The two year slog from computer science foundations to healthcare machine learning with a self designed curriculum
Program Duration: December 19, 2024 – December 18, 2026 Structure: 8 Quarters (~3 months each)
Primary Objectives:
Develop strong foundations in CS, math, and algorithms. Gain proficiency in data science, ML, and DL techniques. Integrate understanding of healthcare systems, organ donation processes, and emotional AI principles. Apply learned skills to build a predictive OPO referral volume tool by the program’s end.
General Approach:
Weekly Routine:
Coding & Project Work: ~10-12 hrs/week Reading/Theory: ~5-6 hrs/week Math/Algorithms Practice: ~2-3 hrs/week Reflection/Documentation: ~1-2 hrs/week (in Notion)
Monthly Checkpoints:
Create a short self-quiz (5–10 questions) covering that month’s topics. Update Anki/flashcards for key terms, formulas, and healthcare/AI concepts. Perform a well-being check and adjust workload if necessary.
Quarterly Reflections:
Write a 1–2 page essay in Notion summarizing key learnings, struggles, and relevance to OPO referral predictions, empathy, and cultural sensitivity.
Community Engagement (Optional):
Once per month, engage in an online forum or Slack group related to healthcare AI, ask a question, or share a small insight.
Mentorship/Peer Exchange (If Possible):
Once per quarter, attempt a short interaction (email, LinkedIn, or forum) with a professional in healthcare AI to gather feedback or advice.
Well-Being and Sustainability:
Every 2-3 weeks, evaluate your balance of study, rest, and other life activities. Adjust as needed to maintain motivation.
Year 1, Quarter 1 (Dec 19, 2024 – Mar 18, 2025)
Focus: Core Computer Science Foundations, Web Basics, Introduction to Healthcare & Organ Donation
Objectives This Quarter:
Build a foundational understanding of programming, algorithms, and basic web development. Understand the structure of organ donation systems and the OPO environment. Acquire basic math skills (algebra, precalculus) essential for future computational work.
Action Items:
Computer Science & Web Fundamentals:
Complete The Odin Project: Foundations (HTML, CSS, basic JavaScript). Start CS50 (edX, free): Finish Weeks 0–3 lectures and problem sets to understand fundamental computing concepts, including problem-solving, data types, and control structures.
Mathematics Foundations:
Khan Academy: Complete Algebra & Precalculus units to ensure a solid math baseline. MIT OCW Discrete Math (Intro Lectures): Begin exploring sets, basic logic, and simple proofs at a slow pace (1–2 lectures/month).
Healthcare & Organ Donation Context:
Read overviews from the UNOS & OPTN websites to understand the US organ allocation system. Read WHO transplantation ethics guidelines (public domain) to contextualize global healthcare standards.
Reflection & Retention:
Set up Anki flashcards for basic CS terms, organ donation acronyms, and ethical principles. Conduct a monthly self-quiz on HTML, CSS terms, simple algorithmic thinking, and key organ donation facts.
Resources This Quarter:
Book: Structure and Interpretation of Computer Programs (SICP), Ch.1–2 (free PDF online). SICP provides conceptual depth in programming. Research Paper: A review article on organ donation (e.g., a free paper from American Journal of Transplantation available on PubMed Central) to understand current challenges in the field. Online Lecture Series: CS50 lectures (Harvard’s free videos on edX) to guide foundational CS concepts.
Project Q1:
Project #1: Create a static webpage explaining the organ donation process and basic healthcare concepts. Include a simple JavaScript-based quiz. Document in Notion how understanding basic CS principles can aid in future data-driven solutions for OPOs.
Quarter-End Reflection Essay:
Reflect on how foundational web development and basic CS knowledge can support the creation of tools that inform healthcare staff about referral patterns. Consider how understanding organ donation flows informs technical design choices.
Year 1, Quarter 2 (Mar 19 – Jun 18, 2025)
Focus: Programming Fundamentals, Algorithms, Initial Data Handling, Deeper Healthcare Data Insight
Objectives This Quarter:
Strengthen programming and algorithmic thinking. Dive into linear algebra and probability foundations for future ML work. Understand how healthcare data (EHR, claims) is structured and biased.
Action Items:
Algorithms & Data Structures:
Complete remaining CS50 weeks (4–7) to solidify programming fundamentals. Start reading Introduction to Algorithms (CLRS) Part I (Ch. 1–4) focusing on sorting/searching. Practice on LeetCode (10–20 Easy/Medium problems).
Mathematics Expansion:
Watch 3Blue1Brown linear algebra YouTube series (free, visually intuitive). Continue MIT OCW Discrete Math (logic, combinatorics) to strengthen problem-solving.
Healthcare Data & Bias:
Read 1–2 open-access papers on EHR bias (search arXiv or PMC). Summarize how data quality affects clinical decision-making and how this might translate to OPO referrals.
Retention & Reflection:
Monthly quizzes on sorting algorithms, linear algebra concepts, and EHR data issues. Update Anki decks with key algorithmic terms and healthcare data points.
Resources This Quarter:
Book: Concrete Mathematics (Graham, Knuth, Patashnik) Ch.1–2 for combinatorial and analytical thinking. Research Paper: A free-access paper on EHR bias (e.g., “Bias in Electronic Health Records” from arXiv). Online Lecture Series: MIT OCW Discrete Mathematics (introductory lectures) available free online.
Project Q2:
Project #2: Implement a command-line Python tool that loads a mock healthcare dataset (CSV), cleans it, and sorts it by chosen criteria. Document how this skill can later be applied to sorting OPO referral data to identify patterns.
Quarter-End Reflection Essay:
Reflect on how algorithmic efficiency and data cleaning could influence the reliability and interpretability of future OPO referral prediction models. Consider the role of data bias and how careful handling can improve outcomes.
Year 1, Quarter 3 (Jun 19 – Sep 18, 2025)
Focus: Data Science Foundations, Introductory Machine Learning, Healthcare Analytics, Time-Series Understanding
Objectives This Quarter:
Learn fundamental data science workflows: EDA, basic ML models, and evaluation metrics. Explore probability & statistics as a base for ML. Start examining time-series analyses relevant to varying healthcare referral volumes.
Action Items:
ML & Data Science Basics:
fast.ai Practical Deep Learning for Coders (Part 1, Lessons 1–2) focusing on simple ML concepts. Learn Pandas, NumPy, and Matplotlib via YouTube tutorials (Corey Schafer, SentDex channels).
Mathematics for ML:
Mathematics for Machine Learning (Deisenroth et al.): Read linear algebra & probability chapters. Reinforce probability via Khan Academy (advanced topics).
Healthcare Analytics & Time-Series:
Acquire a simple Kaggle healthcare dataset (e.g., diabetes readmission). Perform basic EDA. Read an open-access paper on healthcare time-series forecasting (e.g., “Predicting Patient Admissions” on arXiv) to understand techniques that may later apply to OPO referrals.
Retention & Reflection:
Monthly quizzes on regression concepts, probability distributions, and basic time-series terms. Update Anki decks with ML terminology and healthcare time-series concepts.
Resources This Quarter:
Book: Understanding Machine Learning: From Theory to Algorithms (Shalev-Shwartz & Ben-David), at least the introductory chapters if available free online.
Research Paper: A free healthcare analytics/time-series prediction paper from arXiv focusing on patient admissions.
Online Lecture Series: fast.ai free course lectures (Part 1) for practical ML approaches.
Project Q3:
Project #3: Perform EDA and train a simple regression model (e.g., logistic regression) on a healthcare dataset to predict a basic outcome. In Notion, connect how these approaches can be adapted to predict OPO referral patterns.
Quarter-End Reflection Essay:
Consider how data science tools and ML fundamentals will enable building a predictive model for referral volumes. How can time-series analysis help anticipate surges in donor referrals?
Year 1, Quarter 4 (Sep 19 – Dec 18, 2025)
Focus: Full-Stack Development, System Architecture, Complexity Considerations, Introduction to Emotional AI
Objectives This Quarter:
Learn to integrate front-end and back-end development to present healthcare data. Understand complexity theory and its impact on scaling solutions. Gain initial exposure to emotional AI and how empathy can play a role in healthcare technology.
Action Items:
Full-Stack & System Design:
The Odin Project Full-Stack JS Track (Node.js, Express) and React Official Tutorial. Implement a simple full-stack application with a backend API and a React front-end to visualize healthcare data.
Complexity & Advanced Algorithms:
MIT OCW Advanced Algorithms lectures (network flow, NP-completeness). Solve 10 LeetCode medium-level problems to tackle more complex data structures.
Emotional AI Introduction:
Watch Rosalind Picard’s lectures on affective computing (YouTube, MIT Media Lab). Skim empathetic communication guidelines in healthcare from open-access articles (e.g., in BMJ Open).
Retention & Reflection:
Monthly quizzes on complexity definitions, REST API concepts, and a few key affective computing terms. Update Anki decks accordingly.
Resources This Quarter:
Book: Designing Data-Intensive Applications by Martin Kleppmann (read freely available chapter summaries online). Research Paper: A short open-access paper on applying empathy in healthcare AI (search arXiv or BMJ Open). Online Lecture Series: MIT OCW Advanced Algorithms (selected free lectures).
Project Q4:
Project #4: Build a full-stack web dashboard that visualizes mock referral trends. Document architecture, complexity considerations, and note how an empathetic UI might aid OPO staff under stress.
Quarter-End Reflection Essay:
Reflect on how a user-friendly, empathically designed interface can facilitate better decision-making and could, in the future, integrate predictive modeling to inform OPO staffing needs.
Year 2, Quarter 1 (Dec 19, 2025 – Mar 18, 2026)
Focus: Emotional AI, Healthcare NLP, Advanced Probability
Objectives This Quarter:
Introduce NLP for sentiment and understanding clinical notes. Deepen probability knowledge for handling uncertainty in predictions. Integrate empathy and patient-centric understanding from a clinical standpoint.
Action Items:
NLP & Emotional AI:
Hugging Face NLP Course (free) for basic sentiment analysis. Analyze mock donor family feedback or clinical notes to understand emotional tone.
Mathematics & Probability:
MIT OCW Probability advanced lectures. Apply these concepts to understanding model confidence and uncertainty in healthcare predictions.
Empathy in Healthcare & Affective Computing:
Read key chapters/summaries from Being Mortal (Atul Gawande) to gain insights into patient-centered care. Revisit Picard’s lectures on affective computing to consider embedding empathy cues in data tools.
Retention & Reflection:
Monthly quizzes on NLP concepts, probability distributions, and empathy-related terms. Update Anki decks with NLP techniques and emotional AI vocab.
Resources This Quarter:
Book: Being Mortal (or detailed summaries online if full text unavailable for free) for empathy and patient care understanding. Research Paper: A ClinicalBERT or similar clinical NLP paper from arXiv focusing on processing clinical text. Online Lecture Series: Hugging Face NLP free course tutorials and videos.
Project Q1 (Year 2):
Project #5: Implement a sentiment analysis prototype on mock donor family notes. Document how understanding emotional states could help OPO staff better support families and anticipate referral dynamics.
Quarter-End Reflection Essay:
Reflect on how emotional AI and NLP tools can improve the quality of interactions in OPO settings, informing more compassionate and data-driven decisions.
Year 2, Quarter 2 (Mar 19 – Jun 18, 2026)
Focus: Advanced Algorithms, Probabilistic Modeling, Causal Inference for Healthcare
Objectives This Quarter:
Delve into advanced algorithms, complexity theory, and their implications for large-scale healthcare data. Learn basic causal inference techniques to understand cause-effect relationships in OPO referral patterns.
Action Items:
Advanced Algorithms & Probabilistic Models:
Further MIT OCW advanced algorithm lectures (focus on network flows, NP-completeness). Implement a simple Bayesian model (PyMC or similar) to handle uncertainty in healthcare predictions.
Causal Inference:
Read a causal inference primer (search free chapters online) and a healthcare causal inference paper from arXiv to see how identifying causal factors helps in stable predictions.
Retention & Reflection:
Monthly quizzes on causal inference terminology, Bayesian concepts, and complex algorithmic problem-solving. Update Anki decks with causal inference and probabilistic modeling terms.
Resources This Quarter:
Book: Causal Inference in Statistics: A Primer (Pearl et al.) - if not fully free, at least find free summaries or lecture notes online. Research Paper: A free causal inference in healthcare paper from arXiv. Online Lecture Series: Continue with advanced MIT OCW algorithm lectures, and look for free causal inference video lectures from academic conferences on YouTube.
Project Q2 (Year 2):
Project #6: Prototype a backend that processes time-series referral data and applies a simple probabilistic model. Sketch out how causal insights could refine predictions for OPO staffing needs.
Quarter-End Reflection Essay:
Reflect on how understanding cause-effect relationships leads to more reliable and ethically justifiable healthcare predictions.
Year 2, Quarter 3 (Jun 19 – Sep 18, 2026)
Focus: Deep Learning, Convex Optimization, Advanced Healthcare ML
Objectives This Quarter:
Develop deeper DL skills (neural networks, basic architectures). Understand optimization techniques that improve ML model performance. Apply advanced ML techniques to healthcare scenarios relevant to OPO referrals.
Action Items:
Deep Learning:
fast.ai or Andrew Ng’s Deep Learning Specialization (audit free) – focus on foundational neural network lessons. Implement a simple NN to predict a healthcare metric (e.g., hospital readmissions).
Mathematics & Optimization:
Explore free Stanford lectures on convex optimization (or equivalent YouTube playlists). Add advanced math terms and optimization strategies to your Anki deck.
Healthcare ML Context:
Read a DL healthcare paper (arXiv) on medical imaging or patient outcome prediction. Consider how advanced ML architectures (RNN, Transformers) might handle OPO referral time-series data.
Retention & Reflection:
Monthly quizzes on NN architectures, optimization algorithms, and their relevance to time-series healthcare data.
Resources This Quarter:
Book: Deep Learning (Goodfellow et al.) - read selected open-access chapters or summaries. Research Paper: A DL in healthcare paper from arXiv focusing on predicting patient outcomes or identifying risk factors. Online Lecture Series: Andrew Ng’s Deep Learning courses on Coursera (audit mode free lectures).
Project Q3 (Year 2):
Project #7: Build and train a small neural network model for a healthcare prediction task. Document how this technique could be adapted to forecast OPO referral volumes.
Quarter-End Reflection Essay:
Reflect on how DL’s capacity to find patterns in complex data can enhance the accuracy of OPO referral predictions, potentially improving resource allocation.
Year 2, Quarter 4 (Sep 19 – Dec 18, 2026)
Focus: Capstone Integration, OPO Referral Prediction Tool, Ethics & Deployment
Objectives This Quarter:
Integrate all learned skills: web dev, ML/DL, NLP, emotional AI, and causal reasoning into the final predictive tool for OPO referrals. Address ethical, regulatory, and practical deployment considerations.
Action Items:
Capstone Project Planning & Execution:
Combine datasets (synthetic or publicly available proxies) to simulate referral volumes. Implement a pipeline: data cleaning, time-series modeling, a chosen ML/DL model, NLP sentiment analysis, and a user-friendly dashboard.
Ethics & Regulation:
Read WHO AI in Healthcare guidelines (free PDF) and HIPAA summaries from government sites. Understand fairness and bias considerations and document mitigation strategies.
Retention & Reflection:
Monthly quizzes mixing all topics (algorithms, ML, DL, NLP, causal inference, healthcare ethics). Update final Anki decks to ensure you retain core concepts.
Resources This Quarter:
Book: Revisit key chapters of previously mentioned books (SICP, CLRS, Concrete Math, Goodfellow’s DL) or summaries to reinforce integrated knowledge. Research Paper: A paper on AI ethics in healthcare from an open-access journal (e.g., searching “ethical ML in healthcare” on arXiv or PubMed Central). Online Lecture Series: WHO or academic conference talks on AI ethics and healthcare deployment (many free on YouTube).
Final Project Q4 (Year 2) - Capstone:
Project #8: A predictive tool forecasting OPO referral volumes.
Include a simple sentiment analysis component to interpret staff notes or donor family feedback. Provide a dashboard for visualizing predictions, incorporate considerations for data privacy, fairness, and empathy in design. Record a short demo video (if possible) and write comprehensive documentation.
Final Reflection Essay:
Reflect on your entire journey, from a healthcare professional to an AI expert. Consider how empathy, cultural sensitivity, rigorous math, and computational thinking have combined to create a tool that can genuinely benefit OPOs and donor families. Identify how you’ll communicate your new skill set and credibility to future collaborators or employers.
End of Program
By December 18, 2026, you will have:
Mastered essential CS, math, ML, DL, and NLP skills. Gained a deep understanding of healthcare data structures, organ donation processes, and emotional AI. Produced a portfolio of progressively more complex projects, culminating in an OPO referral volume prediction tool. Cultivated habits of reflection, sustainable learning, empathy, and ethical awareness in healthcare AI contexts.