One of my data science projects looked at telehealth satisfaction and how it might relate to socioeconomic factors.

The goals were to:

• Clean and explore a survey dataset.
• Identify patterns in who reports positive or negative telehealth experiences.
• Think critically about what the numbers actually mean.

Interesting challenges

1. Feature engineering.
   Deciding how to encode income brackets, access to devices, and existing health conditions.

2. Bias and limitations.
   The dataset doesn’t represent everyone equally. Any conclusion has to be framed carefully.

3. Communicating results.
   It’s not enough to say “X is correlated with Y”. You have to translate that into something meaningful and responsible.

Why this matters to me

I like projects that sit at the intersection of tech and people.
Telehealth is a good example of where engineering decisions can improve access—or accidentally widen gaps.

Future posts might dig into specific models or visualizations from that project.