Vishnu, the CEO of Paradigm IT Cybersecurity, discusses the unique challenges of cybersecurity in the healthcare industry in India. He highlights that healthcare is one of the most targeted sectors for cyber attacks, with valuable data being a major motivation for attackers. He emphasizes the need for strict access control, compliance, and phishing training to prevent attacks. Vishnu also mentions the lack of investment in cybersecurity in the healthcare sector and the potential risks associated with digitization and remote care. He recommends implementing cybersecurity frameworks, employee training, investing in cybersecurity technologies, data access controls, instant response plans, software updates, and strong third-party vendor agreements.

00:00 Intro
00:30 Whats different about cybersec in healthcare
04:09 What low-risk, high-reward
05:00 Cybersec IS an expensive afterthought so...
07:18 How is Indian healthcare responding to cybersecurity?
09:00 Thoughts on a separate health data law?
10:20 New-age care delivery
12:58 Higher chance of a cyber-attack
14:20 Check-list to assess capabilities against a cyber-attack

Back in 2021, Akash Parvatikar Co-authored a paper titled - 'Prototypical models for classifying high-risk atypical breast lesions'. The premise was that some breast lesions are particularly challenging to classify, leading to different pathologists making different diagnoses based on the same information. The paper aimed to reduce this variability by providing a consistent computational method.

A key contribution of this work is that the AI model can explain its recommendations in a way that is useful for clinical practice. This is important because doctors need to understand why an AI system has made a particular diagnosis to trust and act on its recommendations.

In this episode, Akash discusses his work in relation to xAI in diagnosing breast cancer. He discusses the model he developed, which outperformed baseline models in detecting high-risk breast lesions. Akash emphasizes the importance of xAI in building trust and transparency in clinical decision-making tools and explains how his model incorporates explainability through feature detection and contribution scores.

Akash emphasizes the need for explanations to be provided frequently to end users, as it plays a crucial role in building trust in AI systems. He also highlights the importance of involving domain experts in the development of AI models.

0:00 Intro
1:29 Achieving consistent diagnosis is crucial in patient care
4:45 Why does non-uniformity in diagnosis exist in among pathologists
9:40 What were the considerations for model preparation?
14:04 Components of the model and how they incorporate explainability
17:17 How explanation was incorporated - a simplified analogy
22:52 How does xAI manifest itself for pathologists?
26:54 Should explainability be a feature across all AI models in healthcare?
29:29 So explainability in drug discovery is pointless?
31:00 Frequency of explainability
33:51 Domain experts need to be in the loop when building AI models
36:00 Outro

You can reach out to Akash on his LinkedIn at - https://www.linkedin.com/in/akash007/

In this episode, Srikrishna Seshadri shares insights into the design and implementation of care coordination and data aggregation solutions at Tata Consultancy Services (where he was a product manager). The implementation of the Tata Digital Nerve Center, a centralised capacity management center, is highlighted as a successful model for improving healthcare delivery. The key takeaways include the importance of innovation in healthcare delivery, the need for coordination and partnerships, and the value of technology in improving patient outcomes.

He also talks about Previu Health's (a new healthtech company he is a co-founder in) focus on preventive healthcare and the potential of technologies like Google MedPalm 2 in improving public health outcomes.

0:00 Intro
0:34 Does Bengaluru 'Bangalore' even for tech in healthcare?
1:12 Investment Trends in HealthTech startups that catch his eye
3:25 Care Co-ordination and Data Aggregation - A monologue (high value)
17:10 Care Co-ordination from a population health standpoint cannot have vested interests
20:05 Point of care devices will play a huge role for care co-ordination at capacity (say rural health camps)
24:23 How will AI play a role at Previu?
29:53 Google MedPalm 2's role in public health will be evaluated from specific use cases
35:36 Outro