Templates & Examples
Project Proposal Template
You can use the following Markdown structure to write your proposal.
Save it as proposal.md and send it to Prof. Martin Daumer (CC Pooja N. Annaiah) by the topic approval deadline.
📄 Click to view the full Markdown template
# CACoM Project Proposal
**Clinical Applications of Computational Medicine (CACoM)**
Technical University of Munich
---
## 🧩 Team Information
- **Project Title:**
_Concise and informative title summarizing the main idea._
- **Team Members:**
| Name | Email | Role (optional) |
| :---- | :----- | :--------------- |
| | | |
| | | |
---
## 🎯 Background & Motivation
Explain briefly **why this problem matters**.
What is its **clinical or physiological relevance**?
Why is it interesting or important to study now?
_Example prompts:_
- What gap or limitation are you addressing?
- How does it relate to computational medicine or health data analysis?
---
## ❓ Research Question / Hypothesis
State your main question or hypothesis clearly and precisely.
It should be **specific**, but still flexible enough to evolve as you learn more.
_Example:_
> Does **deceleration area** correlate with **fetal well-being at birth**, as measured by **arterial pH value**?
You can frame your question in various ways — for example:
- testing a hypothesis (_does X predict Y?_),
- developing a method (_can we measure Z more reliably?_),
- exploring an open question (_what patterns emerge in this dataset?_), etc.
---
## 💾 Data Description
Describe your data source(s):
- What type of data will you use (e.g., physiological signals, IMU recordings, audio, tabular)?
- Where does it come from (open dataset, collaborator, simulator, or **your own recordings**)?
- How will you **collect** it if needed (e.g., using an IMU, electronic stethoscope, or fetal heartbeat simulator with a Doppler probe)?
- Are there **privacy, consent, or ethical considerations**?
- Is access or hardware already secured?
:::note
Some projects involve **collecting small-scale experimental data**.
If so, briefly outline your setup (e.g., device type, recording duration, environment) and describe how you’ll ensure data quality and safety.
:::
---
## 🧮 Planned Methods / Approach
Outline your **planned analytical or computational approach**.
You don’t need every detail yet — describe the general strategy, algorithms, or workflows you intend to try.
Possible approaches include:
- **Computational / analytical:** signal processing, feature extraction, ML modeling, simulation, or numerical analysis.
- **Systematic review:** structured literature search, inclusion criteria, and synthesis of existing findings.
- **Survey study:** design of questionnaires, **recruitment and dissemination strategy**, data collection, and statistical evaluation of responses.
- **Engineering / prototyping:** design, testing, or validation of hardware or software components (e.g., sensor prototypes, analysis tools).
_Example elements:_
- Signal preprocessing or filtering steps
- Planned algorithms or model types
- Evaluation setup or comparison baseline
- Visualization or reporting methods
---
## 📊 Evaluation & Success Criteria
Define what **“success”** will mean for your project.
What results or insights will demonstrate that your approach worked?
Depending on your project type, evaluation may involve:
- **Analytical projects:** performance metrics (accuracy, correlation, RMSE, etc.), statistical significance, or reproducibility.
- **Experimental projects:** agreement with reference data, repeatability, robustness to noise, or hardware validation.
- **Systematic reviews:** clarity of inclusion criteria, reproducibility of search strategy, and synthesis quality.
- **Survey studies:** response rate, representativeness, and clarity of statistical analysis.
- **Engineering projects:** functionality, precision, and performance relative to defined specifications.
👉 These criteria may evolve later — that's normal and expected.
---
## 🧠 Expected Deliverables
List what you aim to produce by the end of the course:
- Poster and 1-minute video teaser
- Report or reproducibility package
- Code, scripts, or notebooks
- Dataset or derived results (if applicable)
---
## ⚖️ Feasibility & Risks
Reflect briefly on practical aspects:
- What are the **main risks or uncertainties** (e.g., data access, complexity)?
- Do you have **fallback plans** if something doesn’t work out?
- Is your timeline realistic for a one-semester project?
---
## 🗓️ Timeline (Optional)
_You may include a rough week-by-week plan or milestones._
| Week | Planned Milestone |
| :---- | :---------------- |
| 1–2 | Brainstorming, literature review |
| 3–4 | Data acquisition and setup |
| 5–8 | Method development and testing |
| 9–12 | Analysis, results, and presentation preparation |
---
:::tip
This proposal defines your **starting point and intent**, not a rigid contract.
Refinement of your methods, metrics, or hypotheses as your understanding deepens is **normal and encouraged**.
:::
---
**Submission:**
Send this document as **PDF or Markdown** via email to **Prof. Martin Daumer**, CC **Pooja N. Annaiah**, by the official topic approval date.