"Help in Text Mining"
phahn
New Altair Community Member
Question from a beginner in data mining.I extracted data from PUBMED, looking like the two examples at the end
I want to read the entire file, no problem. Then I want to extract some parts ( AB,AU,TI, EDAT) building a data table for further analysis. I tried to use cut document, but don't know how to handle it.
After that i want to analyse the text for pattern over time, how does the discussed items change.
Any help how I preprocess the document building a CSV table each line containing the elements( AB,AU,TI, EDAT) of one publication ?
cut document ? or other tool ?
Thanks for any hints
Peter
Examples
PMID- 23027338
OWN - NLM
STAT- In-Data-Review
DA - 20121002
IS - 1439-3980 (Electronic)
IS - 0722-1819 (Linking)
VI - 44
IP - 5
DP - 2012 Oct
TI - [Artificial synostosis for traumatic metacarpal defect: a case report].
PG - 314-6
LID - 10.1055/s-0032-1323778 [doi]
AB - Reconstruction of traumatic metacarpal defects is still challenging because of
the key function of the architecture of the metacarpus for the function of the
entire hand. Especially the exact restoration of the rotation for a parallel
finger movement plays an important role. There are less information on this topic
in the literature. We present a 28-year old patient with a traumatic almost
complete defect of the fourth metacarpal. Reconstruction of the metacarpal arch
was achieved with an artificial synostosis between the intact head of the 4th
metacarpal and the 3rd metacarpal.
CI - (c) Georg Thieme Verlag KG Stuttgart . New York.
AD - Klinik fur Unfall-, Hand-, Plastische und Wiederherstellungschirurgie,
Universitatsklinikum, Wurzburg.
FAU - Ziegler, D
AU - Ziegler D
FAU - Meffert, R H
AU - Meffert RH
LA - ger
PT - English Abstract
PT - Journal Article
TT - Artifizielle Synostose zur Rekonstruktion bei traumatischem Metakarpaledefekt:
Fallbericht.
DEP - 20121001
PL - Germany
TA - Handchir Mikrochir Plast Chir
JT - Handchirurgie, Mikrochirurgie, plastische Chirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Handchirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Mikrochirurgie der Peripheren Nerven und Gefasse : Organ
der Vereinigung der Deutschen Plastischen Chirurgen
JID - 8302815
SB - IM
EDAT- 2012/10/03 06:00
MHDA- 2012/10/03 06:00
CRDT- 2012/10/03 06:00
PHST- 2012/10/01 [epublish]
AID - 10.1055/s-0032-1323778 [doi]
PST - ppublish
SO - Handchir Mikrochir Plast Chir. 2012 Oct;44(5):314-6. doi: 10.1055/s-0032-1323778.
Epub 2012 Oct 1.
PMID- 23027337
OWN - NLM
STAT- In-Data-Review
DA - 20121002
IS - 1439-3980 (Electronic)
IS - 0722-1819 (Linking)
VI - 44
IP - 5
DP - 2012 Oct
TI - [Quality Rating of MRI Regarding TFCC Lesions in the Clinical Practice].
PG - 310-3
LID - 10.1055/s-0032-1323799 [doi]
AB - MRI diagnostic is used for wrist pain diagnostic frequently. Clinical studies in
specialized centers show high sensitivity and specificity concerning TFCC
lesions. The aim of this study is a comparison of MRI and arthroscopy regarding
TFCC lesions not in a specialized but in a common medical environment.We
retrospectively recorded all patients between January 2004 and April 2012 who
went through a wrist arthroscopy and had a preoperative MRI. 401 patients were
identified, 218 males and 183 females. The average age was 42.4 (12-84) years. 88
examiners of radiological practices in the region of our hospital reported the
MRI results used for this research.In 334 cases TFCC lesions could be identified
during arthroscopy. MRI showed an average sensitivity of 69% and a specificity of
60%. A Palmer classification was reported through MRI in 58 cases. Most
frequently, the MRI examiners reported a Palmer 1b lesion. That result could only
be verified by arthroscopy in 11 cases.Although MRI has an acceptable degree of
diagnostic test accuracy in controlled clinical studies, we do not recommend the
general use of MRI in diagnosis of ulnocarpal wrist pain.
CI - (c) Georg Thieme Verlag KG Stuttgart . New York.
AD - Handchirurgie, Vulpius Klinik, Bad Rappenau.
FAU - Hahn, P
AU - Hahn P
FAU - Hausler, A
AU - Hausler A
FAU - Bruckner, T
AU - Bruckner T
FAU - Unglaub, F
AU - Unglaub F
LA - ger
PT - English Abstract
PT - Journal Article
TT - Wertigkeit der MRT hinsichtlich TFCC-Lasionen ausserhalb klinischer Studien.
DEP - 20121001
PL - Germany
TA - Handchir Mikrochir Plast Chir
JT - Handchirurgie, Mikrochirurgie, plastische Chirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Handchirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Mikrochirurgie der Peripheren Nerven und Gefasse : Organ
der Vereinigung der Deutschen Plastischen Chirurgen
JID - 8302815
SB - IM
EDAT- 2012/10/03 06:00
MHDA- 2012/10/03 06:00
CRDT- 2012/10/03 06:00
PHST- 2012/10/01 [epublish]
AID - 10.1055/s-0032-1323799 [doi]
PST - ppublish
SO - Handchir Mikrochir Plast Chir. 2012 Oct;44(5):310-3. doi: 10.1055/s-0032-1323799.
Epub 2012 Oct 1.
I want to read the entire file, no problem. Then I want to extract some parts ( AB,AU,TI, EDAT) building a data table for further analysis. I tried to use cut document, but don't know how to handle it.
After that i want to analyse the text for pattern over time, how does the discussed items change.
Any help how I preprocess the document building a CSV table each line containing the elements( AB,AU,TI, EDAT) of one publication ?
cut document ? or other tool ?
Thanks for any hints
Peter
Examples
PMID- 23027338
OWN - NLM
STAT- In-Data-Review
DA - 20121002
IS - 1439-3980 (Electronic)
IS - 0722-1819 (Linking)
VI - 44
IP - 5
DP - 2012 Oct
TI - [Artificial synostosis for traumatic metacarpal defect: a case report].
PG - 314-6
LID - 10.1055/s-0032-1323778 [doi]
AB - Reconstruction of traumatic metacarpal defects is still challenging because of
the key function of the architecture of the metacarpus for the function of the
entire hand. Especially the exact restoration of the rotation for a parallel
finger movement plays an important role. There are less information on this topic
in the literature. We present a 28-year old patient with a traumatic almost
complete defect of the fourth metacarpal. Reconstruction of the metacarpal arch
was achieved with an artificial synostosis between the intact head of the 4th
metacarpal and the 3rd metacarpal.
CI - (c) Georg Thieme Verlag KG Stuttgart . New York.
AD - Klinik fur Unfall-, Hand-, Plastische und Wiederherstellungschirurgie,
Universitatsklinikum, Wurzburg.
FAU - Ziegler, D
AU - Ziegler D
FAU - Meffert, R H
AU - Meffert RH
LA - ger
PT - English Abstract
PT - Journal Article
TT - Artifizielle Synostose zur Rekonstruktion bei traumatischem Metakarpaledefekt:
Fallbericht.
DEP - 20121001
PL - Germany
TA - Handchir Mikrochir Plast Chir
JT - Handchirurgie, Mikrochirurgie, plastische Chirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Handchirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Mikrochirurgie der Peripheren Nerven und Gefasse : Organ
der Vereinigung der Deutschen Plastischen Chirurgen
JID - 8302815
SB - IM
EDAT- 2012/10/03 06:00
MHDA- 2012/10/03 06:00
CRDT- 2012/10/03 06:00
PHST- 2012/10/01 [epublish]
AID - 10.1055/s-0032-1323778 [doi]
PST - ppublish
SO - Handchir Mikrochir Plast Chir. 2012 Oct;44(5):314-6. doi: 10.1055/s-0032-1323778.
Epub 2012 Oct 1.
PMID- 23027337
OWN - NLM
STAT- In-Data-Review
DA - 20121002
IS - 1439-3980 (Electronic)
IS - 0722-1819 (Linking)
VI - 44
IP - 5
DP - 2012 Oct
TI - [Quality Rating of MRI Regarding TFCC Lesions in the Clinical Practice].
PG - 310-3
LID - 10.1055/s-0032-1323799 [doi]
AB - MRI diagnostic is used for wrist pain diagnostic frequently. Clinical studies in
specialized centers show high sensitivity and specificity concerning TFCC
lesions. The aim of this study is a comparison of MRI and arthroscopy regarding
TFCC lesions not in a specialized but in a common medical environment.We
retrospectively recorded all patients between January 2004 and April 2012 who
went through a wrist arthroscopy and had a preoperative MRI. 401 patients were
identified, 218 males and 183 females. The average age was 42.4 (12-84) years. 88
examiners of radiological practices in the region of our hospital reported the
MRI results used for this research.In 334 cases TFCC lesions could be identified
during arthroscopy. MRI showed an average sensitivity of 69% and a specificity of
60%. A Palmer classification was reported through MRI in 58 cases. Most
frequently, the MRI examiners reported a Palmer 1b lesion. That result could only
be verified by arthroscopy in 11 cases.Although MRI has an acceptable degree of
diagnostic test accuracy in controlled clinical studies, we do not recommend the
general use of MRI in diagnosis of ulnocarpal wrist pain.
CI - (c) Georg Thieme Verlag KG Stuttgart . New York.
AD - Handchirurgie, Vulpius Klinik, Bad Rappenau.
FAU - Hahn, P
AU - Hahn P
FAU - Hausler, A
AU - Hausler A
FAU - Bruckner, T
AU - Bruckner T
FAU - Unglaub, F
AU - Unglaub F
LA - ger
PT - English Abstract
PT - Journal Article
TT - Wertigkeit der MRT hinsichtlich TFCC-Lasionen ausserhalb klinischer Studien.
DEP - 20121001
PL - Germany
TA - Handchir Mikrochir Plast Chir
JT - Handchirurgie, Mikrochirurgie, plastische Chirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Handchirurgie : Organ der Deutschsprachigen
Arbeitsgemeinschaft fur Mikrochirurgie der Peripheren Nerven und Gefasse : Organ
der Vereinigung der Deutschen Plastischen Chirurgen
JID - 8302815
SB - IM
EDAT- 2012/10/03 06:00
MHDA- 2012/10/03 06:00
CRDT- 2012/10/03 06:00
PHST- 2012/10/01 [epublish]
AID - 10.1055/s-0032-1323799 [doi]
PST - ppublish
SO - Handchir Mikrochir Plast Chir. 2012 Oct;44(5):310-3. doi: 10.1055/s-0032-1323799.
Epub 2012 Oct 1.
Tagged:
0