A late diagnosis of a disease leading to delayed treatment and recovery is a very acommon occurrence. Now imagine how many lives could be saves if we were able to diagnose a disease even before it appeared in an individual's body. Well, Machine Learning technology is now being explored and leveraged to shorten the diagnosis time of many diseases like cancer.
What is Machine Learning?
Machine learning is an application of Artificial Intelligence that uses algorithms and statistics to find patterns in large amounts of data. Data can be anything: pictures, numbers, words, etc. Machine learning software parses this data and then “learns” from it by applying patterns from which it is able to make predictions. The Machine Learning algorithm looks for a set of rules that allow it to deduce the general characteristics of elements within a group with the objective of applying the learning to similar elements. When the computer is given a completely new image, it will be able to predict the correct label based on ‘previously acquired experience’.
Machine learning has become popular in healthcare for its ability to help with early- diagnosis of diseases, relatively quickly and with accuracy.
Let’s look at a few examples.
Disease Diagnosis by Using ML
In the healthcare setting machine learning can be used to help diagnose disease. It is prevalently used to help screen for breast cancer using ultrasound or X-ray images (such as those shown in Figure 1). This situation is approached using the supervised learning classification since what we want to know is if there is cancer present or not (a discrete binary label). As an added value, it’s possible for the algorithm to state why it classified an image in the way it did, generating valuable knowledge for health experts. According to MIT News a team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Massachusetts General Hospital (MGH) created a new model that can “predict from a mammogram if a patient is likely to develop breast cancer as much as five years in the future.” Trained on over 60,00 mammograms the model can detect the slightest abnormalities in breast tissue. Obviously such technology will have a massive impact on human health. It should be noted, however, machine learning can help identify cancer but the care and treatment a person receives are determined by the doctor.
We engage your customers, workforce, and partners.We engage your customers, workforce, and partners.We engage your customers, workforce, and partners.We engage your customers, workforce, and partners.We engage your customers, workforce, and partners.We engage your customers, workforce, and partners.
Another well-documented healthcare example of machine learning application is in the prediction of Alzheimer’s Disease. In this case, using a set of audio recordings, the machine learning model looks for patterns in the speech of patients with this disease. The analysis is based on the pauses between words, pronunciation, and the frequency and amplitude of sounds. The model helps the expert in geriatric medicine to identify early symptoms of Alzheimer’s through speech.
Current Machine Learning Applications for COVID-19
At the moment, there is no sufficient, reliable, and/or quality data to be able to make predictions related to COVID-19. It is important to note that when machine learning is applied to a problem, it needs vast amounts of data to work with; if this requirement is not met, then not even the best algorithm in the world will be able to come up with reliable predictions.
Kaggle, a page that provides different sets of data for machine learning experimentation, has released labeled data to predict the probability of contracting COVID-19. Table 1 shows part of a set of data, with predictive or descriptive columns. You can observe details such as age, gender, symptom onset date, symptom confirmation date, and travel history (places and dates). These details are considered by experts as potential predictors to determine if a person has been infected with COVID-19.
In China, citizens are monitored by the government using the application WeChat. During the first weeks after the appearance of COVID-19 in Wuhan, the country started to gather information similar to that presented in the table above for each individual, and an application called Health Code was improved. The latter uses a machine learning model to predict the probability of contracting COVID-19. If a person with a high probability of being infected or of being a carrier of COVID-19 leaves their house, then the app will tell them they must remain in isolation. If the person does not heed the warning, then authorities are immediately notified and the person is fined for failure to comply with a health warrant.
Risks
There are a few risks when it comes to applying machine learning for diagnosing diseases:
- Machine learning CANNOT replace a doctor or specialist: although Machine Learning helps to predict the probability of contracting a disease, it does not replace all the work a specialist does. For example, Machine Learning can help identify relatively quickly and early if someone has cancer but the treatment still needs to be determined by the doctor.
- The success of Machine Learning is contingent upon good data. If the data is not of good quality or no patterns can be found in it, then it is useless. Similarly, there’s a risk that when a model is training using a set of data that existing patterns may not apply to new data.
- Doctors and hospitals need to use recently discovered models. In many cases, updating Machine Learning models is not part of a doctor’s line of work. Finding time for a medical specialist to help with the verification of data and results can be difficult. Continuing to use a trained model that no longer makes reliable predictions can be dangerous, especially when human healthcare is involved.It is also risky to change a verified trained model for one that might not work.
Conclusions
Applying machine learning to predict the risk of contracting diseases is not a new technology, but its continual advancements make it more diverse and accurate. Currently, the use of Machine Learning to help in the prediction of COVID-19 infection is being developed, although there is still not enough quality data available. In fact, BBC World (2020) reports that the advance of the pandemic is so fast it makes collecting data difficult. But there is a future possibility that accurate predictions on the probability of infection, related complications , and recovery rate from the COVID-19 virus may be achieved.
Want to learn more about how machine learning can help accelerate your business growth? Let’s talk!
