New additional specialized facilities in India’s leading healthcare institutions are advancing precision medicine in the country through AI.
The Apollo Cancer Center (ACC) in Bengaluru recently launched what could be the country’s first Precision Oncology Center powered by AI. It offers comprehensive, specialized care, tailored to each individual.
The center features AI automation to identify patients eligible for targeted therapy and immunotherapy and alert care teams to patient deterioration. It also uses conversational AI to educate patients and their families about diagnosis, treatment, and connections to support groups. Additionally, it uses AI to monitor compliance with standard of care; enable patient management based on genomic, clinical and pathological data; and make recommendations for diagnostic testing and participation in value-based care and other patient benefit programs.
ACC touts that the use of AI, along with harnessing volumes of health data, is the “future of oncology.” With AI, it can provide accurate diagnoses, real-time insights, cancer risk assessment, treatment protocol and continuum of care.
Leveraging its expertise in AI, the Indian Institute of Science (IISc) recently launched a collaborative laboratory for AI in Precision Medicine with Siemens Healthineers, a well-known brand in medical imaging. The laboratory will develop open-source AI-based tools to automatically segment pathological findings in brain scans. These tools will soon be integrated into regular clinical workflows and are intended to help accurately diagnose neurological diseases and analyze their clinical impact at a population level.
Drs. Vijay Agarwal and Vishwanath S, senior consultants in Medical Oncology at ACC, shared with Healthcare IT news more details on their applications of AI in precision oncology. Vaanathi Sundaresan, assistant professor at IISc Department of Computational and Data Sciences and head of the Siemens Healthineers-Computational Data Sciences Collaborative Laboratory for AI in Precision Medicine, discussed how they plan to protect sensitive patient data amid growing cybersecurity threats.
Q: Can you share specific use cases or applications of AI in your new facility?
Dr. Agarwal, ACC: There is this one case: a woman with a lump in her breast who came to us for consultation. Using AI, she was immediately diagnosed with breast cancer within 24 hours of presentation. After diagnosis, all stakeholders – the treating physician, the lead breast surgeon, the multidisciplinary team coordinator (MDT) and the patient – were informed of the need for an MDT by an automatic alert. After the MDT meeting was held, a recommendation was sent to the center and treatment was initiated. The patient journey was pre-defined using AI and all stakeholders were informed. Once the treatment, which includes chemotherapy, was planned, automatic alerts were built in for a seamless process of admission, ordering medications, prescribing medications, dispensing medications, authorizations (specific to drug regimens and language), discharge and payments, increasing efficiency was improved. and reducing costs. Any change in the treatment plan was automatically communicated to all stakeholders, ensuring seamless and well-integrated care across all specialties. Chemotherapy and targeted therapy were later advised and then the patient was finally referred to the MDT.
Dr. Vishwanath S, ACC: We use AI that fenables early, seamless administration of chemotherapy from registration, bed reservation to discharge. AI also plays a role in facilitating personalized therapy based on NGS (next-generation sequencing) mutation status. Additionally, digital pathology and images can be AI-driven – a good example is the use of bioinformatics and AI to identify a patient with a heavily pre-treated advanced sarcoma and an NGS report showing a targetable mutation.
A/Prof Sundaresan, IISc: Some other relevant applications of AI that are very important for clinical application include population-level modeling of disease progression, adapting the AI models to be robust to variation in data characteristics between sites (domain adaptation), limited data availability ( data sparse regimes), scarcity of manual labels and outliers. Another important long-term direction would be to identify the relationship between brain health and other organs of the body.
Q: What are you planning as the first project of the collaboration lab? How urgent is the need for accurate imaging/diagnosis of neurological diseases and how can AI support this?
A/Prof. Sundaresan: Our first project will be the identification of vascular biomarkers on neuroimaging data that would aid in the early detection of neurodegeneration.
The prevalence of neurodegenerative diseases (such as Alzheimer’s disease and other forms of dementia) and cerebrovascular diseases such as stroke have been associated with cognitive impairment, gait disturbances and brain atrophy, which can sometimes lead to death (with mortality rates of up to 47% reported for stroke) and commonly found in individuals with vascular risk factors and depression. AI methods applied to MRI scans can lead to the detection of imaging biomarkers for personalized treatment. However, differential diagnosis and long-term prognosis of such neurological diseases require very specific imaging biomarkers and thorough investigation of their precise clinical impact – and this is where AI methods can be quite useful.
Q: Given the laboratory’s extensive use of sensitive data, how do you plan to secure and protect this data and the algorithms/models you will apply?
A/Prof. Sundaresan: Most experiments used in the laboratory will involve publicly available data for initial testing. All clinical data obtained for the study (from IISc or collaborators) will be obtained after obtaining approval from the ethics committee and will be strictly anonymized and privacy will be maintained. The methods (without training data) will be open source for the benefit of the broader research community.
_
Their restpunches have been edited for brevity and clarity.