The Second-generation AI systems focus on progress where rather than analysing data for diagnosis assistance, prediction, or tailoring therapy, the second-generation platforms help in improving the biological processes.
Improving global health requires drugs to be more effective and affordable. While there are multiple branded and generic drugs available, partial or complete loss of response to chronic medications is a major cause that leads to ineffectiveness. Combining this with a lack of adherence by patients leads to even more healthcare issues.
The first-generation AI systems did not address these needs, which led to a low adoption rate. But the second-generation AI systems are focused on a single subject – improving patients’ clinical outcomes. The digital pills combine a personalised second-generation AI system along with the branded or generic drug and improve the patient response as it increases adherence and overcomes the loss of response to chronic medications. It works on improving the effectiveness of drugs and therefore reducing healthcare costs and increasing end-user adoption.
There are many examples to prove that there is a partial or complete loss of response to chronic medications. Cancer drug resistance is a major obstacle for the treatment of multiple malignancies, one-third of epileptics develop resistance to anti-epileptic drugs; also, a similar percentage of patients with depression develop resistance to anti-depressants. Other than the loss of response to chronic medications, low adherence is also a common problem for many NCDs. A little less than 50% of severely asthmatic patients adhere to inhaled treatments, while 40% of hypertensive patients show non-adherence.
The second-generation systems are aimed at improving outcomes and reducing side effects. To overcome the hurdle of biases induced by big data, these systems implement an n = 1 concept in a personalised therapeutic regimen. This focus of the algorithm improves the clinically meaningful outcome for an individual subject. The personalised closed-loop system used by the second-generation system is designed to improve the end-organ function and overcome tolerance and loss of effectiveness.
What’s better with second-generation AI systems
The first-generation systems were designed to promote the 4P model: Predictive, Personalised, Preventive, and Participatory treatment and provide patient autonomy. The second-generation AI systems, however, add the ‘5th P‘, which is progress. Rather than analysing data for diagnosis assistance, prediction, or tailoring therapy, the second-generation platforms help in improving the biological processes.
The second-generation AI systems improve quantifiable symptomatic or laboratory endpoints and focus on improving organ function, mental health, and response to drugs. The goal of the algorithms is to get the functionality of the organ back on track.
Many chronic diseases move along a dynamic trajectory that creates a challenge of unpredictable progression. This is often disregarded by first-generation AI as it requires constant adaptation of therapeutic regimens. Also, many therapies do not show loss of response until even a few months. The second-generation AI systems are designed to improve response to therapies and facilitate analysing inter-subject and intra-subject variabilities in response to therapies over time.
Most first-generation AI systems extract data from large databases and artificially impose a rigid “one for all” algorithm on all subjects. Attempts to constantly amend treatment regimens based on big data analysis might be irrelevant for an individual patient. Imposing a “close to optimal” fit on all subjects does not resolve difficulties associated with dynamicity and the inherent variability of biological systems. The second-generation AI systems focus on a single patient as the epicentre of an algorithm and to adapt their output in a timely manner. They continuously respond to feedback in an individualised manner and generate an insightful database.
These platforms do not require a large volume of high-quality data and are expected to be able to function based on input from a single patient. Conventional ML systems developed to analyse massive datasets are not analogous to the way brains perform. The brain learns by analysing data within a certain context. It does not need to watch a thousand aeroplanes to differentiate an aeroplane from a bird. This difference in approach is problematic when trying to achieve good outcomes for individual patients. Generalising from large datasets to a single patient is unsuccessful in many cases due to a large heterogeneity among subjects and to ongoing individualised changes in disease triggers and host responses. The n = 1 concept can be implemented into second-generation platforms by focusing on the dynamicity of disease and response to intervention in a single patient. The multiple host, disease, and environment-related variables learned from big datasets can be implemented into a single subject-based algorithm that analyses input from and generates output to that subject.
Mental and rare diseases
Another major challenge for healthcare systems are patients with rare diseases. From late diagnosis and misdiagnosis to lack of proper response to therapies, and even absence of valid monitoring tools, such patients face major obstacles. The first-generation artificial intelligence (AI) algorithms were designed to improve the management of chronic diseases, but due to the shortage of big data resources in such cases, they did not prove to be helpful. Since the second-generation AI-based systems are patient-tailored, the system provides a means for early diagnosis and even methods for improving the response to therapies, as it is a dynamic system that adapts to ongoing changes in patients’ disease and response to therapy and is not dependent on large datasets.
Second-gen digital pills have also proved results in the treatment of Serious Mental Illness (SMI), which are one of the leading causes of long-term disability worldwide. A Digital Medicine System (DMS), which is basically a drug-device combination for patients with SMI that allows adherence measurement. This provides doctors and caregivers with a lot of insight into the treatment of the patients.
In November 2017, the FDA approved a version of a second-generation antipsychotic, aripiprazole, embedded with a sensor (Abilify MyCite). MIT researchers have created a pill that contains a sensor that can pick up intestinal bleeding. They have also created sensor-containing pills that, when swallowed, are made of hydrogels that swell to the size of a ping pong ball in the gut. That way, rather than passing straight out of the stomach, the ball-sized ingestible sensors can remain in situ for longer and keep tabs on the stomach for a greater time. A swallowable camera called PillCam takes photos of the patient’s bowels as it travels through the gut. The AI spots when it’s at rest and slows down the frame rate and speeds it up when it’s in motion to make sure nothing is missed, and extraneous data isn’t being gathered.