Hey, I’m In-Woo

I’m a 18 y/o high school senior based in Vancouver, BC, Canada, who’s committed to solving the biggest problems in infectious diseases through innovations in biotechnology.

My experience in pharmacy, antibiotic research, biotechnology projects, and business development in digital health has collectively led me to this personal project. In short, I will be developing an AI algorithm to predict disease progression of pulmonary active tuberculosis.

**LinkedIn Personal Website**

I’m solving a problem that should’ve been solved decades ago

I spent the whole month of August 23’ in South Korea for an internship at Novartis, one the largest and most innovative pharmaceutical companies in the world. I also spent that month reconnecting with family, especially my grandmother.

I took her to a large hospital in Seoul for an annual tuberculosis (TB) examination. What appeared in her medical imaging results were small clumps of solid mass, which the physician diagnosed as latent TB. However, what surprised me was what the physician told my grandma:

“You could take antibiotics if you want”

Now, in no way did this make any sense to me. Why couldn’t the physician prescribe? What is the patient—in this case, my grandma—going to do with this information?

This is the problem that I will be solving.

The Problem: The Diagnostic Gap in Tuberculosis

Don’t want to read? Watch this video instead 👇

https://www.loom.com/share/de0e36d5fadb4daeb83623bd96f83d80?sid=e6cbe9b1-d3d1-4545-a1a4-cbcb2f47150b

<aside> 🚨 The Problem

1/4 of the global population is infected with latent TB infections (LTBI) but only 10% of LTBI actually progress to active TB infections (ATBI). However, physicians are not able to determine which LTBIs would progress to ATBI; therefore, 90% of patients are prescribed unnecessary antibiotic treatments with side effects.

Currently, there are few antibiotics available to treat LTBI to kill the “sleeping TB” within the patient, aiming to prevent progression to an ATBI. However, these antibiotics have risks of severe side effects

• e.g., 10% of patients experience anemia or lymphopenia as a result of Rifapentine treatment (10% is a dangerously high incidence rate for drug reactions) </aside>

<aside> 🔍 Root Cause Analysis

• 90% of patients undergo unnecessary antibiotic treatments for LTBI, thereby experiencing preventable side effects - why?

  ⬇️

• There are currently no scalable methods of predicting which LTBIs will progress to ATBIs; therefore, physicians struggle to diagnose the right patients and prescribe the right medications - why?

  ⬇️

• There is research in specific biomarkers that show potential in disease progression prediction; however, the biomarkers individually may serve as attributes to other patient conditions, not only TB - why is this a problem?

  ⬇️

• Without assessing a wider range of biomarkers and variables holistically, the validation for diagnoses may still remain insufficient - what can we do?

  ⬇️

</aside>

<aside> 📢 What The TOP Organizations/Projects Are Currently Doing

• Qiagen - QuantiFERON-TB Gold Plus (QFT-Plus)
• Qure.ai - qTrack
• McGill University Health Center - TSTin3D </aside>

<aside> ❓ Summary: Why Hasn’t This Been Solved Yet?

• Most current solutions can only detect TB; they cannot predict TB disease progression from LTBIs to ATBIs
• Solutions that claim to be able to predict TB disease progression are inaccurate
• Many new solutions (hardware and software) only tend to directly integrate into the healthcare system → not scalable
• The area of research is very new </aside>

The Solution: AI-Driven Analysis of Multiple Biomarkers

Don’t want to read? Watch this video instead 👇

https://www.loom.com/share/a3e960077b8347e5b9c010a00792e44e?sid=46370b4d-f501-4ffc-b7e8-16ada029a0ef