas2, @tylerbn, @arun_venkatesan, @biki, @kenjisuzuki, @bngejane, @dollendorf, @Hlantum, @paulauerbach, @namkugkim - curious to know if you have any inputs to share on the ways in which artificial intelligence and machine learning be leveraged for population health management, personal health, and evaluating health programs.
  • HeatherSuttonHeatherSutton Posts: 77 XPRIZE
    @ymedan ~ Your post gave me chills! What a bright future we could all have if we took to heart your wisdom of "Staying healthy is the only sustainable model for a healthy nation." I hold your vision of this bright future whereby we collectively pick up these social, psychological, and technological tools and allow them and the human spirit to raise us to new levels of health and vitality. Thank you for your comment, truly!
  • HeatherSuttonHeatherSutton Posts: 77 XPRIZE
    @ajchenx ~ Very cool! We'd love to hear more about the work you are doing. Do you mind sharing what organization you work with?
  • ajchenxajchenx Posts: 15 ✭✭
    @HeatherSutton I'm a Learning Health System Consultant based in Silicon Valley, and a visiting professor at West China Hospital (part-time). The use cases I mentioned are from my collaborative research with several hospitals and rural clinics in China. In US, I am participating in the NIH National Covid Cohort Collective to use LHS approach for rapid dissemination of AI/ML results into frontline patient care. Previously I co-chaired Region IX Health Equity Council for US HHS NPA, as well as served on the Consumer Technology Workgroup of Federal Advisory Committee on Health IT Standards. So, I'm focused on helping hospitals build learning health systems (with HIT, AI) to reduce global health care disparities. I believe AI/ML will have huge applications in reducing health care disparities because very often disparities are result of lack of medical professional resources. AI/ML-enable learning health system platforms can bring the high quality clinical experience from teaching hospitals to community and clinics. As I commented in other posts, learning health system (LHS) is the new vision created by National Academy of Medicine, which will transform global healthcare systems.
  • mashizaqmashizaq Posts: 47 ✭✭
    @Shashi Healthcare Apps like Dr. Elsa in Tanzania can be used as a patient virtual assistant to deliver patient education, medical alerts, and analyze their current mental status. They can monitor and offer medical assistance to patients especially in remote areas where clinical personnel may not be readily available.
    Another application of AI that is likely to transform the health sector is the Dictation Assistance using (Natural language Processing) NLP and Translation. Natural language processing can help medical experts deployed in remote areas to capture data from dictated notes, translate and store in the Electronic Health Records (EHR) despite language barriers. NLP can also help in sorting unstructured patient data including images and text to extract vital information for treatment.
    AI will also help bridge the existing gap between the number of surgeons and patients. AI will assist experts in diagnostic processes by analyzing medical images like CT scans, X-rays, and MRIs. Through imaging analysis, medical experts will extract important information that may not be possible through human eyes. AI has also been applied in the field of oncology to help in cancer treatment. For instance, IBM Watson is used in processing unstructured and structured patient data to provide cancer treatment recommendations.
  • ShashiShashi Posts: 596 admin
    Thanks @mashizaq for sharing those amazing future use cases of AI. Is there a way AI could be used to evaluate health programs as well? what do you think?
  • ShashiShashi Posts: 596 admin
    Hi @Shabbir, @jblaya, @acowlagi, @Vishalgandhi, @pglass, @Nitesh, @kakkattil, @Neal_Lesh and @yuanluo - What are your take on how AI / ML may be used in future for healthcare.
  • HeatherSuttonHeatherSutton Posts: 77 XPRIZE
    @ajchenx ~ I'm well impressed by the work you are doing to serve the medical community and the world at large. This morning I am struck by the fact that there are many inroads towards achieving universal access to health (education being a huge component of that) and I'm grateful to people like you, the members of this community, innovators, policymakers, governments, IGOS, our sponsors, our XPRIZE team and others who have committed themselves to this cause. Thank you!
  • HeatherSuttonHeatherSutton Posts: 77 XPRIZE
    @mashizaq ~ Thank you so much for sharing! We were not aware of Dr. Elsa, but I read up about "her" this morning and I find the tool very interesting. I personally get excited by the potential for AI to "uplevel" caregivers and also to relieve them from some of the administrative burdens that are hallmarks of the field. It's quite thrilling to think of these possibilities!
  • ShashiShashi Posts: 596 admin
    Hey @shamakarkal, @grandner, @rguimara, @pkatakam9, @alabriqu, @cimdal2, @owen, @ClaireM, @supratik12, @ajeeta, @rajpanda, @msrjoy, @praveenraja and @Davisthedoc - What are your thoughts on the way artificial intelligence and machine learning be leveraged for population health management, personal health, and evaluating health programs in future.
  • synhodosynhodo Posts: 2
    The future of AI in Healthcare is to make the AI solution possible to be deployed in the Low and Middle-Income Counties for screening disease. AI systems will be able to work day and night with minimum system requirements. AI + Blockchain will be exciting collaboration technology for quality control and trust in the field. High-quality healthcare technologies are reserved in a few countries. So AI + Blockchain will make borderless healthcare possible.
  • ShashiShashi Posts: 596 admin
    Thanks @synhodo for sharing your thoughts on future use cases.

    Hi @SArora and @RahulJindal - What are your thoughts on the future use cases of AI and ML in healthcare?
  • mashizaqmashizaq Posts: 47 ✭✭
    @Shashi Computers that have AI capabilities are currently being used in several real-world domains to solve problems. For example, AI can be used to track the movement of people so as to curb transmission through contact by seeking to know who they have been with, and not just where they have been, to the development of an AI-powered database that will help enable researchers to quickly discover literature resources that are related to various diseases and their cure.
  • ShashiShashi Posts: 596 admin
    Thanks @mashizaq for sharing those insights.

    Hey @mhackett, @stephaniel, @dollendorf, @JoanneP, @siimsaare, @abejanis, @Lizzy_2020, @Ewunate, @ArdenVent, @kevinnicholasbaker, @berniceredley - Curious to know if you have any inputs on the future use cases of AI and ML in healthcare.
  • dollendorfdollendorf Posts: 4
    Automating and making more efficient systematic literature review to provide inputs for advanced synthesis of the clinical evidence

    Accessing available data on cost-effectiveness of health interventions to create a locally-relevant profile and developing predictive models
  • ShashiShashi Posts: 596 admin
    Thanks @dollendorf for sharing these insights.
    Hi @DidierC, @janansmith, @ClaireM, @mendezra2, @marschenrj, @RickyM, @clairecravero, @acavaco, @care2communities and @C_Castellaz - What do you think on the way AI and ML will be used in the future for population health management and evaluating health programs.
  • SAroraSArora Posts: 10 ✭✭

    @Shashi AI and ML, as @synhodo shared, have the potential for huge impact in LMIC’s for disease screening and diagnosis, that leads to early detection and provides access to quality healthcare for rural and underserved communities. One of the biggest challenges to clinician training is the exponential growth of medical knowledge, which currently doubles every few months. AI can help aggregate this knowledge and get it to where it’s needed most. We at Project ECHO see AI playing an increasingly important role in this respect, and in combination with the ECHO Model, helping to democratize knowledge, get it to where it’s needed most, and save lives.
  • mashizaqmashizaq Posts: 47 ✭✭
    edited October 2020
    Patients have been swarming to telehealth amid the pandemic—and telehealth vendors have responded by diversifying their offerings to win over customers and keep them happy.

    https://www.businessinsider.com/amwell-bests-telehealth-competitors-on-user-satisfaction-2020-10?IR=T
  • mashizaqmashizaq Posts: 47 ✭✭
    Telemedicine is the provision of medical services to patients remotely when the doctors and patients are physically separated using the two-way voice and visual communication. Modern technology has enabled doctors to consult patients by the HIPAA compliant video conferencing tools powered by satellite tech. Consequently, Telemedicine is already playing a huge role in cost reduction in wellness.
    https://africanews.space/africa-needs-telemedicine-to-overcome-its-medical-challenges/?fbclid=IwAR39VRIFmDmrY2We2Dk4wlJW3Q2pvBu1C0RhtjzjcMpk6yU3Kwf5eGudpxI
  • ShashiShashi Posts: 596 admin
    Thanks @SArora for sharing an important perspective of AI helping to democratize knowledge. In project ECHO, have you'll been able to use AI and ML for data standardization, integration and systems interoperability? if so, what considerations were taken to protects privacy and security of these data?
  • MachineGenesMachineGenes Posts: 1 ✭✭
    Shashi wrote: »
    Hi @jonc101, @ajchenx, @acowlagi, @reubenwenisch, @nastyahaut, @elekaja, @MachineGenes, @ymedan, @joshnesbit, @addy_kulkarni - What are your thoughts on future use cases of AI and ML in healthcare?

    Hey @Shashi, we're using new forms of evolutionary ML and adversarial AI-- not Generative Adversarial Networks (GANs), but a completely different form of adversarial AI we developed a couple of years before GANs, which has significant operational advantages over the status quo.

    Conventional ML is based on artificial neural networks (ANN), which suffer from inherent limitations (the main one being that they never really explicitly 'model' the dynamics of a system, but merely come to 'embody' those dynamics of the system). In contrast, our form of evolutionary ML takes the best abstract mathematical models of a disease from the medical literature, including its dynamics-- the way it alters the function of the body, and interacts with drugs--and embodies this structure as simulated "chromosomes". Every "gene" on the chromosome corresponds with some parameter associated with the disease or drug-disease interaction. We then take individual medical histories and use evolutionary pressures to force the chromosomes to evolve-- to select and breed and mutate, across generations-- until organ-scale personalized models have been produced that embody the disease dynamics in the individual subject. (This is an idea that has been around for decades in a form originally known as "genetic algorithms", GAs, but GAs had fundamental limitations that prevented their real-world use for complex diseases and partial information. By re-thinking models of evolution and adding additional features we've solved those limitations, and so now can apply our modified evolutionary process to model complex real-world diseases.)

    One of the problems that remains is ambiguity in the evolved computational models. We use a novel adversarial process, whereby the main AI has two subordinate AIs take those models and play a game with them. One subsidiary AI, the "Prime", takes the models and uses them to try to design an appropriate drug therapy. The other AI, the "Adversary", uses known ambiguities within the models to cause adverse outcomes, which the Prime then has to counteract by modifying its strategy. (Unlike ANN, our AI "knows what it knows", including ambiguities among the chromosomes.) The result is ultimately generation of a drug dosage strategy that is personalized, and has been tested for safety and efficacy. This adversarial process was first demonstrated in 2012 and patented in mid-2014, six months prior to GANs. It has major advantages over existing AI-based techniques, in that it is completely explainable, interactive with the users (patient and clinician), able to generate good strategies despite a training history of therapeutic failures, and is able to operate the AI component on an isolated Edge device.

    For the IBM Watson AI XPRIZE we demonstrated this technology to generate insulin strategies for highly-unstable forms of type-1 diabetes by data-mining actual medical histories, despite those histories being comprised solely of therapeutic failures to achieve the desired blood glucose outcomes. Last year, as part of AI XPRIZE, we demonstrated our adversarial AI running on an isolated laptop computer, generating 30 hours of insulin strategy over approximately 20 minutes of computing time, that generated far better blood glucose outcomes than the original histories. The generated insulin strategies look nothing like conventional insulin dosing.

    This suggests that the medical use of AI is about to look very different from previous use cases.
  • ymedanymedan Posts: 127 ✭✭✭
    @Shashi IMHO ML/AI will dominate the clinical decision support domain, simply because the uderlying infrastructure can digest information both vertically and horizonatlly and provide a personalized and integrative perspective. Something only a very few physicians are capable of. This will democratize access to high quality healthcare
  • ShashiShashi Posts: 596 admin
    Thank you @MachineGenes for providing us with insights on evolutionary ML and adversarial AI. The insulin strategies demo is amazing!
  • kenjisuzukikenjisuzuki Posts: 5
    There are two directions. AI will be more and more personal or local. The other is more and more global. Current AI help physicians diagnose or cure diseases. I believe future use cases for AI are more and more for patients and personal, as opposed to physicians or hospitals. The purpose of using AI is becoming from treatment and diagnosis to prevention, to keeping healthy, and to well-being. One AI may monitor health conditions of an individual every day, when one sleeps, when one sits on a chair, when one walks, AI senses data related to his/her health conditions, and suggests him/her his/her behavior of eating, excising, working, etc. to keep him/her healthy.
  • kenjisuzukikenjisuzuki Posts: 5
    The other direction is global. By collecting healthcare data from individuals, for example, by using smart watches, big data acquired from the individuals are stored in a cloud server. AI analyzes the big data and monitor if a particular population of individuals provides a sign of a certain disease, like Influenza or a new virus like the COVID-19, and it identifies a possible source of pandemic. The government or an organization like CDC can prevent the new disease from widespread. One caution for us is that AI is not perfect. It is very dangerous to fully believe AI without the knowledge on what AI can do and what AI cannot. Also, AI can facilitate some sort of discrimination or may create a bias. It is important to know what AI can do, and to think how we, individuals or our society, should work with AI when AI is used in a global setting.
  • ShashiShashi Posts: 596 admin
    @kenjisuzuki - Thank you for sharing these amazing examples of future use cases of AI in healthcare.
Sign In or Register to comment.