Diagnosing Illness with a Statistically Significant Computer Program
CSEF · 2003 Mathematics & Software
Overview
Objectives/Goals Several illnesses, ranging from the common cold to bronchitis, plague today's society; the increasing shortage of nurses further prevents the treatment of these illnesses. Because of this problem, the purpose of our science fair project is to create a user friendly computer program that effectively diagnoses the illness that the user suffers from based on symptoms that the user inputs into the program. Prescription treatments and home remedies are also provided. Our hypothesis is that our program will be accurate at least 60% of the time. Methods/Materials We compiled a list of illnesses with their symptoms and treatments. Next, we created an algorithm to write the program. After writing the program, we made four different surveys, for four different illnesses. They directed the subjects to place a check next to the symptoms and treatments that they experienced. We placed these surveys in a physician's office so that the physician's patients could take them and mail them back to us with the addressed envelope with postage that we provided. Results We received 22 surveys (of 110). To determine if our results validated our hypothesis, we conducted a T test. The null hypothesis was that the program was accurate 60% of the time. The alternative hypothesis was that the program was accurate more than 60% of the time. The test was significant to the .01 level; therefore, we rejected the null hypothesis and accepted the alternative hypothesis. There is strong evidence that the program is accurate more than 60% of the time. Conclusions/Discussion We presented our program and the strong evidence of accuracy to physicians. We asked them their opinions.
Summary statement
To counteract the current nursing shortage we have created a computer program that diagnoses a user's illness and provides treatments.
Help received
Dr. Hitesh Shah gave us advice about illnesses and provided his office as the location of our surveys.
Competition history
- CSEF 2003
Resources
Related projects
CSEF · 2015
False Positive and False Negative Paradox
CSEF · 2017
Using Machine Learning to Predict the Flu
ISEF · 2015
Respiratory Illness Diagnosis through Time and Spectral Based Sound Analysis
CSEF · 2019
Developing a Novel, Accurate, and Rapid Machine Learning Based Skin Disease Diagnosis Algorithm and Mobile Application
CSEF · 2014
Indium: Using Novel Machine Learning Algorithms to Develop a Nondisease-specific Personalized Medicine Engine
CSEF · 2019
Automated Diagnosis of Aortitis Using Machine Learning
ISEF · 2025
Assessing Medical Condition Severity Through AI Analysis of Textual Symptoms
CSEF · 2011
Plagiarism Analysis Program
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects