|
|
|
|
@ -2,11 +2,59 @@
|
|
|
|
|
\graphicspath{{\subfix{Assets/img/}}}
|
|
|
|
|
|
|
|
|
|
\begin{document}
|
|
|
|
|
In September of 2019, the European Space Agency (ESA) released a tweet
|
|
|
|
|
explaining that they had performed an appendicotomy in space using
|
|
|
|
|
nothing more than radiation from the sun.
|
|
|
|
|
They are sad to announce that the patient died due to complications from
|
|
|
|
|
exposure to the cold vaccum of space.
|
|
|
|
|
%% Describe goal
|
|
|
|
|
% Estimate probability distribution of normalized durations and conclusion statuses.
|
|
|
|
|
% Explain why this answers questions well.
|
|
|
|
|
% How do I propose estimating that?
|
|
|
|
|
|
|
|
|
|
%%NOTATION
|
|
|
|
|
|
|
|
|
|
First, some notation:
|
|
|
|
|
\begin{itemize}
|
|
|
|
|
\item $t,i$ index trial and snapshot of the trial respectively.
|
|
|
|
|
\item $S_{it}$ : status (``Terminated'', ``Concluded'')
|
|
|
|
|
at the conclusion of the trial
|
|
|
|
|
\item $\tau_{it}$ : elapsed percentage of planned duration, i.e. the normalized elapsed duration.
|
|
|
|
|
\item $s_{it}$: current status variable(s) describing current trial status as one of:
|
|
|
|
|
``Recruiting'', ``Active, not recruiting'', or ``Suspended''
|
|
|
|
|
\item $X_{it}$: data describing the trial at the snapshot level
|
|
|
|
|
\begin{itemize}
|
|
|
|
|
\item number of sponsor changes so far
|
|
|
|
|
\item percentage currently enrolled of planned enrolled
|
|
|
|
|
\end{itemize}
|
|
|
|
|
\item $M_{t}$: data describing market conditions at the time of the snapshot.
|
|
|
|
|
\begin{itemize}
|
|
|
|
|
\item number of compounds approved for the same indication
|
|
|
|
|
\item total number of marketers approved for the same indication
|
|
|
|
|
\item number of marketers for this specific compound
|
|
|
|
|
\end{itemize}
|
|
|
|
|
\item $T_t$: Trial Level Data
|
|
|
|
|
\begin{itemize}
|
|
|
|
|
\item Indication or indication class
|
|
|
|
|
\item Sponsor Type
|
|
|
|
|
\end{itemize}
|
|
|
|
|
\end{itemize}
|
|
|
|
|
|
|
|
|
|
Other variables used when selecting trials to include as observations are:
|
|
|
|
|
\begin{itemize}
|
|
|
|
|
\item Trial Phase\footnote{
|
|
|
|
|
Conditioning on previous trials can be as simple as selecting only
|
|
|
|
|
phase 2 or phase 3 trials.
|
|
|
|
|
}.
|
|
|
|
|
\item Does the trial have a Data Monitoring Committee?
|
|
|
|
|
\item Are the compounds an FDA regulated drug?
|
|
|
|
|
\end{itemize}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
The goal is to estimate the probability distribution of conclusion status and duration conditional on the active snapshot status.
|
|
|
|
|
|
|
|
|
|
\begin{align}
|
|
|
|
|
\pr{ t, S | X,M,T} = \sum_{S\in\{\text{Terminated},\text{Concluded}\}} \pr{t|S,X,M,T} \pr{S|X,M,T}
|
|
|
|
|
\end{align}
|
|
|
|
|
Note how this has two component parts:
|
|
|
|
|
\begin{itemize}
|
|
|
|
|
\item The survival probability portion $\pr{t|S,X,M,T}$
|
|
|
|
|
\item The conclusion status portion $\pr{S|X,M,T}$
|
|
|
|
|
\end{itemize}
|
|
|
|
|
|
|
|
|
|
\end{document}
|
|
|
|
|
|
youainti
4 years ago