While India's industries deal with the aftermath of the crisis, certain innovative technologies have really taken the mainstream. And Artificial intelligence tops the list of those technologies.
In the past, Artificial intelligence and machine learning have been shown to strengthen old systems and increase efficiency in a variety of industries (including healthcare). But the pandemic had just escalated the growth of Artificial intelligence like never before. We have suffered significant setbacks as a result of the COVID-19 pandemic, but artificial intelligence and machine learning can possibly overcome some of these gaps by building appropriate, data-driven solutions to help us through the current crisis by learning from artificial intelligence's accomplishments and drawbacks.
As of now, AI is being successfully used in the identification of monitoring of cases, disease clusters, mortality risk, prediction of the future outbreaks, diagnosis of COVID-19, disease management by resource allocation, pattern recognition for studying the disease trend and much more. Several applications of AI that are garnering a lot of interest and raising hopes in the fight against COVID-19 are as follows:
General Process Flow:
The AI can be used for multiple purposes based on the requirement and need. Here the General process is explained as how AI can be used for Covid Related Cases.
Step 1 - Data Collection
Step 2 - Data Preparation.
Step 3 - Choose a Model
Step 4 - Train the Model
Step 5 - Evaluate the Mode
Step 6 - Parameter Tuning
Step 7 – Analysis
Step 8 – Reporting
1. Data Collection - Covid Related cases can be collected from various sources. AI can take input from the following sources:
Directly from affected persons
PET and CT test Centres
Relatives and Family members of Covid Patients
Government Test Reports
The information feed from these sources can be fed to the Artificial Software.
2. Data Preparation - In order for better understanding of the data, the data has to be sanitised (removal of unrelated information). For example
Frequently Repeated Words
Document file extension type
Improper Access method
3. Choose a Model - Based on the need/requirement of the user the model can be selected from some of the models that are listed below
1. Linear regression
2. Logistic regression
3. Linear discriminant analysis
4. Decision trees
5. Naive Bayes
6. K-Nearest Neighbors
7. Learning vector quantization
8. Support vector machines
9. Bagging and random forest
10. Deep neural networks
4. Train the model - With the various variants of COVID-19 the model can be trained using different algorithms from various regions in India.
5. Evaluate the Mode - From the selected and trained model it evaluates with the different conditions based on the algorithm developed and produces the report as output.
6. Parameter Tuning - Based on the AI model’s Algorithm, the parameters can be set. The data and the information can be gathered for later processing and analysing.
7. Analysis - The developed algorithm the analysed output will be reported in the provided/developed template.
E.g., Graphic flowchart, bar chart, histogram, pdf, word etc.
8. Reporting - The collected data from the model and from the analysis a report/summary is formed and then submitted to the authorized people.
AI Can be used in multiple purposes for COVID-19. As per recent findings, AI – used for tackling COVID can be generally categorized into 3 levels namely,
3. Corrective measures
Before COVID enters the human body, it can be prevented by using AI.
· Finding out existing positive cases
· Covid Positive Patients
· People who were in close contact with Covid positive patients
· People above the age of 60 who are not vaccinated
· People with low immune system
· Frontline workers
· Medical Professionals
The above-mentioned people can be monitored and prevented from further spread of the Corona virus using AI technology.
After detecting the positive Corona patients, we need to ensure the level at which the patients are in.
Level 1: Low level of COVID-19
Level 2: Moderate level of COVID-19
Level 3: High level of COVID-19
Level 4: Very high level of COVID-19
According to this level, based on the Algorithm built, AI will decide and suggest
Availability of the doctor
Availability of the COVID-19 Care centre
Availability of the Bed with oxygen supply and ventilator
Availability of the Bed without oxygen supply and ventilator
Further Customization is possible in AI based on the requirement or need.
We need to ensure all the corrective measures are in place with the help of AI. For example,
Patients recovered from increase/decrease in Oxygen level
Tests performed and result produced
Automate report to doctors and healthcare centres
Report to close family members for quarantine
Prescribe the required medicine
Enable monitoring and reporting
Confirm the recovery status
This entire process can be automated through AI
AI in early diagnosis
AI was used for the detection and quantification of COVID-19 cases from chest x-ray and CT scan images. Researchers have developed a deep learning model called COVID-19 detection neural network (COVNet), for differentiating between COVID-19 and community-acquired pneumonia based on visual 2D and 3D features extracted from volumetric chest CT scan. Singh et al. developed a novel deep learning model using Multi-Objective Differential Evolution and convolutional neural networks for COVID-19 diagnosis using a chest CT scan. Another study used AI-based classifiers for predicting the outcome of RT-PCR results of COVID-19 cases using 16 simple parameters derived from complete blood profile. This may find application in reducing the number of RT-PCR tests in resource-poor settings.
AI in Research
AWS-powered CORD-19 Search can help researchers quickly find COVID-19-related studies and documents. The website uses machine learning to identify relevant papers from its database of more than 128,000 research papers.
AI in prediction & tracking
AI can be harnessed for forecasting the spread of virus and developing early warning systems by extracting information from social media platforms, calls and news sites and provide useful information about the vulnerable regions and for prediction of morbidity and mortality. Bluedot identified a cluster of pneumonia cases and predicted the outbreak and geographical location of the COVID-19 outbreak based on available data using machine learning. HealthMap collects the publicly available data on COVID-19 and makes it readily available to facilitate the effective tracking of its spread. Recently, the role of AI in identification and forecasting of COVID-19 outbreaks by employing multitudinal and multimodal data was emphasized.
AI in contact tracing
AI can augment mobile heath applications where smart devices like watches, mobile phones, cameras and range of wearable device can be employed for diagnosis, contact tracing and efficient monitoring in COVID-19. Applications like AI4COVID-19 that rely on audio recording samples of 2 s cough can be used in telemedicine.
AI in Drug Discovery
Benevolent AI, a UK based set-up, is using its platform to understand the impact of COVID-19 on the patient’s body. Its machine learning platform is helping to identify drugs that can inhibit the progression of the disease.
AI in monitoring of COVID-19 cases
AI techniques are applied for monitoring patients in clinical settings and prediction of course of treatment. Based on the data derived from vital statistics and clinical parameters, AI may provide critical information for resource allocation and decision-making by prioritizing the need of ventilators and respiratory supports in the Intensive Care Unit. AI can also be used for predicting the chances of recovery or mortality in COVID-19 and to provide daily updates, storage and trend analysis and charting the course of treatment.
AI and Big Data
Both University of Copenhagen and Case Western Reserve University are using past data and patterns to suggest if a patient will need a ventilator and for how long.
Frontiers in Public Health journal published a paper titled COVID-19 Patient Health Prediction Using Boosted Random Forest Algorithm that will combine “healthcare data and demographic processing models with CXR scanning models.”
AI in reducing the burden from medical practitioners & healthcare staff
AI can be used for classification of patients based on the severity of symptoms, genetic disposition and clinical reports in different categories like mild, moderate and severe, so that different approaches can be adopted for handling the patients in the most effective manner. AI in telemedicine can also be used to eliminate the need of frequent and unnecessary hospital visits by distant monitoring of cases and recording of patient’s data in asymptomatic cases or patients with mild symptoms. AI-based medical chatbots can also be used for consultations, thereby reducing the physical crowding of hospitals as well as the spread of infection and thus prevent weighing down of efficient operation of critical care services. Chatbots like Clara from the Centre for Disease Control and Zini are providing much needed support to patients in remote settings.
AI in protein structure prediction
AI can help in predicting the structure of important proteins crucial for virus entry and replication and provide useful insight that can pave way for drug development in a very short time. Source: Alpha old algorithm of Google Deep.
AI in development of therapeutics
AI techniques can boost and complement traditional technologies by reducing the time required in bringing a drug from bench to bed by speeding up lead discovery, virtual screening and validation processes by a huge margin. AI can also accelerate the pace by deriving useful data for drug repurposing or drug repositioning by screening properties of already approved and validated drugs based on molecular descriptors and properties, which may not be possible for a human expert. Benevolent AI used machine learning methods to accelerate its drug discovery program and identified baricitinib as a potential drug against COVID-19. Insilico Medicine has identified several small molecules against COVID-19 using AI. Another study combined virtual screening and supervised learning to identify potential drugs against COVID-19. Zhou et al. adopted an integrative network-based systems pharmacological methodology for finding potential drugs for SARS-CoV-2 from the already existing repertoire of drug molecules and drug combinations. Many machine learning approaches and deep learning-based applications are also being used for expediting the drug discovery process.
AI in development of vaccines
Never before has mankind witnessed such a race for the development of a vaccine against a pathogen. The pace of the discovery can be accelerated manifold by harnessing the power of AI. Ong et al. predicted possible vaccine candidates for COVID-19 using the Vaxign reverse vaccinology-machine learning platform that relied on supervised classification models.
AI in curbing spread of misinformation
Due to the avalanche of information, this pandemic has turned into an infodemic. Understanding knowledge, awareness and practices toward COVID-19 by tapping information from social media platforms like Twitter, Facebook etc. can help in devising the strategy to assemble and disseminate timely and correct information for mitigating the impact of COVID-19 .Machine learning techniques can be used to identify trends and sentiment analysis and provide information regarding the origin of false information and help in curtailing the rumours and misinformation .AI techniques can further be used for presenting a clear picture of recovery rates, accessibility and availability to healthcare and identification of the gaps. AI can provide the latest updates about the emerging evidence in diagnosis, treatment, spectrum of symptoms and therapeutic outcomes in this highly dynamic situation, which will help clinicians in real-world scenario and help public in overcoming fear and panic
Big Companies that are using AI to fight COVID-19:
Facebook AI researchers are using publicly available data to help hospitals in Montreal use their own patient data to better forecast what resources they will need to treat people with COVID-19 and applying Multivariate Hawkes Processes to create daily COVID-19 predictions for the state. They are also working on a project that will help hospitals in Montreal use their own patient data to show what resources they will need to treat people with COVID-19.
Google Cloud AI:
According to the statistics of The White House Office of Science and Technology Policy, it had 29,000 articles last year, which has now grown to more than 59,000 this year, that may contain answers to key questions about the virus. It turned to Kaggle, a Google Cloud subsidiary, to call upon its community of more than 4 million data scientists to use AI to help find these answers. Participants have already developed several text and data mining tools to search through this dataset, named COVID-19 Open Research Dataset (CORD-19), to help answer critical questions like, “What do we know about COVID-19 risk factors?”, “What do we know about the virus’ genetics, origin, and evolution?”, and more.
Multiple Technologies used in AI to COVID-19:
A huge number of applications and models appeared right at the beginning of the crisis, most of them driven by start-ups and true to their salt. It’s difficult to list them all, but here are a few prominent ones:
· UC San Diego Health had engineered a machine learning algorithm to detect pneumonia, which is assisting in managing COVID-19 cases.
Two technologies are helping big time:
1. Chest Imaging - According to findings published in Nature Medicine, AI tools can quickly identify COVID-19 from the chest CT scans and the patients’ clinical data. Researchers at Massachusetts General Hospital and Harvard Medical School are developing a deep learning algorithm to identify COVID-19-linked pulmonary disease likelihood and severity.GE Healthcare recently announced a partnership with National Consortium of Intelligent Medical Imaging (NCIMI), UK to create an algorithm for predicting the complications, severity and long-term impact of COVID-19.
2. Blood Biomarkers - John T McDevitt, professor at NYU College of Dentistry and NYU Tandon School of Engineering, and his colleagues are working on an app that uses blood biomarkers and AI to determine the disease’s severity. With details like age, sex and blood biomarkers, the model can arrive at the case severity outputting numerals ranging from 0 to 100, zero being mild to hundred being critical.
Chan Zuckerberg Biohub built a model to know the number of undetected cases and their consequences on public health.
Closedloop, an AI start-up, created an “open-sourced vulnerability index”. The model identified patients who were at the most risk to develop severe complications from COVID-19.
Clevy.io, a French start-up, created a chatbot to channel COVID-19-related government communications. Today, it answers almost 3 million public queries every day.
An artificial intelligence tool developed by New York University researchers is using predictive analytics. This tool finds patterns among patients with early COVID-19 symptoms and identifies who are more likely to get extremely sick. So far, the tool has had a 70-80% success rate using data from 53 patients. Currently in its experimental stage, the researchers are making further developments by expanding the data and improving accuracy
Researchers at NVIDIA and Massachusetts General Brigham Hospital have developed an AI model that determines whether a person showing up in the emergency room with COVID-19 symptoms will need supplemental oxygen hours or even days after an initial exam.
The original AI model, named CORISK actually combines medical imaging and health records to help clinicians more effectively manage hospitalizations at a time when many countries may start seeing a second wave of COVID-19 patients.
In just two weeks, the global collaboration achieved a model with .94 area under the curve (with an AUC goal of 1.0), resulting in excellent prediction for the level of oxygen required by incoming patients.
How Different States in India Are Using AI-Powered Tools to Fight Covid-19?
Kerala is not only the first to get the first few covid cases in India but also one of the first few states in India to use AI for battling the corona virus. They have developed a drone supported with artificial intelligence (AI) that can help combat COVID-19 by monitoring body temperature, supplying essential commodities and spraying disinfectants. It is also used to collect swabs and samples of people for the virus test.
They have launched Artificial Intelligence (AI) based healthcare pods to aid efforts in containment of contagious diseases like covid- 19.
The pods, which can accommodate up to nine beds, uses negative air pressure to help contain airborne diseases such as TB, Flu, and COVID-19, the minister’s office said in a statement.
Similar to Srishti Robotics’ Nightingale-19 Robot, Addverb Technologies has been assisting government quarantine centres in Noida by enabling contactless operations like medicine and food delivery and also to sanitise hospitals and schools.
Staqu, another startup, has launched AI-powered crowd surveillance technologies to help stop the outbreak from spreading. Using its proprietary video analytics platform JARVIS, it is currently being used across the state to help higher officials enforce social distancing rules and identify protocol violators.
Tamil Nadu university develops AI-based software for Covid-19 Preliminary. Professor R Elakkiya who developed the tool said "We developed VGG16, a network trained on 14 million images. I made a transfer learning from that network to my CNN baseline network and I augmented it with 12,000 images," and also gave confirmation of the success of the software by adding "We validated our tool with 150 images from the three government hospitals and found it 100% accurate."
The students of Sri Ramakrishna Engineering College have come up with an AI software that could find out if one is positive for Covd-19 with a chest x-ray. It could also detect severe acute respiratory syndrome (SARS) and pneumonia. A student who was part of the team that developed the software, says, “When the virus enters the lungs, it causes certain changes. The patches have distinct notches and nodes, which could be picked up in the x-ray. The AI software will examine a picture in every x-ray 224 times and identify if it is Covid-19 or not.”
AI Softwares that are used to fight Covid-19 Worldwide:
Deargen - Korea-based Deargen’s scientists published a paper with the results from a deep learning-based model called MT-DTI which employs simplified chemical sequences instead of 2D or 3D molecular structures to predict how strongly a molecule of interest will bind to a target protein. Deargen is now using their deep learning technology to generate new antivirals, but they need partners to help them develop the molecules
Baidu - The Linearfold algorithm from Baidu is made available to scientific and medical teams fighting the outbreak. The Linearfold algorithm is significantly faster than traditional RNA folding algorithms at predicting a virus’s secondary RNA structure. Baidu AI scientists have used this algorithm to predict the secondary structure prediction for the Covid-19 RNA sequence, reducing overall analysis time from 55 minutes to 27 seconds, meaning it is 120 times faster.
Insilico Medicine - The researchers at Insilico Medicine used an AI-powered drug discovery platform to generate tens of thousands of novel molecules that could bind to a specific SARS-CoV-2 protein and prevent the virus from replicating. The list was narrowed by a deep learning filtering system. Insilico is also actively investigating drugs that might improve the immune systems of the elderly, so an older individual might respond to SARS-CoV-2 infection as a younger person does, with milder symptoms and faster recovery.
Bluedot - One of the few companies that sensed the upcoming healthcare crisis in December was Bluedot. On December 30, the company identified a cluster of "unusual pneumonia" cases near a market in Wuhan, China, and reported it. Big data is the secret to BlueDot's success. It gathers data from hundreds of thousands of sources, including official public health pronouncements, internet media, worldwide airline ticketing data, and livestock health data, using natural language processing and machine learning.
EndoAngel Medical Technology Company - A separate AI developed by researchers from Renmin Hospital of Wuhan University, Wuhan Endo Angel Medical Technology Company, and the China University of Geosciences purportedly shows 95-percent accuracy on detecting COVID-19 in chest CT scans. The system is a deep learning algorithm trained on 45,000 anonymized CT scans. According to a preprint paper published on medRxiv, the AI’s performance is comparable to expert radiologists.
Benevolent AI - Benevolent AI, based in London, is developing and applying artificial intelligence for scientific innovation. The company’s Benevolent Platform is a leading computational and experimental drug discovery platform that enables scientists to uncover new ways to treat disease and personalize drugs for patients. The company focuses on target identification, molecular design, and precision medicine to better understand the underlying mechanisms of disease and to develop new treatments. Benevolen AI integrates AI technologies at every step of the drug discovery process, from early discovery to late-stage clinical development.
Nanox - The Israel-based MedTech company, Nanox, has developed a mobile digital X-ray system that uses AI cloud-based software to diagnose infections and help prevent epidemic outbreaks. Also known as the Nanox System, it incorporates a vast image database, radiologist matching, diagnostic reviews and annotations, and also assistive artificial intelligence systems, which combine all of the above to arrive at an early diagnosis. Nanox is currently building on this technology to develop a new standing X-ray machine that will supply tomographic images of the lungs.
IEEE Standards for AI Projects:
As artificial intelligence (AI) and autonomous systems begin to pervade daily life, developers of these technologies must keep certain ethical considerations at hand to ensure the safety of human society during pandemic situation. Technical professional organization IEEE announced three new standards for ethics in AI that prioritize human well-being as these technologies advance during COVID-19 crisis.
As the world's largest technical professional organization, IEEE will introduce knowledge and wisdom based on the accepted facts of science and technology to help reach public decisions that maximize the overall benefits for humanity during pandemic.
The three IEEE standards projects are chaired by subject matter experts in their respective fields of study which will reduce the number of cases. They include the following:
1. Standard for ethically driven nudging for robotic, intelligent, and autonomous systems
This standard examines "nudges," which in terms of AI are overt or hidden suggestions designed to influence human behaviour or emotions. It explains the concepts, functions, and benefits needed to ensure that robotic and autonomous systems are adhering to worldwide ethics and moral theories. It emphasizes the need for aligning the ethics and engineering communities on designing and implementing these systems.
2. Standard for fail-safe design of autonomous and semi-autonomous systems
Autonomous and semi-autonomous systems that malfunction can potentially harm human users, society, and the environment, IEEE noted. Effective fail-safe measures are needed to lower risks related to systems breaking down, and to provide developers, installers, and operators with clear technical instructions to terminate compromised systems safely. This standard establishes clear procedures for measuring, testing, and certifying an autonomous system's ability to fail safely on a scale from weak to strong, along with instructions for improving performance. It also provides a basis for developers, users, and regulators to design these fail-safe systems to improve accountability.
3. Well-being metrics standard for ethical artificial intelligence and autonomous systems
As AI systems improve, programmers, engineers, and technologists must consider how the products and services they build can improve human well-being in terms of economic growth and productivity. This standard identifies human well-being indicators and metrics that may be directly impacted by autonomous and intelligent systems, and provides a baseline to align the data that these systems should include so they can be used to increase human well-being.
As the technology advances, it's clear that autonomous and intelligent systems will play an increasing role our daily lives to prevent, detect and take corrective action. The efforts we undertake today are of utmost urgency to ensure all stakeholders are afforded the peace of mind to know these systems have been well thought out and incorporate the globally accepted ethical considerations at the heart of these technologies.
Top 10 AI technologies will help the current pandemic to the manageable / controllable level.
1. AI Optimized Hardware while implementing Covid-19 pandemic:
The upcoming AI-devices of the digital world are focused on being structured and are used to execute AI-oriented tasks specifically. They have improved graphics and central processing units that accelerated the next generation of application advancements. For example, AI-optimized silicon chips are easily portable and can be inserted into any device when the company needs to get information. These advanced methodologies are opening the door for organizations to invest more in AI applications. Alleviate, Google, Cray, etc. are some of the companies generating AI-optimized hardware solutions to use for current pandemic situation.
2. Using Biometrics to track covid -19 patients:
Biometrics is a futuristic technology that stands as the source of interaction between humans (corona virus infected person) and machines. There are many types of biometrics technology namely face recognition, touch recognition, Iris recognition, DNA matching, Retina recognition, voice recognition, etc. that are making it big in the digital world. Biometrics allows a person to be identified and authenticated based on recognizable and verifiable data, unique and specific.
3. Computer vision to monitor corona virus patients:
Computer vision is the advanced technology that acts as computers’ eyes to monitor corona virus affected people. It is a field of artificial intelligence that helps train machines to interact and understand the visual world. With the help of computer vision technology, machines can accurately identify and classify objects in images, videos and deep learning models. To some extent, computer vision even exceeds human visual abilities in many areas.
4. Wearable Smart devices to corona virus positive people:
As technology is invading people’s everyday life, most of them are seen in close proximity areas with humans like wearables and smart homes. These smart devices are stealing the spotlight in the connected environment. The normal devices that were used for a long time in daily routine are re-modelled as smart devices. For example, smart security cameras, smart speakers, smart watches, smart key chains, etc. are some of the major smart devices that we imply in our life to track the corona virus positive people.
5. Text analytics & NLP to find fake and fraud during the pandemic.
Text analytics alone is an amazing technology that brings breakthrough changes to tech radar. When it is espoused with Natural Language Processing (NLP), text analytics facilitates the understanding of sentence structure and meaning, sentiment, and intent through statistical and machine learning methods. Currently, text analytics and NLP are mainly used in fraud detection and security for corona virus related activities.
6. Decision management ability to reduce the corona virus cases:
To run an effective and efficient control over corona virus, decision management grounds should be firm. With more and more technologies emerging in the modern world, company executives are taking the tech twist to make data-driven decisions. Intelligent machines are designed to frame new rules (as per the requirements of government and health care systems) and logic to AI systems for setting up the decision-making processes, enhance maintenance and optimum tune the routine.
7. Cyber defense for covid-19 related data and information:
When the world is stepping into a new phase of improvement, the digital means is breaking into the working system. As more and more companies take technological grounds, cybercriminals are enjoying the luxury of stealing information from government and hospital to take personal advantages. Henceforth, cyber defence emerge comes for the rescue of data theft. Computer defence mechanism is capable of detecting, preventing and mitigating attacks and threats to data and infrastructure of the systems which is termed as the process of cyber defence for covid-19 related information.
8. Content creation with responsibility and accountability during crisis situation (Covid-19)
In today’s routine, people are entitled to carry out the content creation process. Whether it is making covid19 related videos, images, ads, blogs, white papers, or news stories, humans engage in the initial thought-provoking works. But this won’t continue for a long time. Already, brands like USA Today, Hearst and CBS are availing technology to do the thinking work. In 2021, more such intellectual AI machines will outperform human abilities.
9. Peer-to-peer network leakage or authorized access of covid-19 related patient and healthcare system information.
Connectivity is a big issue in Iota devices, especially; data shared through the connected modes are at critical spots (Government and healthcare centres) of being leaked. However, peer-to-peer network connections address the connectivity problem. It integrates different systems and computers for data sharing without the data being transmitted via a server. Peer-to-peer networks even have the ability to solve the most complex problems.
10. Self-driving cars / Ambulances usage
Finally, fully automated cars ambulances are just a few steps away from daily usage. It has been a long dream for humans to come up with self-driving cars / Ambulance services particularly; the technology sector has taken immense efforts to make this dream come true. This form of artificial intelligence will help reduce collisions and the burden on drivers. Besides, the car is powered with sensors that aides in mapping out the immediate environment of the vehicle.
BENEFITS OF AI:
In the Field of Research: A lot of research has been going on to find more information about the SARS-CoV-2 virus. In this respect, many companies like Microsoft, Chan Zuckerberg Initiative, etc. have come together and released the COVID Open Research Dataset.
Robots to Help Reduce Human Exposure: Many hospitals have considered introducing Robots to take up some tasks so that healthcare staff can be protected.
Time saving - Automation: This is a key factor in the medical field because, AI almost completes almost more effectively than a human being. And also, Automation has had significant impacts on the communications, transportation, consumer products, and service industries
Discovering Vaccines: Artificial Intelligence techniques are being used to find the structure and other information about the virus so that a vaccine can be found soon.
Helping People Receive Genuine News: One of the biggest problems apart from the pandemic is Fake news. And fake news does nothing but spreads fear in the minds of people. So, the WHO has collaborated with Praekelt.Org to deliver precise and helpful information directly to people. They have used AI to help with this initiative to keep the information 100 percent real and authentic.
Statistical Report of protocol and usage of AI apps:
Covid-19 has presented us with new problems to solve and new solutions to develop. While we are still far from victory, AI has allowed us to innovate and fight the pandemic on various levels. What is clear is that AI is most effective when combined with human insight, experience, and empathy. After the pandemic has managed to pass, let us hope to see more of this collaboration in the future to find ways of improving health care for patients all over the world.