<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Anuradha Monga Kapoor on Medium]]></title>
        <description><![CDATA[Stories by Anuradha Monga Kapoor on Medium]]></description>
        <link>https://medium.com/@anuradhamongakapoor?source=rss-c81875d19e8a------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*Hyy_67EP2evuU9Lrn2-tDA.jpeg</url>
            <title>Stories by Anuradha Monga Kapoor on Medium</title>
            <link>https://medium.com/@anuradhamongakapoor?source=rss-c81875d19e8a------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 16:13:36 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@anuradhamongakapoor/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[AI as a decision support in the Physician’s office]]></title>
            <link>https://medium.com/artificial-intelligence-a-physician-and-patients/artificial-intelligence-a-physician-and-patients-long-term-partner-in-chronic-disease-management-6b321b7af5e3?source=rss-c81875d19e8a------2</link>
            <guid isPermaLink="false">https://medium.com/p/6b321b7af5e3</guid>
            <category><![CDATA[physicians]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[chronic-disease]]></category>
            <category><![CDATA[diabetes]]></category>
            <dc:creator><![CDATA[Anuradha Monga Kapoor]]></dc:creator>
            <pubDate>Thu, 03 May 2018 08:52:44 GMT</pubDate>
            <atom:updated>2018-05-04T14:32:15.307Z</atom:updated>
            <content:encoded><![CDATA[<p>In the past few decades, countries across the world have witnessed a substantial increase in the burden of chronic diseases that contribute significantly to disability and early death. A majority of deaths across the world are caused due to cardiovascular diseases; diabetes and obesity are now considered to be the most worrisome chronic conditions not only because they affect a significant population of the world, but also because they are emerging as diseases of the young. As per WHO (World Health Organization) the worldwide disease burden will reach upto <a href="http://www.who.int/whr/2002/en/whr02_en.pdf?ua=1">57% of the total morbidity by the year 2020</a>. In the year 2015, six out of top ten diseases leading to 56.4 million deaths worldwide were chronic diseases. A study carried out by World Economic Forum, anticipates that the five leading chronic diseases namely cardiovascular diseases, respiratory diseases, cancers and diabetes may create a global financial burden of nearly 47 trillion USD by the year 2030.</p><p><strong>Challenges in early detection of chronic diseases:</strong></p><p>A large number of patients in the US seek <a href="https://jamanetwork.com/journals/jama/fullarticle/190758">initial care from a primary care physician rather than a specialist</a>, however there is a growing dissatisfaction amongst patients with their primary care experience. Physicians too on the other hand feel frustrated as the expectations from them exceed the limits of human capability, compromising their efforts to provide the best care. The average time spent by a physician per patient in outpatient setting ranges from 15 to 18 minutes which is grossly inadequate to provide quality care. Only <a href="https://www.nejm.org/doi/full/10.1056/NEJMsa022615">56%</a> of recommended preventive health care services are received by people with chronic conditions as outlined by the US Preventive Services Task Force. Studies have estimated that physicians will need 10.6 hours/ working day to deliver chronic condition care as per recommended guidelines and another <a href="http://www.annfammed.org/content/3/3/209.full">7.4 hours per day to for evidence-based preventive care,</a> to an average practice population of 2500 patients.</p><p>A study in the BMJ Quality &amp; Safety revealed that every year in the U.S., roughly <a href="http://qualitysafety.bmj.com/content/early/2014/04/04/bmjqs-2013-002627">12 million adults are misdiagnosed in the outpatient care</a>. This equates to 1 out of every 20 adult patients or 5% of outpatient care, half of these cases have a potential to cause severe harm. Some of the common reasons for misdiagnosis include issues with inability of the patient to provide an accurate medical history; incorrect diagnostic tests, errors in interpreting lab results and inadequate time spent.</p><p>Many patients may miss out communicating important information pertaining to their signs and symptoms with their primary care giver due to barriers like language, health illiteracy, time constraints etc. Early signs of a disease may sometimes be evident in subtle forms like in a person’s social activities, emotions and daily habits, a primary care giver may have no means to access this kind of information. As a result, the physician may have only a partial view of the overall health status of a patient, thus compromising his ability to sift through high risk cases and allocating adequate time for their management.</p><p><strong>Can Artificial intelligence bridge the gap in diagnosis, prevention and management of chronic diseases?</strong></p><p>AI can armour physicians with literally all the information required for making a good clinical decision and allow for better diagnosis, cure and treatment of debilitating conditions.</p><p>Healthcare is probably one of the biggest generator of data in all forms. AI has the capability to combine this structured and unstructured data to produce information that can then be used to identify early symptoms and predict the risk score of patients. This opportunity can specially be leveraged in early prevention and management of many forms of chronic diseases.</p><p>Some of the data sources that AI can use for gathering and analyzing information include:</p><p>· Academic textbooks</p><p>· Electronic medical records (EMRs), Personal health records</p><p>· Genomic profiles</p><p>· Images like MRI, CT scans, X-rays etc and other forms of diagnostic images</p><p>· Journal publications, research articles etc</p><p>· Monitoring equipment in hospitals</p><p>· Open access databases (e.g., cancer registries, clinical trial records)</p><p>· Payer records</p><p>· Physician notes and prescriptions</p><p>· Social media</p><p>· Wearable fitness devices, monitors etc</p><p><strong>Need of symptom identification for establishing risk and predicting chronic diseases:</strong></p><p>Diagnosis is a very intricate and important aspect of disease management. The symptomatic features of a chronic conditions like diabetes or cardiac disease may be diverse, and being a multi-layered problem the diagnosis maybe marred by false assumptions and impulsive effects at times. Diagnosis is generally made when the disease is already established or it’s late to reverse its progression.</p><p>Artificial intelligence makes use of millions of data points and not only remembers, but also draws important information from the current case and also in retrospect from similar other cases. AI helps the healthcare system to be preventive than reactionary. The role of AI in exploiting knowledge of many specialists, academic resources and screening historical clinical data to aid diagnosis and prediction of risk level is considered as a valuable option. Based on deep learning and real time response of patients, AI can help in creating personalized and predictive feedback for every patient.</p><p><strong>How is AI helping in care management?</strong></p><p>Some of the popular applications of AI in chronic disease management are spread over the following areas:</p><p>Pre-Physician Check-up (Outside Doctor’s office)</p><p><a href="https://cointelegraph.com/news/blockchain-powered-ai-doctors-to-revolutionize-medicine"><strong>Doc.ai</strong> is making use of Blockchain technology</a> to collect vast sets of global medical data in order to analyse the information through machine learning and generate insights. The information can be processed to offer personalized feedback about their medical issues to the users. It is believed that an ongoing feedback acts as a catalyst in driving patient engagement.</p><p>During Physician’s visit</p><p><a href="https://www.enlitic.com/index.html"><strong>Enlitic</strong></a>, is a deep learning medical start up that aims to advance diagnostics and improve patient outcomes by using artificial intelligence techniques.</p><p>Sweden based <strong>Lytics </strong>makes use of machine learning to support the management of patients with end stage renal disease (ESRD) on maintenance dialysis. The system has the capability to learn the health trends and analyse data in order to identify or predict any unusual changes and monitor patient condition through wearable devices.</p><p>Post visit monitoring, adherence of treatment and follow up</p><p>The medical start up <a href="http://www.sensely.com/"><strong>Sense.ly</strong></a> has designed a virtual nurse, Molly that helps in monitoring the patient’s condition and treatment. The machine learning platform makes use of artificial intelligence for supporting patients of chronic conditions with customized monitoring between follow ups with their treating doctor.</p><p><a href="http://159.65.230.118/"><strong>“Symptom.ai”, a product of predictdisease</strong></a>, is an artificial intelligence and machine learning based platform that focuses on data and all aspects of disease management. Unlike many other platforms, it empowers both patients and primary care physicians to jointly establish the potential risk of a chronic disease that begins with minor symptoms. The platform makes use of not only clinical data, but also takes into account data from other sources like lifestyle activities, family history, social media/website forums, research papers, medical articles and outcomes research. The system then matches this big data based holistic information with medical information like medical history, signs and symptoms and lab tests for an early detection of the chronic disease. The main purpose and outcome is identification of high-risk individuals who are more likely to develop a chronic disease during regular body check-up or primary care visits. The identification is followed by insights and personalized recommendations to the primary care physicians for reducing the risk and preventing or delaying disease by suitable interventions. As the system matures, it will also help physicians in predicting which patients are at high risk of developing specific complications over a period of time. The stand-alone system can be effectively used by providers, payers, researchers, pharmaceutical companies, wellness companies, government and non-government organizations in public health management.</p><p><strong>Conclusion:</strong></p><p>Treatment of chronic diseases not only causes a financial strain on individuals and families, but also on the institutions like insurers, governments and the global economy. Chronic diseases are preventable conditions and primary prevention is considered to be an affordable and cost-effective strategy to combat this epidemic. Healthcare systems across the world are moving from volume to value based care, AI has the capability to positively affect not only the treatment outcomes, but also the experience of patients while receiving long term care. AI can prove to be a catalyst in this change, however, the true potential of this technology can be harnessed only when they are available to the average providers by being cost effective and user friendly.</p><p>The author can be contacted at : amonga@predictdisease.com</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6b321b7af5e3" width="1" height="1" alt=""><hr><p><a href="https://medium.com/artificial-intelligence-a-physician-and-patients/artificial-intelligence-a-physician-and-patients-long-term-partner-in-chronic-disease-management-6b321b7af5e3">AI as a decision support in the Physician’s office</a> was originally published in <a href="https://medium.com/artificial-intelligence-a-physician-and-patients">Predict Disease</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>