Jussi Paananen is the head of technology at Blueprint Genetics. He is in charge of directing and developing company’s data science, AI and software technology efforts. He has a Master’s Degree in Computer Science and a PhD in Molecular Medicine. He has worked as a Fulbright scholar and research affiliate at the Broad Institute of MIT and Harvard, and as an Assistant Professor and Manager of Bioinformatics Center at the University of Eastern Finland. He has an extensive track-record of publishing scientific publications, software and databases in the fields of genetics, bioinformatics and data science as well as experience from co-founding two life-science start-ups. Read his full bio.
Interview with Jussi Paananen of Blueprint Genetics Inc.
Q: Artificial intelligence (AI) techniques have sent vast waves across healthcare, even fueling an active discussion of whether AI doctors will eventually replace human physicians in the future. Do you believe that human physicians will be replaced by machines in the foreseeable future? What are your thoughts?
A: Right now, we are looking at merely a fragment of clinical work that could be replaced by a machine. The whole question whether “we need humans” is strange, for us at least the question is what can humans and very sophisticated software do together and how far can we reach? Humans are of course needed. A lot of clinical work is about presence, listening, problem-solving and decision-making to name a few and I don’t see this changing in the near future. However, machines and software can enable a lot of improvements such as better access to healthcare in developing countries where healthcare services are limited. Augmented Intelligence, which in healthcare could refer to bringing more knowledge and insights to the clinicians, providing solutions in areas where machine performs better and faster than a human. For example, doing observations and finding connections from large amounts of data (imaging, publications, databases and existing scientific and medical knowledge in general).
Q: Can you provide some use cases that have already successfully demonstrate the value of AI/Machine Learning in healthcare?
A: There are many areas that hold promise but so far, a lot of it is still hype. We have seen some so-called AI-solutions that have turned out to be simple implementations of standard software, whereas genuinely scientifically and technologically advanced solutions often take a very long time to be implemented in the clinical environment. However, for example in medical imaging there are many successful applications that speed up processing of images and videos. This market is growing and becoming a more common resource for healthcare professionals. Many interesting players exist in this field, for example Google DeepMind Health and new startups such as Finnish company Aiforia working with deep learning-based microscopy image processing. Our own work in improving clinical interpretation of genetic testing using machine learning shows a great promise in supporting the awesome work that our geneticist team is doing. We believe our approaches will not only enable more efficient processing of massive numbers of genomes, but can also result in novel discoveries.
Q: What areas in healthcare will benefit the most from AI/Machine Learning applications and when will that be?
A: Screening large amounts of patients, predictive and preventive healthcare to name a few. In the future, a machine could screen through masses of genetic data for an analysis that could provide information on risks or recommend lifestyle choices and preventive treatments. Additionally, other high-throughput technologies such as metabolomics hold a lot of promise. Good example of this is Nightingale Health, which just brought their high-throughput metabolomics platform to direct-to-customer market, and hopes to change the way how clinical chemistry is performed globally.
Q: What are some of the challenges to realize AI/Machine learning in healthcare?
A: Availability of talented people, regulation (requires proof and validation that the things we do are safe), and for businesses, timing the strategy (high reward comes with high risk). Just a couple of years ago there was general suspicion towards cloud-based solutions and AI in healthcare. This has already begun to change. Healthcare is conservative in a way that implementing changes takes time, which is widely a good thing. You need special attention and external validation to successfully bring AI/ML based solutions to the clinical space, and this can be an obstacle for companies that are only experienced in either software or AI/ML.
Q: What are the services Blueprint Genetics develops in the AI/Machine Learning sector? What makes Blueprint Genetics unique?
A: Blueprint Genetics provides clinical genetic testing, so for us, it is important to develop tools to support clinical interpretation which typically is the bottleneck in mainstreaming genetic testing. We have a great team of 30 geneticists that wade through scientific and medical data. Among millions of variants they identify a variant that causes a disease. Even with good tools, it still can take a long time from an experienced clinical geneticist to arrive to a conclusion. With our software development and machine learning approaches we are speeding up this process dramatically. At the same time, we are creating a world class curated data resource on rare disease genetics.
Q: What are the short-term challenges that Blueprint Genetics and its peers are facing?
A: Availability and competition for the talented people. A certain challenge, but also an opportunity, is that the field is not yet that stabilized. The market is growing, and different companies are adapting to the swift changes in the NGS-based landscape of genetic testing.
Q: What is your role at Blueprint Genetics and what excites you about your work?
A: I’m the Chief Technology Officer at Blueprint Genetics. I’m in charge of directing and developing company’s data science, AI and software technology efforts. I benefit from the fact that I have background from both software engineering and data science as well as genetics. I love my work because of the sense of purpose and really being able to help real patients. Today, we are big enough to take on the challenge of solving problems in genetics and healthcare, and have the resources to develop and acquire the tools we need. We are small enough to be very dynamic. The constant change and growth of the company allows us to become even more data and software development driven.
Q: Is there anything else you would like to share with the PMWC audience?
A: Really looking forward to connecting with colleagues at PMWC! Throw me a message for example on Twitter @datadriveby if you want to meet and discuss further.
The Precision Medicine World Conference (PMWC), in its 17th installment, will take place in the Santa Clara Convention Center (Silicon Valley) on January 21-24, 2020. The program will traverse innovative technologies, thriving initiatives, and clinical case studies that enable the translation of precision medicine into direct improvements in health care. Conference attendees will have an opportunity to learn first-hand about the latest developments and advancements in precision medicine and cutting-edge new strategies and solutions that are changing how patients are treated.
See 2019 Agenda highlights:
- Five tracks will showcase sessions on the latest advancements in precision medicine which include, but are not limited to:
- AI & Data Science Showcase
- Clinical & Research Tools Showcase
- Clinical Dx Showcase
- Creating Clinical Value with Liquid Biopsy ctDNA, etc.
- Digital Health/Health and Wellness
- Digital Phenotyping
- Diversity in Precision Medicine
- Drug Development (PPPs)
- Early Days of Life Sequencing
- Emerging Technologies in PM
- Emerging Therapeutic Showcase
- FDA Efforts to Accelerate PM
- Gene Editing
- Genomic Profiling Showcase
- Immunotherapy Sessions & Showcase
- Implementation into Health Care Delivery
- Large Scale Bio-data Resources to Support Drug Development (PPPs)
- Microbial Profiling Showcase
- Microbiome
- Neoantigens
- Next-Gen. Workforce of PM
- Non-Clinical Services Showcase
- Pharmacogenomics
- Point-of Care Dx Platform
- Precision Public Health
- Rare Disease Diagnosis
- Resilience
- Robust Clinical Decision Support Tools
- Wellness and Aging Showcase
See 2019 Agenda highlights:
- Five tracks will showcase sessions on the latest advancements in precision medicine which include, but are not limited to:
- AI & Data Science Showcase
- Clinical & Research Tools Showcase
- Clinical Dx Showcase
- Creating Clinical Value with Liquid Biopsy ctDNA, etc.
- Digital Health/Health and Wellness
- Digital Phenotyping
- Diversity in Precision Medicine
- Drug Development (PPPs)
- Early Days of Life Sequencing
- Emerging Technologies in PM
- Emerging Therapeutic Showcase
- FDA Efforts to Accelerate PM
- Gene Editing / CRISPR
- Genomic Profiling Showcase
- Immunotherapy Sessions & Showcase
- Implementation into Health Care Delivery
- Large Scale Bio-data Resources to Support Drug Development (PPPs)
- Microbial Profiling Showcase
- Microbiome
- Neoantigens
- Next-Gen. Workforce of PM
- Non-Clinical Services Showcase
- Pharmacogenomics
- Point-of Care Dx Platform
- Precision Public Health
- Rare Disease Diagnosis
- Resilience
- Robust Clinical Decision Support Tools
- Wellness and Aging Showcase
- A lineup of 450+ highly regarded speakers featuring pioneering researchers and authorities across the healthcare and biotechnology sectors
- Luminary and Pioneer Awards, honoring individuals who contributed, and continue to contribute, to the field of Precision Medicine
- 2000+ multidisciplinary attendees, from across the entire spectrum of healthcare, representing different types of companies, technologies, and medical centers with leadership roles in precision medicine