False Negative: An Error That Must Be Avoided

There are lots of testing going on to test the Covid-19 virus. People feel so sure and confident after they are tested. But even after testing there is still a doubtful situation to be considered as tests aren’t 100 percent efficient. Such testing is not limited to any particular disease or health field. They are observed in various fields like in production, research et cetera.In making the decision there is generally four types of result. To understand let just observe the contingency table.

Contingency table

Wikipedia's definition:

In statistics, a contingency table (also referred to as cross tabulation or cross tab) is a type of table in a matrix format that displays the (multivariate) frequency distribution of the variables. It is often used to record and analyze the relation between two or more categorical variables.

We might get confuse with confusion matrix and contingency table.

confusion matrix

Wikipedia's definition:

In the field of artificial intelligence, a confusion matrix is a visualization tool typically used in supervised learning (in unsupervised learning it is typically called a matching matrix). Each column of the matrix represents the instances in a predicted class, while each row represents the instances in an actual class.

2*2 contingency table

The confusion matrix is a special type of Contingency table of 2*2 dimension (“actual” and “predicted”) and identical sets of “classes” in both dimensions.

So If we diagnose any disease we get the result either positive or negative. In the above table, we can see four segments.

• True Positive/True Negative: These two results are the actual result that we obtained in the test.
• False Positive /False Negative: These two wrong results obtained in the test. They are the errors.

False Positive

False-positive condition is a condition when a person is free of disease and is diagnosed positive for having the disease. This case can be a warning to people and can be used for precaution/warning for other people in case of the epidemic and this type of error isn’t hazardous. They are type-I errors.

False Negative

False Negative is an error which can be dangerous and will create more problem in coming time. False Negative in terms of diagnosing will create lots of confusion to the patient and in the case of a pandemic, this will be a real issue. They are type-II errors.

So false negative should be avoided as much as possible. In many cases, there might be many cases due to faulty machines or different parameters this may occur. It might be due to improper sample or improper steps in diagnosis.

Talking about the current situation, there might be false-negative and false-positive cases. False-positive cases are the cases when the patient is tested positive for Covid-19 even though they have a minor symptom which was similar to flu or Influenza. While False Negative is a very rare case . they are the cases when the sample is exchanged or contaminated. This is why people try multiple diagnoses in a different hospital in case of confusion.

For additional reading you may visit given link:

https://neptune.ai/blog/evaluation-metrics-binary-classification