Medical science has improved rapidly, raising life expectancy around the world. As longevity increases, healthcare systems face growing demand for their services, rising costs and a workforce that is struggling to meet the needs of its patients. Artiﬁcial Intelligence (AI) encompasses a broad spectrum emerging technologies establishes high-quality patient care and continue to inﬂuence daily life.
What is artificial intelligence?
The term “artificial intelligence” (AI) coined in the 1950s, refers to the idea of building machines that are capable of performing tasks normally performed by humans. Machine learning (ML) is a subfield of AI, in which algorithms are applied to learn the intrinsic statistical patterns and structures in data, which allows for predicting unseen data for future use.
Machine learning was ﬁrst mentioned in 1959 by Arthur Samuel, who deﬁned it as a process that enables computers to learn without being explicitly programmed. ML is one of the AI ﬁelds that researchers and practitioners have applied broadly, using it for data analysis. Machine learning has made it possible for a computer to classify or predict an outcome from an extensive database.
The most prevalent subfields of AI include:
- Machine learning- Machines use neural networks, physics, and statistics to find insights in data without being explicitly programmed to do so.
- Deep learning- This involves learning complex patterns in large datasets
- Cognitive computing- This simulates human processes through image and speech interpretation and responding appropriately.
- Computer vision- This recognizes content in photos and videos.
- Natural language processing- This is the ability of computers to analyze and generate human speech.
Applications of AI in healthcare:
1. Support medical imaging analysis
AI can support a clinician to review images and scans. This enables radiologists or cardiologists to identify and prioritize critical cases and avoid potential errors in electronic health records (EHRs) and to establish more precise diagnoses. A clinical study generates huge amounts of data and images. AI algorithms can analyse these datasets at high speed and compare them to other studies to pinpoint patterns and out-of-sight interconnections.
2. AI can decrease the cost of drug development
Supercomputers are used to predict molecular structures of potential medicines and its efficacy for various diseases. By using convolutional neural networks, (a technology similar to the one that makes cars drive by themselves), AtomNet was able to predict the binding of small molecules to proteins by analyzing hints from millions of experimental results and protein structures. AtomNet was able to identify a safe and effective drug candidate from the large database, thus reducing the cost of developing drugs.
3. AI analyses unstructured data
Clinicians often struggle to stay updated with the latest medical advances due to huge amounts of health data and medical records. Moreover, patient medical records are stored as complicated unstructured data making it difficult to access and interpret access. EHRs and biomedical data curated by medical units can be quickly scanned by ML to provide prompt and reliable answers to clinicians. AI can seek, collect, store and standardize medical data regardless of the format.
It can also assist with repetitive tasks and supply fast, accurate, tailored treatment plans to the clinician. This will help the clinician provide the appropriate medicine for their patients instead of doing the tedious task of searching, collecting and transcribing solutions from piles of paper formatted EHRs.
4. Developing tools for assessing drug safety.
AI can predict which potential medicines would be effective for various diseases from databases of molecular structures. The AI builds consolidated platforms for identifying and assessing the safety profile of drugs, medical devices, vaccines etc.
5. AI builds consolidated platforms for drug discovery
AI algorithms can identify new drug applications, their toxicity profile and their route of action. This technology has led to creating a drug discovery platform that enables Recursion Pharmaceuticals to repurpose existing drugs and bioactive compounds. By combining elements of biology, data science and chemistry with automation and the latest AI advances, the company is able to generate around 80 terabytes of biological data that by AI tools generate across 1.5 million experiments weekly.
The ML tools draw insights from complex biological datasets thus decreasing the risk of human bias. Identifying new uses for known drugs is a big boon for Big Pharma companies, since it is less expensive to repurpose existing drugs than to create them from scratch.
6. AI can forecast kidney diseases
Acute kidney injury (AKI) can be difficult to detect by clinicians, but can severely patient health and become life-threatening. With an estimated 11% of deaths in hospitals following a failure to identify and treat patients, early detection and treatment of these cases can greatly reduce life-long treatment processes and the cost of kidney dialysis.
7. Assist emergency medical staff
During a sudden heart attack, the time between call and an ambulance arrival is crucial for recovery. For an increased chance of survival, emergency dispatchers must recognize the symptoms of a cardiac arrest to take appropriate measures. AI can analyze both verbal and nonverbal clues and establish a diagnosis from a distance.
8. AI contributes to cancer research and treatment, especially in radiation therapy
In some cases, radiation therapy lacks a digital database to collect and organize EHRs making cancer research and treatment difficult. Automatic generation of clinical notes with EHRs can reduce the time spent by clinicians in patient documentation, thus improving medical operations and health outcomes.
9. AI helps in predictive analytics
Turning EHRs into an AI-driven predictive tool allows clinicians to be more efficient with their workflows, medical decision making and treatment plan.
10. Assist in the discovery and development of genetic medicine
The use of AI in healthcare brings multiple benefits for stakeholders. By improving workflows and operations, assisting the medical and nonmedical staff with tedious tasks, supporting users in finding faster answers and developing innovative treatments and therapies, everyone including patients, payers, researchers and clinicians can greatly benefit from the use of AI.
2. Quintessence Int 2020;51:248–257; doi: 10.3290/j.qi.a43952