top of page

Investigate No-Show Patients

Case Study

Problem Statement

Missed medical appointments are a persistent challenge for healthcare providers, leading to inefficient use of resources and delays in patient care. The No-Show Appointments. dataset, which records over 100,000 patient appointments from Brazil, was analyzed to identify factors influencing whether a patient attends or misses their scheduled appointment.


The objective was to uncover patterns behind “no-show” behavior and highlight demographic or behavioral variables that contribute to patient absenteeism through the following questions:

​

  1. Does the no-show behavior occur more in a particular gender?

  2. Does the no-show behavior occur more in a particular age-group?

  3. Does having scholarship affect no-show behavior?

  4. Does the no-show behavior occur more on a particular day?

  5. Does waiting period affect no-show behavior?

  6. Does receiving an SMS affect no-show behavior?

  7. Does number of handicaps in a patient affect no-show behavior?

  8. How do different medical conditions correlate with making appointments and not showing up?

Solution

The dataset was cleaned, transformed, and analyzed using Python (Pandas, NumPy, Matplotlib, Seaborn).


Key data-wrangling steps included handling invalid entries (such as negative ages), standardizing date formats, and deriving new features like waiting period, appointment day of the week, and age groups for deeper insights.

​

Exploratory analysis was conducted to examine the relationships between attendance behavior and variables such as:

  • Gender

  • Age group

  • Scholarship (financial aid) status

  • Waiting period between scheduling and appointment

  • SMS reminders

  • Presence of chronic medical conditions or disabilities

​

Visual exploration and group-level statistics were used to identify the strongest correlations with patient no-shows.

Conclusion

The analysis revealed several important behavioral patterns:

​

  • Age: Younger patients (below 20) and the very elderly (above 100) showed higher no-show rates, while middle-aged groups (50–80) were more consistent.

  • Financial Aid: Patients receiving scholarships were more likely to miss appointments, suggesting socioeconomic barriers.

  • Waiting Time: Longer waiting periods between scheduling and the appointment significantly increased the likelihood of no-shows.

  • SMS Reminders: Surprisingly, patients who received SMS reminders had slightly higher no-show rates—possibly indicating ineffective messaging or poor timing.

  • Chronic Conditions: Alcoholism showed the strongest link to missed appointments, while hypertension and diabetes were less influential.

​

These findings highlight the importance of reducing wait times, tailoring communication strategies, and targeting outreach efforts for specific patient groups to improve attendance rates.

bottom of page