Can machine learning predict the remaining time for a lung cancer patient? The time is flying by let’s go.

I got an internship challenge offer to do, about survival analysis, I got rejected though but still, I’ve Learned so much from this experience you can find the challenge link here in case you want to participate.

In the beginning, I had no idea what survival analysis was so I needed some help:

Survival analysis

Survival analysis is the analysis of time-to-event data. Such data describe the length of time from a time origin to an endpoint of interest. For example, individuals might be followed from birth to the onset of some disease, or the survival time after the diagnosis of some disease might be studied. Survival analysis methods are usually used to analyze data collected prospectively in time, such as data from a prospective cohort study or data collected for a clinical trial.

The time origin must be specified such that individuals are as much as possible on an equal footing. For example, if the survival time of patients with a particular type of cancer is being studied, the time origin could be chosen to be the time point of diagnosis of that type of cancer. Equally importantly, the endpoint or event of interest should be appropriately specified, such that the times considered are well-defined. In the above example, this could be death due to cancer studied. Then the length of time from the time origin to the endpoint could be calculated.

One of the reasons why survival analysis requires ‘special’ techniques is the possibility of not observing the event of interest for some individuals. For example, individuals may drop out of a study, or they might have a different event, such as in the above example death due to an accident, which is not part of the endpoint of interest. Another possibility is that there might be a time point at which the study finishes and thus if any individuals have not had their event yet, their event time will not have been observed. These incomplete observations cannot be ignored, but need to be handled differently. This is called censoring. Another feature of survival data is that distributions are often skewed (asymmetric) and thus simple techniques based on the normal distribution cannot be directly used.

The objectives of survival analysis include the analysis of patterns of event times, the comparison of distributions of survival times in different groups of individuals, and examining whether and by how much some factors affect the risk of an event of interest.

#survival #cancer #life #time #love