The Role Of Artificial Intelligence In Improvement Of The Data Mining And Predictive Analytics In Hospitals And Healthcare
Artificial Intelligence is everywhere in our lives before we realize it. It there when you are watching a video on youtube, browsing products on Amazon, or writing some words on google searching box. “AI assistants will become trusted advisers to consumers, anticipating and satisfying their needs, ensuring that routine purchase flow uninterrupted to their households like electricity and guiding them through complex buying decision. ” AI is more than just a tool in marketing and business analytics. It is rapidly and vastly changing modern hospitals and healthcare nowadays, from both technological and systematic level. This article will first give an analysis of how AI improve the data mining and predictive analytics in hospitals and healthcare; I will also give examples of Amazon Alexa’s wide application in hospital data mining strategy to provide a deep understanding of this revolutionary trend; Lastly, I’d like to make a brief comparison of Amazon Alexa and Google Home, the most two famous AI voice assistants in current market, to foresee the trends of the market.
AI and Data Mining
According to Laudon, Data Mining, as a discover-driven method, “provides insights into corporate data…by finding hidden patterns and relationships in large databases and inferring rules from them to predict future behavior. ” The healthcare and medical industries generate huge amount of data, from patients' biological traits, the reaction of medication, doctors' diagnosis and records etc. They all exist in the information flow of the hospital in a semi-structured or even unstructured forms. The lack of integration of data from both chronological and geographical levels has disenabled doctors, the decision-makers in these cases, to make better and faster solutions for patients.
Artificial Intelligence consists of “computer-based systems (both hardware and software) that attempt to emulate human behavior…. able to learn languages, accomplish physical tasks (robotics), use a perceptual apparatus that informs physical behavior and language, and emulate human expertise and decision making”. AI has provided Data Mining the technological frame and tool to build up the data pattern and recognition in hospital and healthcare industries. For example, Google has launches its Deepmind Health Project to focus on mining medical records with the aim to provide faster health services. Deepmind Health can process hundreds of thousands of medical data in a few minutes. The use of data mining in healthcare has great potential. For example, data mining can provide associated type of information, one of the five types of information provided by data mining. According to recent research, data mining can “develop a patient risk score by matching abnormally high utilization rates against medical complexity and socioeconomic factors”. Data mining can also provide forecast information, such as “providing early warning for severe sepsis by predicting sudden downturns due to changes in multiple real-time vital signs. ”
AI and Predictive Analytics
In healthcare industry, the best use of medical knowledge and AI technologies would be preventing illness happen in the first place, or at least predicate it in advance to minimize the time and financial cost from both patients and hospitals’ sides. That’s why Predictive Analytics has become more and more popular nowadays. It uses “statistical analysis, data mining techniques, historical data, and assumptions about future conditions to predict future trends and behavior patterns. Variables that can be measured to predict future behavior are identified. ” From a technological point of view, mature and effective medical predictive analytics is based on AI as its foundation and relies deeply on data mining and algorithms. For example, Sentrian is a start-up company aiming to bring medical community closer to the future. As it claims itself as “the remote patient intelligence company”, it uses algorithms to inform people when they will be sick before they even have symptoms.
Of course this technology is used on chronic diseases which already have considerable amount of data and previous research. The use of predictive analytics in this case requires patients’ data from all possible resources and sensors, and monitor each patient’s status continually to acquire abnormal signals. Besides predictive analytics used in medical diagnosis, this technology is also used in hospital resource management. When hospital resources is limited while patients’ need is huge, one should assign medical resources based on safety and efficiency. Boston Children’s ICU is using IDHA voice deployment to ask administrative information such as number of beds needed, nurses’ distribution etc. Boston Children’s Hospital is planning to develop this system into a “learning” system that anticipates information needs and provides just-in-time guidance.
Amazon Alexa and Hospital Data Mining Strategy
Based on the above arguments on how AI is improving data mining and predictive analytics in hospitals, one question has to be asked: which platform could we use to connect the central hospital database with hundreds of thousands of families/patients scattered around the city, or even around the country? The current answer, though debatable, is Amazon Alexa. Alexa is Amazon's cloud-based voice service available on tens of millions of devices from Amazon and third-party device manufacturers. One of its advantages, compared to other voice assistants, is that Alexa has the huge user database to provide a wide and useful data sample for Alexa hospital data mining strategy. According to Consumer Intelligence Research Partners, there is an estimated 10 million consumers own an Alexa-powered device from Amazon. There are almost 37 million consumers using voice assistant devices for entertainment tasks such as music, news, shopping and smart home devices. They are also potential users of Alexa in medical use.
Besides Alexa’s huge user base, it also achieves successful implications in medical practices. Boston Children's Hospital launched the KidsMD Alexa skill in early 2016 with a goal to provide a trusted source of pediatric education. So far, the hospital has 100, 000 interactions with the skill and 200 unique users each week. Amazon uses its years of experiences in virtual customer interaction and develops the Alexa easy to use for parents and kids learn quickly about common illness, even remotely.
However, Alexa is facing some held-backs. It is still an early technology to be widely installed in healthcare and hospitals. So far, doctors from some a few hospitals use Alexa for digital medical recording. According to a recent survey of Boston Children’s pediatricians, “only 48% of pediatricians would be willing to deploy the voice activation within their practice while 36% were undecided and 16% were against using it. ” Alexa also has to deal with patient privacy and Health Insurance Portability and Accountability Act of 1996 (HIPPA) compliance. Nowadays people are willing to give up certain amount of privacy for conveniences in life and entertainment. However, this progress isn’t as fast in medical and healthcare industries since these issues are vitally important and relates to life. Amazon is already making a lead in smart medical and hospital systems compared to other market players. As long as it works on wide applications of its Alexa system and takes steps to ensure Alexa will safely store and use patient health info, Amazon Alexa could have a promising future in hospital data mining strategy from both technological and compliant aspects.
Amazon Alexa and Google Home
Currently, AI-driven voice assistants like Amazon Alexa, Google Home, Apple Siri or Microsoft Cortana are major market players in this field. Especially Alexa and Google home, which share a combined 51 million American users based on a recent figure. Amazon Alexa, with its advanced progress in home Medicare, unique features as well-rounded, individual-customization and more access to apps and integration of home products, has become a better option in home hospital immobile residences. Amazon Alexa is approaching faster and more productive than Google Home. Alexa, as the first third-party voice assistant device when it first came out, is now use in some healthcare institutions such as Boston Children’s Hospital, Northwell Health, and Beth Israel Deaconess Medical Center. Market reports also indicate that 30 million Echo units have been sold, which represents about 70 percent of the smart home device market. Amazon is actively establishing its own medical and healthcare ecology in the market, by generously sponsoring start-ups to develop their own AI-based technologies in healthcare and hospital uses. For example, Wellpepper, a Seattle-based start-up, won a competition sponsored by Amazon with a grand prize of $125, 000.
Amazon Alexa is well-rounded and individual user-based, while Google Home is general google user based. With Prime membership on Amazon, Alexa users are automatically connected with their personal account on Amazon, together with their other life aspects such as online shopping, prime video and so on. As a home hospital assistant, Alexa not only provides basic medical inquiries, but also fast shopping experiences when necessary. For example, when the doctor recommends healthy food options for the patient at home, it would be much easier to place the order on Alexa. For Google Home users, they have to jump from Google to other websites or service provides to finish such operations. Alexa obviously provides time-saving and cost-effective ways.
Amazon Alexa has more access to apps and integration of home products compared with Google Home. There is another comparative research shown that Alexa supports slightly more smart home devices, for instance, while Google lets you upload your own music to its cloud. For Home Hospital companionship, Alexa could be a better option since more and more healthcare apps have been developed, and patients can connect the preferential ones with Alexa and develop their own medical advisory, recording and analysis. Another research also shows that Alexa platform includes a growing list with more than 15, 000 of “Skills, ” akin to apps on a smartphone. With these skills and built-in functions, Amazon Alexa will have its own home hospital ecology circle and serve home patients at its best than Google Home.
