Machine Learning And Its Use Case

What is Machine Learning?

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves.

The process of learning begins with observations or data, such as examples, direct experience, or instruction, in order to look for patterns in data and make better decisions in the future based on the examples that we provide. The primary aim is to allow the computers learn automatically without human intervention or assistance and adjust actions accordingly.

Some machine learning methods

Machine learning algorithms are often categorized as supervised or unsupervised.

Supervised machine learning algorithms 

It can apply what has been learned in the past to new data using labeled examples to predict future events. Starting from the analysis of a known training dataset, the learning algorithm produces an inferred function to make predictions about the output values. The system is able to provide targets for any new input after sufficient training. The learning algorithm can also compare its output with the correct, intended output and find errors in order to modify the model accordingly.

Unsupervised machine learning algorithms 

When the information used to train is neither classified nor labeled. Unsupervised learning studies how systems can infer a function to describe a hidden structure from unlabeled data. The system doesn’t figure out the right output, but it explores the data and can draw inferences from datasets to describe hidden structures from unlabeled data.

Semi-supervised machine learning algorithms 

It fall somewhere in between supervised and unsupervised learning, since they use both labeled and unlabeled data for training – typically a small amount of labeled data and a large amount of unlabeled data. The systems that use this method are able to considerably improve learning accuracy. Usually, semi-supervised learning is chosen when the acquired labeled data requires skilled and relevant resources in order to train it / learn from it. Otherwise, acquiring unlabeled data generally doesn’t require additional resources.

Reinforcement machine learning algorithms 

It is a learning method that interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning. This method allows machines and software agents to automatically determine the ideal behavior within a specific context in order to maximize its performance. Simple reward feedback is required for the agent to learn which action is best; this is known as the reinforcement signal.

Machine learning enables analysis of massive quantities of data. While it generally delivers faster, more accurate results in order to identify profitable opportunities or dangerous risks, it may also require additional time and resources to train it properly. Combining machine learning with AI and cognitive technologies can make it even more effective in processing large volumes of information.

How does machine learning work?

Machine learning utilizes various techniques to intelligently handle large and complex amounts of information to make decisions and/or predictions.

In practice, the patterns that a computer (machine learning system) learns can be very complicated and difficult to explain. Consider searching for dog images on Google Search as seen in the image below, Google is incredibly good at bringing relevant results, yet how does Google search achieve this task? In simple terms, Google search first gets a large number of examples (image dataset) of photos labeled “dog” then the computer (machine learning system) looks for patterns of pixels and patterns of colors that help it guess (predict) if the image queried it is indeed a dog.

At first, Google’s computer makes a random guess of what patterns are reasonable to identify a dog's image. If it makes a mistake, then a set of adjustments are made for the computer to get it right. In the end, such collection of patterns learned by a large computer system modeled after the human brain (deep neural network), that once is trained, can correctly identify and bring accurate results of dog images on Google search, along with anything else that you could think of such process is called the training phase of a machine learning system.

Imagine that you were in charge of building a machine learning prediction system to try and identify images between dogs and cats. As we explained above, the first step would be to gather a large number of labeled images with “dog” for dogs and “cat” for cats. Second, we would train the computer to look for patterns on the images to identify dogs and cats, respectively.

Once the machine learning model has been trained , we can throw at it (input) different images to see if it can correctly identify dogs and cats. As seen in the image above, a trained machine learning model can (most of the time) correctly identify such queries.

MACHINE LEARNING IN HEALTHCARE

The healthcare sector has long been an early adopter of and benefited greatly from technological advances. These days, machine learning (a subset of Artificial Intelligence) plays a key role in many health-related realms, including the development of new medical procedures, the handling of patient data and records and the treatment of chronic diseases. As computer scientist Sebastian Thrum told the New Yorker in a recent article titled “A.I. Versus M.D., “Just as machines made human muscles a thousand times stronger, machines will make the human brain a thousand times more powerful.”

MACHINE LEARNING APPLICATIONS IN HEALTHCARE

Machine learning has virtually endless applications in the healthcare industry. Today, machine learning is helping to streamline administrative processes in hospitals, map and treat infectious diseases and personalize medical treatments.

Despite warnings from some doctors that things are moving too fast, the rate of progress keeps increasing. And for many, that’s as it should be. "AI is the future of healthcare,” Fatima Paruk, CMO of Chicago-based Allscripts Analytics, said in 2017. She went on to explain how critical it would be in the ensuing few years and beyond — in the care management of prevalent chronic diseases; in the leveraging of “patient-centered health data with external influences such as pollution exposure, weather factors and economic factors to generate precision medicine solutions customized to individual characteristics”; in the use of genetic information “within care management and precision medicine to uncover the best possible medical treatment plans.”

“AI will affect physicians and hospitals, as it will play a key role in clinical decision support, enabling earlier identification of disease, and tailored treatment plans to ensure optimal outcomes,” Paruk explained. “It can also be used to demonstrate and educate patients on potential disease pathways and outcomes given different treatment options. It can impact hospitals and health systems in improving efficiency, while reducing the cost of care."

Here are five applications of machine learning in healthcare, along with some companies that harness its power to benefit patients and providers.

SMART RECORDS

QUOTIENT HEALTH

Location: Denver, Colorado

How it’s using machine learning in healthcare: With the help of machine learning, QUOTIENT HEALTH developed software that aims to “reduce the cost of supporting EMR [electronic medical records] systems” by optimizing and standardizing the way those systems are designed. The ultimate goal is improved care at a lower cost.

Industry impact: The company’s founding CEO Jason Michael O'Rourke recently spoke about "Healthcare’s Disruptive Next Generation" at the YJP CEO Healthcare Symposium in New York.

KENSCI

Location: Seattle, Washington

How it’s using machine learning in healthcare: KenSci uses machine learning to predict illness and treatment to help physicians and payers intervene earlier, predict population health risk by identifying patterns and surfacing high risk markers and model disease progression and more.

Industry impact: KenSci recently partnered with healthcare consulting firm T3K Health to focus on helping caregivers harness AI and machine learning for health records and workflow.

CIOX HEALTH

Location: Alpharetta, Georgia

How it's using machine learning in healthcare: Ciox Health uses machine learning to enhance "health information management and exchange of health information," with the goal of modernizing workflows, facilitating access to clinical data and improving the accuracy and flow of health information. 

Industry impact: The company recently partnered with Chicago-based Northwestern Memorial Healthcare "to bring efficiency and transparency to Northwestern Memorial’s release of information (ROI) process."

MEDICAL IMAGING AND DIAGNOSTICS

PATHAI

Location: Cambridge, Massachusetts

How it’s using machine learning in healthcare: PathAI's technology employs machine learning to help pathologists make quicker and more accurate diagnoses as well as identify patients that might benefit from new types of treatments or therapies.

Industry impact: In 2017 the company raised an additional $11 million in a Series A funding round, which brought its total bank to $15 million.

QUANTITATIVE INSIGHTS

Location: Chicago, Illinois

How it’s using machine learning in healthcare: Quantitative Insights want to improve the speed and accuracy of breast cancer diagnosis with its computer assisted breast MRI workstation Quantx. The goal: better results for patients via improved diagnoses by radiologists.

MICROSOFT

Location: Redmond, Washington

How it’s using machine learning in healthcare: Microsoft's Project InnerEye employs machine learning to differentiate between tumors and healthy anatomy using 3D radiological images that assist medical experts in radiotherapy and surgical planning, among other things. 

Industry impact: InnerEye is used in the United Kingdom to produce 3D imaging that pinpoints the precise location of tumors and enables more accurately targeted radiotherapy.

DRUG DISCOVERY AND DEVELOPMENT

PFIZER

Location: New York, New York

How it’s using machine learning in healthcare: With the help of IBM’s Watson AI technology, Pfizer uses machine learning for immuno-oncology research about how the body’s immune system can fight cancer. 

Industry impact: According to fiercebiotech.com, Pfizer expanded its collaboration with Chinese tech startup XtalPi “to develop an artificial intelligence-powered platform to model small-molecule drugs as part of its discovery and development efforts.

The project will combine quantum mechanics and machine learning to help predict the pharmaceutical properties of a broad range of molecular compounds.”

INSITRO

Location: San Francisco, California

How it’s using machine learning in healthcare: Machine learning and data science combined with advanced laboratory technology are helping recent startup insitro develop drugs with the goal of more quickly curing patients at a lower cost. 

Industry impact: Insitro’s list of top-tier investors includes ARCH Venture Partners, Foresite Capital, a16z, GV and Third Rock Ventures.

BIOSYMETRICS

Location: Boston, Massachusetts

How it’s using machine learning in healthcare: Via its machine learning platform Augusta, BioSymetrics “enables customers to perform automated ML and data pre-processing,” which improves accuracy and eliminates a time-consuming task that’s typically done by humans in different sectors of the healthcare realm, including biopharmaceuticals, precision medicine, technology, hospitals and health systems.

Industry impact: BioSymetrics’s recently announced Strategic Advisory Board will work with company leadership team to advance healthcare and R&D innovation via machine learning and integrated analytics.

MEDICAL DATA

CONCERTO HEALTH AI

Location: New York, New York

How it’s using machine learning in healthcare: Concerto Health AI uses machine learning to analyze oncology data, providing insights that allow oncologists, pharmaceutical companies, payers and providers to practice precision medicine and health. 

Industry impact: Its recently launched platform, Eureka Health Oncology, uses deep data from electronic medical records to offer AI solutions for the management, delivery and use of clinical data.

ORDERLY HEALTH

Location: Denver, Colorado

How it’s using machine learning in healthcare:  Orderly Health thinks of itself as “an automated, 24/7 concierge for healthcare” via text, email, Slack, video-conferencing. The company’s goal is to help employers and insurers save time and money on healthcare by making it easier for people to understand their benefits, locate the least expensive providers. enabling employees or members to understand their benefits and find lowest cost providers.

Industry impact: Orderly joined TreeHouse Health’s stable of startups in 2017 and landed a grant months later to expand its operations.

TREATMENT AND PREDICTION OF DISEASE

BETA BIONICS

Location: Boston, Massachusetts

How it’s using machine learning in healthcare: Beta Bionics is developing a wearable “bionic” pancreas it calls the iLet, which manages blood sugar levels around the clock in those with Type 1 diabetes.”

Industry impact: The company was recently awarded an SBOR grant valued at up to $2 million by the NIH-affiliated National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK).

PROGNOS

Location: New York, New York

How it’s using machine learning in healthcare: The company claims its Prognos Registry contains 19 billion records for 185 million patients. With an assist from machine learning, Prognos’s AI platform facilitates early disease detection, pinpoints therapy requirements, highlights opportunities for clinical trials, notes gaps in care and other factors for a number of conditions.        

Industry impact: Last year Prognos reportedly raised $20.5 million in a Series C funding round. The backing came from insurance companies, drug manufacturers and venture capitalists.

BERG

Location: Framingham, Massachusetts

How it’s using machine learning in healthcare: Powered by AI, Berg's Interrogative Biology platform employs machine learning for disease mapping and treatments in oncology, neurology and other rare conditions. Using patient-driven biology and data, the company allows healthcare providers to take a more predictive approach rather than relying on trial-and-error.

Industry impact: Berg’s director of digital health, Vijetha Vemulapalli, recently took part in the Artificial Intelligence in Healthcare Conference in Boston.

Thankyou For Reading ??