BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-19035
DTSTART;TZID=Europe/Berlin:20220825T170000
SEQUENCE:1660316019
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20220825T183000
URL:https://www.dresden-science-calendar.de/calendar/de/detail/19035
LOCATION:B CUBE\, Tatzberg 4101307 Dresden
SUMMARY:Haupt: EKFZ | Lecture  Why the combination of modeling and machine 
 learning could be the future direction in mathematical oncology
CLASS:PUBLIC
DESCRIPTION:Speaker: Saskia Haupt\nInstitute of Speaker: University of Heid
 elberg | Interdisciplinary Center for Scientific Computing\nTopics:\nMathe
 matik\, Informatik\n Location:\n  Name: B CUBE ()\n  Street: Tatzberg 41\n
   City: 01307 Dresden\n  Phone: +49 351 463 43000\n  Fax: +49 351 463 4032
 2\nDescription: In recent years\, oncology has become a quite interdiscipl
 inary field including experts from many medical disciplines but also mathe
 maticians\, computer scientists and bioinformaticians. Especially the fiel
 d of mathematical oncology has expanded successfully with the aim at devel
 oping mathematical models and approaches to simulate cancer development an
 d by this\, better understand the underlying biological processes and impr
 ove current clinical procedures. Mathematical models are built based on me
 dical expertise and the current understanding or hypotheses of cancer deve
 lopment making them explainable. However\, the validation with clinical da
 ta is often challenging.    Besides mathematical modeling\, artificial int
 elligence and machine learning are very prominent fields in data analysis 
 and pattern recognition of various omics data and histological images. Her
 e\, machine learning algorithms are trained to learn the underlying rules 
 of a system by using large amount of data. Although machine learning algor
 ithms are not fully understandable\, they often outperform mathematical mo
 dels in terms of accuracy.    Thus\, a combination of mathematical modelin
 g and machine learning while using the advantages of both fields seems ver
 y promising. In this talk\, we will elaborate on this possible future dire
 ction of mathematical oncology at the example of Lynch syndrome cancer dev
 elopment\, the most common inherited cancer predisposition syndrome. We sh
 ow our recent advances in modeling Lynch syndrome colorectal carcinogenesi
 s at different physical scales ranging from the DNA over the cell and cryp
 t to the population level. Coming from the modeling side\, we will point t
 o possibilities of adding machine learning to these models. We emphasize w
 hy this could be a very promising future research direction leading to exp
 lainable models of cancer development which are calibrated and validated b
 y biomedical and clinical data in a straightforward and efficient way.
DTSTAMP:20260628T074135Z
CREATED:20220812T145339Z
LAST-MODIFIED:20220812T145339Z
END:VEVENT
END:VCALENDAR