Existing Problems With Hemodialysis

As previously mentioned, the technology and techniques surrounding hemodialysis therapy have remained largely unchanged so far in the 21st century. This has resulted in medical professionals still having a lack of dialysis devices that are capable of reacting to any changes that occur in the middle of the dialysis treatment. These devices are also unable to continually improve themselves through learning from past treatment sessions and using this information to personalize future sessions.

With the number of complications that occur during dialysis treatments, being able to make real-time changes is crucial to help further lower the amount of dialysis-related deaths and reduce the amount of resources required from healthcare professionals.

Current Use of AI in Hemodialysis Therapy

There are several ways that AI technology is currently being tested for its effectiveness in hemodialysis therapy. Two of the most promising areas are the anemia control model (ACM) and the Hemocontrol™ system.

With the ACM, the AI neural network model predicts future hemoglobin concentrations for patients based on their updated clinical data. It also uses an algorithm that provides the optimal exogenous erythropoiesis-stimulating agents (ESA) and iron dosage in an attempt to reach the target hemoglobin level.

Hemocontrol™ helps to prevent intradialytic hypotension (IDH) by analyzing three different variables that include total patient weight loss, blood volume, and average dialysate sodium level. It then takes this up-to-date information and precisely adjusts the sodium concentration of dialysate and UF rate in order to help reduce the rate of IDH.

Future of AI Use in Hemodialysis Therapy

While the current systems being developed and used are a step in the right direction, they still have many improvements to make before they will be able to help significantly reduce the $28 billion cost of hemodialysis care in the U.S.

The biggest areas currently being focused on are miniaturization, flexibility, portability, wearable tech, and “water use” efficiency. Once implantable bioartificial kidneys and wearable artificial kidney tech exist that use dialysate-regenerating sorbent techniques, the treatment of hemodialysis therapy will see significant advancements and result in lesser burdens on healthcare professionals.

In order to get other current news regarding AI and machine learning use in healthcare, make sure to follow our blog at RediMinds today.

Current Screening Practices Fall Short

The accuracy of mammograms has improved tenfold in recent years, but current practices are still only just over 80 percent accurate. This leaves a lot of room for improvement, which is why medical professionals are exploring the ways AI technology could be used during the screening process in order to significantly raise this accuracy by lowering the rate of both false negatives and false positives.

International Effort to Improve Screenings By Using AI

A group of researchers conducted an international study that involved subjects from both the United Kingdom and the United States. By using a database of 28,953 different women, they were able to train an AI system to effectively identify signs of potential breast cancer. Out of this database, all of the subjects had undergone biopsies or additional imaging at least a full year later in order to confirm whether or not they had breast cancer.

Originally, this particular set of women consisted of 6.3 percent false positives and 12.1 percent false negatives. However, with the use of the AI system, both of these numbers were able to be significantly lowered and the workload of a second reader was able to be reduced by as much as 88 percent. By being able to reduce the workload by such a large amount, it allows medical professionals to be able to accurately go through significantly more tests.

In order to further determine how much more accurate the AI system was, its results were directly compared against the decisions made by six expert radiologists who analyzed 500 random cases from the database, in addition to the historical decisions made by the radiologists who were originally involved in screening the individuals from the database. The results of this study concluded that the use of an AI system provided an AUC of 0.871, which is significantly better than the AUC of 0.750 from the original screenings.

With such a major reduction in false negatives and false positives, it indicates that incorporating AI systems into the breast-screening process can have significant improvements in medical facilities throughout the country. In order to receive even more news regarding AI and machine learning use in healthcare, make sure to follow our blog at RediMinds.

Problems with Conventional Prediction Models

In conventional approaches, the prediction models used for AKI rates were unable to be accurately applied to larger groups of patients as they ignore vast physiological time-series data. These limitations prevented them from being of any significant clinical value who are still spending a lot of time and resources trying to treat patients with post-surgical AKI.

How Machine Learning Improves AKI Prediction

The previously mentioned study included a group of 2,911 adults who had surgery at the University of Florida Health sometimes from 2000 to 2010. By using a combination of statistical analysis and machine learning algorithms, the researchers were able to create a perioperative model that was capable of attempting to predict the risk of these patients developing AKI during the course of their illness.

The results were segmented and analyzed as three separate time periods. The first was within three days after the date of the surgery, the second time period was within seven days of the surgery, and the third time period was from the date of the surgery to as far as the data went. One of the biggest differences in these models when compared to other existing ones was the inclusion of intraoperative physiological time-series variables.

By using this new prediction model, the researchers were able to achieve much higher accuracy when compared to the previous models across all three time periods. In total, the machine learning algorithm correctly reclassified 40 percent of patients who had originally received a false negative. These patients were now being classified as high-risk for developing AKI, which would have allowed them to get the preemptive treatment they needed.

When someone develops AKI, it makes them much more susceptible to developing future cases of AKI and also increases the likelihood of them developing morbidity, heart disease, a stroke, and much more. Therefore, the increased accuracy of this machine learning prediction algorithms means that significant amounts of money and man-hours will be saved trying to treat AKI and its related future health issues.

The results of this study indicate that with a machine learning-based prediction model, future predictions of AKI risk will soon be far more accurate in nation-wide predictions for any group of patients. To get more up-to-date news regarding AI and machine learning use in healthcare, make sure to follow our blog at RediMinds.

How Coronavirus Was Flagged By AI

The sooner that medical professionals can become aware of serious diseases, the sooner that they can begin to take steps to better prepare themselves in order to handle it. That is why it is so crucial to have systems like BlueDot’s, which used its AI system to identify Coronavirus as a lingering health crisis over a week before the World Health Organization (WHO) alerted the public about the new strain of the disease.

Its natural language processing and machine learning algorithm was able to do so by automatically reading through over 100,000 articles every single day. Therefore, it becomes aware of a potential disease outbreak when it is still in its very early stages. In fact, the system is able to accurately track over 100 infectious diseases simultaneously, one of which happened to be the new strain of Coronavirus.

Even once the disease was publicly acknowledged as a health crisis, AI systems continue to be used in order to predict how it is going to spread. The perfect example of this is the Healthmap system, which automatically aggregates data from various chat rooms, news reports, and many other online sources in order to create a current database of confirmed cases of various diseases. It is then able to generate a visual map representing how the diseases have spread from the beginning and how they are likely to continue to spread.

Not only that, AI algorithms are also helping to identify early signs of hemodynamic instability, a common COVID-19 complication.

How AI Will Be Used in the Future to Predict Serious Diseases

It is not just the Coronavirus that AI systems can be used to predict. They are also able to be applied to nearly every type of serious disease as long as they are given the right data to be trained with, which is where initiatives like the Global Virome Project come in handy.

This research effort is attempting to develop a very detailed ecological and genetic database of current animal viruses that could possibly infect humans. By having this information readily available, it can be provided to new and current AI algorithms to help them better predict which diseases are more likely to spread to the public.

In order to stay up-to-date on news regarding the application of AI and machine learning in healthcare, make sure to follow our blog at RediMinds today.

Predicting Sepsis

In an intensive care environment, the sepsis is associated with high morbidity and mortality and difficult to treat complication. Patients who have developed sepsis are a major part of what makes ICU patient treatment so expensive. In fact, the cost of treating sepsis has risen by $1.5 billion in the past three years alone. This is partially due to the fact that conventional prediction models are only able to predict sepsis with a maximum accuracy of 0.725 area under the curve (AUCs).

However, through the use of deep learning models, tests have shown that it is able to predict which children would develop sepsis as early as 12-hours before onset and maintain an AUC of 0.83. This means that doctors will be able to effectively preempt the occurrence of sepsis and treat the same with appropriately selected antibiotics and save thousands or even millions of dollars in the process.

Predicting Mortality Rates

Understanding the probability of mortality with any extreme accuracy is something that has remained challenging due to the complexity of ICU patients in each medical facility. But with the use of Deep Learning Models, researchers have been able to track lab results, physiologic observations, and any administered drugs i.e the entire patient data in order to create mortality probability predictions that are far superior to previous models.

In fact, using the new algorithms achieved an AUC of 0.93 and allows doctors to more accurately understand the risk of mortality associated with each ICU patient and take the appropriate life-saving and cost-saving measures.

Predicting Proper Mechanical Ventilator Removal

The use of mechanical ventilation requires an eventual ventilator removal, which can significantly increase the risk of mortality if done too early or too late. Prolonged ventilation is associated with significant complications as well as it involves huge opportunity cost of blocking a scarce resource. Whereas premature weaning of ventilation increases reintubation and readmission rates. Hence predicting optimal time of weaning the patients off the ventilation is a challenging task for the clinicians in ICU.

A study done using an AI algorithm has demonstrated that this predictive model is able to more accurately predict when extubation should take place. With an AUC of 0.82, which has significantly improved the predicting power of the intensivists.

But it is important to note that this algorithm is limited to the fact that it can help to predict when a specific time is okay to perform extubation. However, it is not able to indicate whether it also would have been fine to perform the extubation earlier or later than when it was. Therefore, improved AI algorithms with larger datasets are needed to help further the accuracy of optimal extubation prediction.

These three areas are only the start of how AI systems are expected to revolutionize the treatment of ICU patients and hospital operations in general. To get more industry news regarding the use of artificial intelligence in clinical care, make sure to subscribe to our blog at RediMinds.