Difference between revisions of "User:Shawndouglas/sandbox/sublevel6"

From LIMSWiki
Jump to navigationJump to search
Line 1: Line 1:
This next section considers the difficulty of trying to categorize laboratories and provides a recommended framework for doing just that.
<div class="nonumtoc">__TOC__</div>
{{ombox
| type      = notice
| style    = width: 960px;
| text      = This is sublevel2 of my sandbox, where I play with features and test MediaWiki code. If you wish to leave a comment for me, please see [[User_talk:Shawndouglas|my discussion page]] instead.<p></p>
}}


<div align="center">-----Return to [[User:Shawndouglas/sandbox/sublevel4|the beginning]] of this guide-----</div>
==Sandbox begins below==
__TOC__
{{Infobox journal article
|name        =
|image        =
|alt          = <!-- Alternative text for images -->
|caption      =
|title_full  = A new numerical method for processing longitudinal data: Clinical applications
|journal      = ''Epidemiology Biostatistics and Public Health''
|authors      = Stura, Ilaria; Perracchione, Emma; Migliaretti, Giuseppe; Cavallo, Franco
|affiliations = Università di Torino, Università di Padova
|contact      = Email: Ilaria dot stura at unito dot it
|editors      =
|pub_year    = 2018
|vol_iss      = '''15'''(2)
|pages        = e12881
|doi          = [http://10.2427/12881 10.2427/12881]
|issn        = 2282-0930
|license      = [https://creativecommons.org/licenses/by-nc-nd/4.0/ Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International]
|website      = [https://ebph.it/index.php/ebph/article/view/12881 https://ebph.it/index.php/ebph/article/view/12881]
|download    = [https://ebph.it/article/view/12881/11630 https://ebph.it/article/view/12881/11630] (PDF)
}}
{{ombox
| type      = content
| style    = width: 500px;
| text      = This article should not be considered complete until this message box has been removed. This is a work in progress.
}}
==Abstract==
'''Background''': Processing longitudinal data is a computational issue that arises in many applications, such as in aircraft design, medicine, optimal control, and weather forecasting. Given some longitudinal data, i.e., scattered measurements, the aim consists in approximating the parameters involved in the dynamics of the considered process. For this problem, a large variety of well-known methods have already been developed.


==A framework for the laboratories in our lives==
'''Results''': Here, we propose an alternative approach to be used as an effective and accurate tool for the parameters fitting and prediction of individual trajectories from sparse longitudinal data. In particular, our mixed model, that uses radial basis functions (RBFs) combined with stochastic optimization algorithms (SOMs), is here presented and tested on clinical data. Further, we also carry out comparisons with other methods that are widely used in this framework.  
When thinking casually about laboratories, clinical diagnostic and chemistry labs likely spring to mind. But when the layman is pressed to name more laboratory types than that, the task becomes increasingly difficult. The next logical jump is to think about all the different types of scientific study that might have a laboratory associated with it: how about biology, physics, geology, and engineering? That list could get rather long, actually, and it may be a little like throwing darts blindfolded given the increasingly interdisciplinary nature of scientific research today.  


So how do we better visualize how and where laboratories intersect our lives? It helps to build a framework that all laboratories could find a home within.
'''Conclusion''': The main advantages of the proposed method are the flexibility with respect to the datasets, meaning that it is effective also for truly irregularly distributed data, and its ability to extract reliable [[information]] on the evolution of the dynamics.


Below (Fig. 1) is a diagrammatic expression of one method of organizing laboratories of the world. The idea behind the framework is that you could name a specific laboratory and be able to put it somewhere within the framework. For example:
'''Keywords''': statistical method, radial basis function; stochastic optimization algorithm, longitudinal data


* The U.S. Federal Bureau of Investigation's mobile forensics laboratory<ref name="StephensInside15">{{cite web |url=http://www.kctv5.com/story/28266161/inside-look-at-fbis-new-mobile-forensics-lab |title=Inside look at FBI's new mobile forensics lab |author=Stephens, B. |work=KCTV5 News |publisher=Gannaway Web Holdings, LLC |date=04 March 2015 |accessdate=29 March 2017}}</ref> would fall under Government > Public > Compliance and Legal > Wet (or Dry) > Mobile.  
==Introduction==
 
Longitudinal data are often the object of study in many fields, e.g., sociology, meteorology, and medicine. In medicine, repeated measurements are used to monitor patients’ behaviors and also to adjust therapies accordingly. However, many problems occur when these data are analyzed. Indeed, each time series could have a different number of observations and not be equally spaced. In addition, the sampling period could vary from patient to patient, and measurement errors and also missing data often occur. Thus, since in these cases common methods such as linear regression usually fail, the recent research is directed towards more robust statistical methods. For instance, longitudinal data are commonly analyzed using parametric models such as Bayesian ones<ref name="RaoPrediction87">{{cite journal |title=Prediction of Future Observations in Growth Curve Models |journal=Statistical Science |author=Rao, C.R. |volume=2 |issue=4 |pages=434–47 |year=1987 |doi=10.1214/ss/1177013119}}</ref>, as well as functional data analysis (FDA).<ref name="JiOptimal17">{{cite journal |title=Optimal designs for longitudinal and functional data |journal=Statistical Methodology Series B |author=Ji, H; Müller, H.-G. |volume=79 |issue=3 |pages=859-876 |year=2017 |doi=10.1111/rssb.12192}}</ref><ref name="RamsayFunctional05">{{cite book |title=Functional Data Analysis |author=Ramsay, J.; Silverman, B.W. |publisher=Springer-Verlag |pages=428 |year=2005 |isbn=9780387400808}}</ref> In both cases, many data are required in order to model the behavior of the studied variable(s). These methods, in fact, try to find an "average curve" using all the data, including truncated series and observations with missing information.
* An engineering design laboratory based within a for-profit car manufacturing company would fall under Private > Internal Customer > Research / Design > Dry > Fixed.  
 
* A chemistry laboratory housed in a secondary school in Germany would fall under Academic > Public > Teaching > Secondary > Wet > Fixed.
 
 
[[File:Laboratory types diagram.png|1400px]]
{{clear}}
{|
| STYLE="vertical-align:top;"|
{| border="0" cellpadding="5" cellspacing="0" width="1400px"
|-
  | style="background-color:white; padding-left:10px; padding-right:10px;"| <blockquote>'''Figure 1.''' A diagrammatic representation of laboratory types using both client type and function as the key organizational elements</blockquote>
|-
|}
|}
 
The original inspiration for this diagram came from Jain and Rao's attempt to diagram Indian diagnostic laboratories in 2015.<ref name="JainMedical15">{{cite journal |title=Medical diagnostic laboratories provisioning of services in India |journal=CHRISMED Journal of Health and Research |author=Jain, R.; Rao, B. |volume=2 |issue=1 |pages=19–31 |year=2015 |doi=10.4103/2348-3334.149340}}</ref> While their diagram focused entirely on the clinical sphere of laboratories, it was easy to envision expanding upon their work to express laboratories of all types. Additional inspiration came from KlingStubbins architecture textbook ''Sustainable Design of Research Laboratories: Planning, Design, and Operation''<ref name="KlingstubbinsSustainable10">{{cite book |url=https://books.google.com/books?id=yZQhTvvVD7sC&pg=PA18 |title=Sustainable Design of Research Laboratories: Planning, Design, and Operation |author=KlingStubbins |publisher=John Wiley & Sons |year=2010 |pages=17–18 |isbn=9780470915967 |accessdate=29 March 2017}}</ref>, which lists several methods for organizing types of laboratories; Daniel D. Watch's ''Building Type Basics for Research Laboratories''<ref name="WatchBuilding01">{{cite book |url=https://books.google.com/books?id=_EGpDgUNppIC&pg=PA37 |chapter=Chapter 2: Laboratory Types |title=Building Type Basics for Research Laboratories |author=Watch, D.D. |publisher=John Wiley & Sons |year=2001 |pages=37–99 |isbn=9780471217572 |accessdate=29 March 2017}}</ref>; and Walter Hain's ''Laboratories: A Briefing and Design Guide''.<ref name="HainLab03">{{cite book |url=https://books.google.com/books?id=HPB4AgAAQBAJ&pg=PA2 |title=Laboratories: A Briefing and Design Guide |author=Hain, W. |publisher=Taylor & Francis |year=2003 |pages=2–5 |isbn=9781135822941 |accessdate=29 March 2017}}</ref>
 
The benefit of this diagrammatic approach — with client type at its base — becomes more apparent when we start considering the other two methods we could use to categorize laboratories, as described by KlingStubbins ''et al.'': by science and by function. Organizing by science quickly becomes problematic, emphasizes KlingStubbins<ref name="KlingstubbinsSustainable10" />:
 
<blockquote>Gone are the days when the division was as simple as biology and chemistry. New science fields emerge rapidly now and the lines between the sciences are blurred. A list based on science types would include not just biology and chemistry, but biochemistry, biophysics, electronics, electrophysiology, genetics, metrology, nanotechnology, pharmacokinetics, pharmacology, physics, and so on.</blockquote>
 
As for function, we can look at what type of activity is primary to the lab. Is the lab designed to teach students, function as a base for research, provide quality control functions, calibrate equipment, act as a routine analytical station, or perform more than one of these tasks? Another benefit of looking at labs by function is it helps with our organization of labs within industry (discussed in the next section) by ''what they do''. For example, we don't have a "manufacturing lab"; rather, we have a laboratory in a manufacturing company — perhaps making cosmetics — that serves a particular function, whether its quality control or research and development (R&D). This line of thinking has utility, but upon closer inspection, we discover that we need to also look further up the chain at who's running it.
 
As such, we realize these functions can be integrated with client type to provide a more complete framework. Why? When we look at laboratories by science type — particularly when inspecting newer fields of science —  we realize 1. they are often interdisciplinary (e.g., molecular diagnostics integrating molecular biology with clinical chemistry) and 2. they can serve two different functions within the same science (e.g., a diagnostic cytopathology lab vs. a teaching cytopathology lab). Rather than build a massively complex chart of science types, with numerous intersections and tangled webs, it seems more straightforward to look at laboratories by client type and then function, following from the architectural viewpoints presented by KlingStubbins ''et al.'' With that framework firmly in place, we can better organize an examination of where labs can be found and what roles they function under.
 
However, this doesn't mean looking at laboratories by science is entirely fruitless. But rather than focus directly on the sciences, why not look at the industries employing laboratory science? While there is crossover between industries (e.g., the cosmetic and petrochemical industries both lean on various chemical sciences), we can extend from the previous diagram (or work in parallel with it) and paint a broader picture of just how prevalent laboratories are in our life.
 
In the next section, we look at the private, government, and academic labs in various industries (client type); provide real-life examples of labs and their specific tests; and discuss the various activities and sciences (functions) performed in them.


==References==
==References==
{{Reflist|colwidth=30em}}
{{Reflist|colwidth=30em}}
==Notes==
This presentation is faithful to the original, with only a few minor changes to presentation, spelling, and grammar. We also added PMCID and DOI when they were missing from the original reference. No other modifications were made in accordance with the "no derivatives" portion of the distribution license.


<!--Place all category tags here-->
<!--Place all category tags here-->
[[Category:LIMSwiki journal articles (added in 2018)‎]]
[[Category:LIMSwiki journal articles (all)‎]]
[[Category:LIMSwiki journal articles on public health informatics]]

Revision as of 23:48, 18 August 2018

This is sublevel2 of my sandbox, where I play with features and test MediaWiki code. If you wish to leave a comment for me, please see my discussion page instead.

Sandbox begins below

Full article title A new numerical method for processing longitudinal data: Clinical applications
Journal Epidemiology Biostatistics and Public Health
Author(s) Stura, Ilaria; Perracchione, Emma; Migliaretti, Giuseppe; Cavallo, Franco
Author affiliation(s) Università di Torino, Università di Padova
Primary contact Email: Ilaria dot stura at unito dot it
Year published 2018
Volume and issue 15(2)
Page(s) e12881
DOI 10.2427/12881
ISSN 2282-0930
Distribution license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Website https://ebph.it/index.php/ebph/article/view/12881
Download https://ebph.it/article/view/12881/11630 (PDF)
This article should not be considered complete until this message box has been removed. This is a work in progress.

Abstract

Background: Processing longitudinal data is a computational issue that arises in many applications, such as in aircraft design, medicine, optimal control, and weather forecasting. Given some longitudinal data, i.e., scattered measurements, the aim consists in approximating the parameters involved in the dynamics of the considered process. For this problem, a large variety of well-known methods have already been developed.

Results: Here, we propose an alternative approach to be used as an effective and accurate tool for the parameters fitting and prediction of individual trajectories from sparse longitudinal data. In particular, our mixed model, that uses radial basis functions (RBFs) combined with stochastic optimization algorithms (SOMs), is here presented and tested on clinical data. Further, we also carry out comparisons with other methods that are widely used in this framework.

Conclusion: The main advantages of the proposed method are the flexibility with respect to the datasets, meaning that it is effective also for truly irregularly distributed data, and its ability to extract reliable information on the evolution of the dynamics.

Keywords: statistical method, radial basis function; stochastic optimization algorithm, longitudinal data

Introduction

Longitudinal data are often the object of study in many fields, e.g., sociology, meteorology, and medicine. In medicine, repeated measurements are used to monitor patients’ behaviors and also to adjust therapies accordingly. However, many problems occur when these data are analyzed. Indeed, each time series could have a different number of observations and not be equally spaced. In addition, the sampling period could vary from patient to patient, and measurement errors and also missing data often occur. Thus, since in these cases common methods such as linear regression usually fail, the recent research is directed towards more robust statistical methods. For instance, longitudinal data are commonly analyzed using parametric models such as Bayesian ones[1], as well as functional data analysis (FDA).[2][3] In both cases, many data are required in order to model the behavior of the studied variable(s). These methods, in fact, try to find an "average curve" using all the data, including truncated series and observations with missing information.

References

  1. ↑ Rao, C.R. (1987). "Prediction of Future Observations in Growth Curve Models". Statistical Science 2 (4): 434–47. doi:10.1214/ss/1177013119. 
  2. ↑ Ji, H; Müller, H.-G. (2017). "Optimal designs for longitudinal and functional data". Statistical Methodology Series B 79 (3): 859-876. doi:10.1111/rssb.12192. 
  3. ↑ Ramsay, J.; Silverman, B.W. (2005). Functional Data Analysis. Springer-Verlag. pp. 428. ISBN 9780387400808. 

Notes

This presentation is faithful to the original, with only a few minor changes to presentation, spelling, and grammar. We also added PMCID and DOI when they were missing from the original reference. No other modifications were made in accordance with the "no derivatives" portion of the distribution license.

Retrieved from "https://www.limswiki.org/index.php?title=User:Shawndouglas/sandbox/sublevel6&oldid=33815"