feat(proposal): add presentation

This commit is contained in:
Julian Lobbes 2023-05-02 03:57:10 +02:00
parent 100ce38ab0
commit 59b3eb857a
7 changed files with 166 additions and 13 deletions

112
figures/gantt.drawio Normal file
View File

@ -0,0 +1,112 @@
<mxfile host="Electron" modified="2023-05-01T22:16:34.541Z" agent="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/21.2.1 Chrome/112.0.5615.87 Electron/24.1.2 Safari/537.36" etag="1Wzcjv7OB8KUVon0POAM" version="21.2.1" type="device">
<diagram name="Page-1" id="fc2ac565-0d4e-3f0d-88b0-a54af1634ed7">
<mxGraphModel dx="1710" dy="991" grid="1" gridSize="10" guides="1" tooltips="1" connect="0" arrows="1" fold="1" page="1" pageScale="1.5" pageWidth="1169" pageHeight="827" background="none" math="0" shadow="0">
<root>
<mxCell id="0" style=";html=1;" />
<mxCell id="1" style=";html=1;" parent="0" />
<mxCell id="75" value="1. Design" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="140" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="80" value="2. Development and testing" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="160" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="85" value="3. Integration &amp;amp; deployment" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="180" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="90" value="4. Data collection" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="200" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="95" value="5. Analysis &amp;amp; interpretation" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="220" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="100" value="6. Written compilation" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="240" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="2" value="Task" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="440" y="120" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-289" value="7. Reviews &amp;amp; adjustments" style="align=left;strokeColor=#CCCCCC;html=1;fontStyle=2" parent="1" vertex="1">
<mxGeometry x="440" y="260" width="160" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-291" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="140" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="4" value="week 1" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-278" value="week 2" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="670" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-279" value="week 3" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="740" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-280" value="week 4" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="810" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-281" value="week 5" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="880" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-282" value="week 6" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="950" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-283" value="week 7" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="1020" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-284" value="week 8" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="1090" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-285" value="week 9" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="1160" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-286" value="week 10" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="1230" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-287" value="week 11" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="1300" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-288" value="week 12" style="strokeWidth=1;fontStyle=0;html=1;" parent="1" vertex="1">
<mxGeometry x="1370" y="120" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-292" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="160" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-293" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="180" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-294" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="200" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-295" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="220" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-296" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="240" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-297" value="" style="align=left;strokeColor=#CCCCCC;html=1;" parent="1" vertex="1">
<mxGeometry x="600" y="260" width="840" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-299" value="3 d" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="600" y="140" width="30" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-300" value="4 w" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="630" y="160" width="280" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-301" value="2d" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="910" y="180" width="20" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-302" value="2 w" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="930" y="200" width="140" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-303" value="2d" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="1070" y="220" width="20" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-304" value="7d" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="1090" y="240" width="70" height="20" as="geometry" />
</mxCell>
<mxCell id="67c90442a009f359-305" value="4w" style="whiteSpace=wrap;html=1;strokeWidth=2;fillColor=#6b8ebd;gradientColor=none;fontSize=14;align=center;strokeColor=#3391cc;" parent="1" vertex="1">
<mxGeometry x="1160" y="260" width="280" height="20" as="geometry" />
</mxCell>
</root>
</mxGraphModel>
</diagram>
</mxfile>

BIN
figures/gantt.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

View File

@ -2,7 +2,7 @@
\hspace{0pt}
\vfill
\begin{center}
{\huge\textbf{Title of my Thesis}} \\
{\Large\textbf{Early detection of patient deterioration at home using smart medical sensors}} \\
\vspace{1cm}
\includegraphics[width=0.5\textwidth]{figures/tubs-logo.png} \\
\vspace{1cm}

Binary file not shown.

After

Width:  |  Height:  |  Size: 82 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

BIN
proposal/presentation.odp Normal file

Binary file not shown.

View File

@ -49,7 +49,7 @@ Two commonly used clinical scores are the \textit{National Early Warning Score 2
Both are calculated by capturing various vital parameters from the patient at a specific point in time, followed by numerical aggregation of the
captured data according to the score being used\cite{subbe_validation_2001, noauthor_national_2017}.
For MEWS, each measured physiological parameter is assigned an individual score based on which range it is in.
The ranges for scoring each parameter are shown in table \ref{mews-table}.
The ranges for scoring each parameter are shown in Table \ref{mews-table}.
The individual scores are then added together to produce the final MEWS.
\begin{table}[!h]
@ -73,14 +73,14 @@ The individual scores are then added together to produce the final MEWS.
\caption{\label{mews-table}MEWS calculation ranges}
\end{table}
Traditionally, doctors and nursing staff perform collection and evaluation of the data manually, inputting data into an EWS-calculator by hand.
Traditionally, doctors and nursing staff perform collection and evaluation of the data manually, often inputting data into an EWS-calculator by hand.
Low frequency of scoring, miscalculations and practical integration are known setbacks of NEWS2 and other scores\cite{eisenkraft_developing_2023}.
Remote patient monitoring (RPM) can improve detection of deterioration\cite{shaik_remote_2023} by greatly reducing the
Remote patient monitoring (RPM) can improve deterioration detection\cite{shaik_remote_2023} by greatly reducing the
amount of human interaction required to take measurements and perform EWS calculations.
A number of studies have explored RPM combined with automated EWS calculation in hospitals\cite{filho_iot-based_2021, un_observational_2021, karvounis_hospital_2021, eisenkraft_developing_2023}.
With hospitals facing critical patient demand during the SARS-CoV-2 pandemic, interest in exploring remote patient monitoring options surged,
and NEWS2 emerged as an effective tool for predicting severe infection outcomes\cite{gidari_predictive_2020, otoom_iot-based_2020, filho_iot-based_2021, carr_evaluation_2021},
A number of studies have explored RPM combined with automated EWS calculation in hospitals\cite{eisenkraft_developing_2023, filho_iot-based_2021, un_observational_2021, karvounis_hospital_2021}.
With hospitals facing overwhelming patient load during the SARS-CoV-2 pandemic, interest in exploring remote patient monitoring options surged,
and NEWS2 emerged as an effective tool for predicting severe infection outcomes\cite{filho_iot-based_2021, gidari_predictive_2020, otoom_iot-based_2020, carr_evaluation_2021}
while reducing person-to-person contact during patient monitoring.
Since then, a variety of wearable medical sensors capable of continuously recording vital parameters have been developed and are
commercially available\cite{noauthor_visi_nodate, noauthor_equivital_nodate, noauthor_vitls_nodate, noauthor_caretaker_nodate, noauthor_medtronic_nodate}.
@ -96,7 +96,7 @@ Furthermore, these systems are cumbersome for patients, as they involve connecti
and cables, restricting patient mobility to the bed area, and physically tying the monitoring equipment
to a single location.
In contrast, battery-powered, wireless vitals monitoring devices, such as wearable arm- or wristbands, can incorporate multiple biosensors in a single device in a
much smaller form-factor, and allow for a much higher degree of patient mobility, rapid deployment and scalability\cite{un_observational_2021}.
smaller form-factor, and allow for a much higher degree of patient mobility, rapid deployment and scalability\cite{un_observational_2021}.
Therefore, utilizing such devices for RPM is a suitable approach.
While the application of EWS in ambulant care facilities and hospitals has been thoroughly investigated, very little research has been done to
@ -133,7 +133,7 @@ The system will consist of a network of smart medical sensors and a centralized
Patients and, potentially, medical staff can interact with the application to visualize and utilize captured data.
In addition to monitoring individual physiological parameters for abnormalities, the application will calculate the patient's current
MEWS, and send alerts when an increased risk of deterioration is detected.
A visualization depicting the main flow of data in the system is shown in figure \ref{system-components-macro}.
A visualization depicting the main flow of data in the system is shown in Figure \ref{system-components-macro}.
\begin{center}
\begin{figure}[h]
\includegraphics[width=\textwidth]{../figures/components-macro.png}
@ -160,7 +160,7 @@ The following vital signs will be captured and processed by the application:
the user to answer a simple question coherently to determine whether they are alert or not may be a suitable option.
}
\end{itemize}
The devices listed in table \ref{device-table} will be used to measure the patient's vital signs, while
The devices listed in Table \ref{device-table} will be used to measure the patient's vital signs, while
the web application and its alert system prompts the patient periodically to take new measurements.
\begin{table}[!h]
\noindent\adjustbox{max width=\textwidth}{
@ -183,14 +183,55 @@ the web application and its alert system prompts the patient periodically to tak
Following the technical implementation of the described system, its day-to-day usability and effectiveness will be evaluated in
a case study.
% TODO set timescale
A test subject, representing a patient recently dismissed from an accident and emergency hospital department (A\&E) will be using
the system for a week both from home and while away from home.
Over the course of two weeks, a test subject, representing a patient recently dismissed from an accident and emergency hospital department
(A\&E) will be using the system both at home and while out and about.
While awake, the patient will be prompted by the system via smartphone notifications to take new measurements every two hours.
The captured data and resulting MEWS records will be periodically reviewed by another person representing medical staff during
this time.
Overall, the proposed research is aimed at answering the following scientific inquiries:
\begin{enumerate}
\item Can smart medical sensors be used effectively to determine MEWS remotely for patients discharged from A\&E, hospital wards and
ambulant care?
\item Can RPM be used to potentially reduce the frequency of necessary follow-up visits for patients at risk?
\end{enumerate}
\newpage
\section{Tasks}
The following milestones are defined for the research project:
\begin{enumerate}
\item Application design
\begin{itemize}
\item Detailed software architecture design, data model design
\end{itemize}
\item Application development and unit testing
\begin{itemize}
\item Database, API, authentication
\item MEWS algorithm, alerts
\item User interface
\end{itemize}
\item Application integration and deployment
\begin{itemize}
\item SSL certificate installation, deployment to public webserver
\end{itemize}
\item Case study data collection
\item Case study data analysis and interpretation
\item Written compilation of findings
\item Reviews and adjustments
\end{enumerate}
The total available time for the project is 12 weeks.
A timeline for each defined milestone is displayed in Figure \ref{gantt}.
\begin{center}
\begin{figure}[h]
\includegraphics[width=\textwidth]{../figures/gantt.png}
\caption{\label{gantt}Project Timeline}
\end{figure}
\end{center}
\newpage
\printbibliography