From 9d5a726494aa598dd793a627ca0d8d5dc860db54 Mon Sep 17 00:00:00 2001 From: youainti Date: Tue, 28 Jun 2022 12:42:39 -0700 Subject: [PATCH] added feature to extract start_date. deleted unused files and modified others for ease of use. --- Parser/NCT01303796.html | 3266 +++++++++++++++++++++------------- Parser/extraction-lib.py | 120 +- Parser/prototype_history.sql | 6 +- Parser/textprocessing.py | 184 -- 4 files changed, 2130 insertions(+), 1446 deletions(-) delete mode 100644 Parser/textprocessing.py diff --git a/Parser/NCT01303796.html b/Parser/NCT01303796.html index 32308ad..dc1fec8 100644 --- a/Parser/NCT01303796.html +++ b/Parser/NCT01303796.html @@ -1,1244 +1,2028 @@ + -History of Changes for Study: NCT01303796 - - - - - - - - -
ClinicalTrials.gov -
-
-
-
History of Changes for Study: NCT01303796
-
A Study of Oral Sapacitabine in Elderly Patients With Newly Diagnosed Acute Myeloid Leukemia (SEAMLESS)
-
Latest version (submitted October 28, 2018) on ClinicalTrials.gov
-
-
-
-
-
    -
  • A study version is represented by a row in the table.
    • -
  • Select two study versions to compare. One each from columns A and B.
    • -
  • Choose either the "Merged" or "Side-by-Side" comparison format to specify how the two study versions are to be displayed. The Side-by-Side format only applies to the Protocol section of the study.
    • -
  • Click "Compare" to do the comparison and show the differences.
    • -
  • Select a version's Submitted Date link to see a rendering of the study for that version.
    • -
  • The yellow A/B choices in the table indicate the study versions currently compared below. A yellow table row indicates the study version currently being viewed.
    • -
  • Hover over the "Recruitment Status" to see how the study's recruitment status changed.
    • -
  • Study edits or deletions are displayed in red.
    • -
  • Study additions are displayed in green.
    • -
-
-
-
-
Study Record Versions - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
VersionABSubmitted DateChanges
1February 24, 2011 -None (earliest Version on record)
2March 23, 2011 -Contacts/Locations and Study Status
3April 11, 2011 -Contacts/Locations and Study Status
4November 7, 2011 -Sponsor/Collaborators, Study Status, Contacts/Locations and Oversight
5May 2, 2012 -Study Status, Outcome Measures, Arms and Interventions, Study Description, Contacts/Locations and Study Design
6May 3, 2012 -Contacts/Locations and Study Status
7May 4, 2012 -Contacts/Locations and Study Status
8May 7, 2012 -Contacts/Locations and Study Status
9May 14, 2012 -Contacts/Locations and Study Status
10July 11, 2012 -Contacts/Locations and Study Status
11September 25, 2012 -Study Status and Contacts/Locations
12December 14, 2012 -Contacts/Locations and Study Status
13November 14, 2013 -Contacts/Locations and Study Status
14February 10, 2014 -Contacts/Locations and Study Status
15March 25, 2014 -Contacts/Locations and Study Status
16September 8, 2014 -Contacts/Locations and Study Status
17April 13, 2015 -Recruitment Status, Study Status and Contacts/Locations
18August 17, 2015 -Contacts/Locations and Study Status
19October 18, 2018 -Recruitment Status, Study Status, Arms and Interventions, Outcome Measures, Contacts/Locations, Study Design, Study Description, Oversight, IPDSharing, References and Eligibility
20October 28, 2018 -Arms and Interventions and Study Status
Show
Results Submission Events
-
- -
-Comparison Format: -
    -
    • -
    • -
-
-
-
-
-
-
-
-
-
Scroll up to access the controls
-
-
-Changes (Merged) for Study: NCT01303796
-February 24, 2011 (v1) -- October 28, 2018 (v20)

Changes in: Study Status, Sponsor/Collaborators, Oversight, Study Description, Study Design, Arms and Interventions, Outcome Measures, Eligibility, Contacts/Locations, IPDSharing, References -
- -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-
- Open or close this module -Study Identification -
- - - - - - - - - - - - - - - - - - - -
Unique Protocol ID:CYC682-12
Brief Title:A Study of Oral Sapacitabine in Elderly Patients With Newly Diagnosed Acute Myeloid Leukemia (SEAMLESS)
Official Title:A Phase III Randomized Study of Oral Sapacitabine in Elderly Patients With Newly Diagnosed Acute Myeloid Leukemia
Secondary IDs:
-
-
-
-
-
-
- Open or close this module -Study Status -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Record Verification:February 2011 October 2018
Overall Status:Recruiting Completed
Study Start:January 2011 October 1, 2011
Primary Completion:September 2013 [Anticipated] December 15, 2016 [Actual]
Study Completion:March 2014 [Anticipated] July 31, 2017 [Actual]
First Submitted:February 21, 2011
First Submitted that
Met QC Criteria:		February 24, 2011
First Posted:February 25, 2011 [Estimate]
Last Update Submitted that
Met QC Criteria:		February 24, 2011 October 28, 2018
Last Update Posted:February 25, 2011 [Estimate] October 31, 2018 [Actual]
-
-
-
-
-
-
- Open or close this module -Sponsor/Collaborators -
- - - - - - - - - - - - - - - -
Sponsor:Cyclacel Pharmaceuticals, Inc.
Responsible Party: Sponsor
Collaborators:
-
-
-
-
-
-
- Open or close this module -Oversight -
- - - - - - - - - - - - - - - -
U.S. FDA-regulated Drug: Yes
U.S. FDA-regulated Device: No
Data Monitoring: Yes
-
-
-
-
-
-
- Open or close this module -Study Description -
- - - - - - - - - - - - - -
Brief Summary:This Phase 3 study assesses three two drug regimens as the initial treatment of patients who are at least 70 years of age and have newly diagnosed acute myeloid leukemia (AML) for whom the doctor does not recommend the use of standard intensive treatment or the patient has decided not to receive standard intensive treatment after being fully informed about its benefits and risks by his/her doctor. The three two drug regimens are sapacitabine administered in alternating cycles with decitabine, sapacitabine alone or decitabine or decitabine alone. The purpose of the study is to learn which drug regimen is more likely to keep AML in check as long as possible.
Detailed Description:This is a multicenter, randomized, Phase 3 study ("SEAMLESS") comparing three two drug regimens (arms) as the front-line treatment of elderly patients aged 70 years or older with newly diagnosed acute myeloid leukemia (AML) who are not candidates for intensive induction chemotherapy. In Arm A, sapacitabine is administered in alternating cycles with decitabine, in Arm B sapacitabine is administered alone and in Arm C decitabine is administered alone. The primary efficacy endpoint is overall survival. The study is designed to demonstrate an improvement in overall survival of either of two pairwise comparisons: (1) Arm A versus Arm C or (2) Arm B versus Arm C.
-
-
-
-
-
-
- Open or close this module -Conditions -
- - - - - - - - - - - - - -
Conditions:Acute Myeloid Leukemia
Keywords:AML
-
-
-
-
-
-
- Open or close this module -Study Design -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Study Type:Interventional
Primary Purpose:Treatment
Study Phase:Phase 3
Interventional Study Model:Parallel Assignment
Number of Arms:3 2
Masking:None (Open Label)
Allocation:Randomized
Enrollment:470 [Anticipated] 482 [Actual]
-
-
-
-
-
-
- Open or close this module -Arms and Interventions -
- - - - - - -
- - - - - - - - - - - - - - -
ArmsAssigned Interventions
Experimental: Arm A Experimental: Sapacitabine-decitabine alternating
Sapacitabine and decitabine Arm A sapacitabine administered in alternating cycles with decitabine
Drug: Sapacitabine and decitabine Drug: Sapacitabine
Sapacitabine administered in alternating cycles with decitabine oral sapacitabine capsules
Drug: Decitabine
decitabine intravenous - -
Active Comparator: Arm B
Sapacitabine - -
Drug: Sapacitabine
Sapacitabine alone - -
Active Comparator: Arm C Decitabine
Arm C Decitabine
Drug: Decitabine
Decitabine alone decitabine intravenous
-
-
-
-
-
-
-
- Open or close this module -Outcome Measures -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Primary Outcome Measures:
1.Overall survival
[ Time Frame: up to 39 43 months ]

OS - -
Secondary Outcome Measures:
1.Complete remission with duration
[ Time Frame: Up up to 39 43 months ]

CR with duration - -
2.Complete remission with incomplete platelet count recovery and duration
[ Time Frame: up to 39 43 months ]

CRp with duration - -
3.Partial remission with duration
[ Time Frame: up to 39 43 months ]

PR with duration - -
4.Hematological improvement with duration
[ Time Frame: up to 39 43 months ]

HI with duration - -
5.Stable disease with duration
[ Time Frame: up to 39 43 months ]

SD with duration - -
6.Number of units of blood product transfused
[ Time Frame: up to 39 43 months ]

7.Hospitalized days
[ Time Frame: up to 39 43 months ]

8.1-year survival
[ Time Frame: up to 39 43 months ]

In % - -
-
-
-
-
-
-
- Open or close this module -Eligibility -
- - - - - - - - - - - - - - - - - - - - - - - - - - -
Minimum Age:70 Years
Maximum Age:
Sex:All
Gender Based:
Accepts Healthy Volunteers:No
Criteria:

Inclusion Criteria:

    -
  • Newly diagnosed AML based on WHO (World Health Organization) classification
  • Age 70 years or older for whom the treatment of choice is low-intensity therapy by investigator assessment or who has refused intensive induction therapy recommended by investigator
  • ECOG (Eastern Cooperative Oncology Group) performance status 0-2
  • Adequate renal function
  • Adequate liver function
  • Able to swallow capsules
  • Agree to practice effective contraception
  • Ability to understand and willingness to sign the informed consent form
-

Exclusion Criteria:

    -
  • AML is of the sub-type of acute promyelocytic leukemia or extramedullary myeloid tumor without bone marrow involvement
  • Having received any systemic anti-cancer therapy for AML or received treatment with hypomethylating agents or cytotoxic chemotherapy for the preceding MDS myelodysplastic syndrome (MDS) or myeloproliferative disease (MPD)
  • Known or suspected central nervous system (CNS) involvement by leukemia
  • Uncontrolled intercurrent illness
  • Known hypersensitivity to decitabine
  • Known to be HIV-positive
-
-
-
-
-
-
-
- Open or close this module -Contacts/Locations -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Central Contact Person:Judy H Chiao, MD
Telephone: 908-517-7330
Email: jchiao@cyclacel.com
Study Officials: Hagop M Kantarjian, M.D.
Study Chair
M.D. Anderson Cancer Center
Locations: United States, Alabama
University of Alabama Comprehensive Cancer Center
Birmingham, Alabama, United States, 35294
United States, California
Scripps Cancer Center
La Jolla, California, United States, 92037
UCLA Ronald Reagan Medical Center
Los Angeles, California, United States, 90095
United States, Connecticut
Norwalk Hospital
Norwalk, Connecticut, United States, 06850
United States, Connecticut
Cancer Center of Central Connecticut
[Recruiting]
Southington, Connecticut, United States, 06489
Contact:Contact: Mark Turney 860-621-9316
Contact:Principal Investigator: Peter Byeff, MD
United States, Florida
Shands Cancer Hospital at University of Florida
Gainesville, Florida, United States, 32608
Cleveland Clinic Florida
Weston, Florida, United States, 33331
United States, Georgia
Winship Cancer Institute, Emory University
Atlanta, Georgia, United States, 30322
Blood and Marrow Transplant Group of Georgia
Atlanta, Georgia, United States, 30342
United States, Illinois
The University of Chicago Medical Center
[Recruiting]
Chicago, Illinois, United States, 60637
Contact:Contact: Margaret Green, RN 773-702-0267
Contact:Principal Investigator: Wendy Stock, MD Northwestern Memorial Hospital
Chicago, Illinois, United States, 60611
Rush University Medical Center
Chicago, Illinois, United States, 60612
The University of Chicago Medical Center
Chicago, Illinois, United States, 60637
United States, Indiana
St. Francis Medical Group Oncology and Hematology Specialists
Indianapolis, Indiana, United States, 46237
United States, Iowa
University of Iowa Hospitals and Clinics
Iowa City, Iowa, United States, 52242
United States, Maryland
University of Maryland Greenbaum Cancer Center
Baltimore, Maryland, United States, 21201
United States, Massachusetts
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States, 02215
United States, Michigan
Henry Ford Health System
Detroit, Michigan, United States, 48202
United States, Minnesota
Mayo Clinic
Rochester, Minnesota, United States, 55905
United States, Missouri
Saint Luke's Cancer Institute
Kansas City, Missouri, United States, 64111
St. Louis University Cancer Center
Saint Louis, Missouri, United States, 63110
United States, Nebraska
University of Nebraska Medical Center
Omaha, Nebraska, United States, 68198
United States, New Hampshire
Dartmouth - Hitchcock Medical Center
Lebanon, New Hampshire, United States, 03756
United States, New Jersey
John Theurer Cancer Center at the Hackensack University Medical Center
Hackensack, New Jersey, United States, 07601
United States, New York
Westchester Hematology Oncology Group, PC
Hawthorne, New York, United States, 10532
Beth Israel Medical Center
New York, New York, United States, 10003
Memorial Sloan Kettering Cancer Center
New York, New York, United States, 10065
Stony Brook University Medical Center
Stony Brook, New York, United States, 11794
United States, North Carolina
Duke University Medical Center
Durham, North Carolina, United States, 27710
United States, Ohio
Gabrail Cancer Center Research
Canton, Ohio, United States, 44718
University of Cincinnati
Cincinnati, Ohio, United States, 45267
Cleveland Clinic Foundation
Cleveland, Ohio, United States, 44195
United States, Pennsylvania
Penn State Milton S. Hershey Medical Center
Hershey, Pennsylvania, United States, 17033
Abramson Cancer Center of the University of Pennsylvania
Philadelphia, Pennsylvania, United States, 19104
United States, South Carolina
Saint Francis Hospital
Greenville, South Carolina, United States, 29601
United States, Tennessee
Vanderbilt University Medical Center
Nashville, Tennessee, United States, 37232
United States, Texas
Baylor University Medical Center
Dallas, Texas, United States, 75246
United States, Texas
MD Anderson Cancer Center
[Recruiting]
Houston, Texas, United States, 77030-3387
Contact:Contact: Patricia Boone, RN 713-792-9191
Contact:Principal Investigator: Hagop Kantarjian, MD MD Anderson Cancer Center
Houston, Texas, United States, 77030-3387
Joe Arrington Cancer Research and Treatment Center
Lubbock, Texas, United States, 79410
United States, Utah
Huntsman Cancer Institute at the University of Utah
Salt Lake City, Utah, United States, 84112
United States, Wisconsin
The Medical College of Wisconsin
Milwaukee, Wisconsin, United States, 53226
Austria
Medizinische Universitaetsklinik
Innsbruck, Austria
Elisabethinen Krankenhaus
Linz, Austria
Krankenhaus der Barmherzigen Schwestern
Linz, Austria
Univ. Klinik fur Innere Medizin III LKH
Salzburg, Austria
Klinikum Wels-Grieskirchen GmbH
Wels, Austria
AKH Wien
Wien, Austria
Hanusch Krankenhaus
Wien, Austria
Belgium
Ziekenhuis Netwerk Antwerpen Stuivenberg
Antwerpen, Belgium
AZ Sint-Jan Brugge-Oostende
Brugge, Belgium
Universite Catholique de Louvain
Brussels, Belgium
Centre Hospitalier De Jolimont-Lobbes
La Louviere, Belgium
Cliniques Universitaires UCL de Mont-Godinne
Yvoir, Belgium
France
CHU d'Amiens Hopital Sud
Amiens, France
Centre Hospitalier de la Cote Basque
Bayonne, France
CHU de Lyon - Hopital Edouard Herriot
Lyon, France
Institut Paoli Calmettes
Marseille, France
CHRU De Montpellier Hopital St. Eloi
Montpellier, France
Centre Hospitalier De Mulhouse
Mulhouse, France
Hopital St Louis Universite Paris 7
Paris, France
Centre Hospitalier de Perigueux
Perigueux, France
Centre Hospitalier d'Annecy
Pringy, France
Centre Hospitalier de Saint-Brieuc Yves Ie Foll
St Brieuc, France
CHU de Strasbourg - Hopital Civil
Strasbourg, France
Strasbourg Oncologie Liberale
Strasbourg, France
CHU de Tours Hopital Bretonneau
Tours, France
Germany
Universitaetsklinikum Charite Berlin, Campus Benjamin Franklin
Berlin, Germany
Universitaetsklinikum Carl-Gustav-Carus Dresden
Dresden, Germany
St. Johannes Hospital
Duisburg, Germany
Klinikum Frankfurt Hoechst
Frankfurt, Germany
Asklepios Klinik Altona
Hamburg, Germany
Medizinische Hochschule Hannover
Hannover, Germany
SLK Kliniken Heilbronn
Heilbronn, Germany
Klinikum St. Georg
Leipzig, Germany
Johannes Wesling Klinikum
Minden, Germany
TU Muenchen
Muenchen, Germany
Universitaetsklinikum Muenster
Muenster, Germany
Hungary
University of Debrecen
Debrecen, Hungary
Petz Aladar Megyei Oktato Korhaz
Győr, Hungary
Kaposi Mor Oktato Korhaz
Kaposvár, Hungary
Italy
AOU Ospedali Riuniti Umberto I
Ancona, Italy
AO Ospedali Riuniti di Bergamo
Bergamo, Italy
Universita di Bologna Ist Ematologia Oncologia Medica Seragnoli
Bologna, Italy
AO Spedali Civili di Brescia
Brescia, Italy
Universita Cattolica del Sacro Cuore
Campobasso, Italy
AOU Careggi
Firenze, Italy
AOU San Martino IST
Genova, Italy
PO Vito Fazzi
Lecce, Italy
Ospedale San Raffaele
Milano, Italy
AORN Antonio Cardarelli
Napoli, Italy
Uni. Napoli Ospedale Federico lI
Napoli, Italy
AOU Maggiore della Carità di Novara
Novara, Italy
AOOR Villa Sofia Cervello di Palermo
Palermo, Italy
Policlinico San Matteo Di Pavia
Pavia, Italy
AOU San Luigi Gonzaga
Torino, Italy
Poland
Akademickie Centrum Kliniczne Szpital Akademii Medycznej w Gdansku
Gdansk, Poland
Wojewodzki Szpital Specjalistyczny
Legnica, Poland
Wojewódzki Szpital Specjalistyczny w Legnicy
Legnica, Poland
University of Lodz N. Copernicus Memorial Hospital
Lodz, Poland
IHT Instytut Hematologii I Transfuzjologii w Warszawie
Warsaw, Poland
Samodzielny Publiczny Szpital Kliniczny Nr 1 w Wroclawiu
Wroclaw, Poland
Spain
Hospital Universitari Germans Trias i Pujol ICO Badalona
Badalona, Spain
Hospital Clinic de Barcelona
Barcelona, Spain
Hospital De La Santa Creu Sant Pau
Barcelona, Spain
Hospital Universitario Vall d'Hebron
Barcelona, Spain
Hospital Universitario de Canarias
La Laguna, Spain
Hospital Universitario Ramon y Cajal
Madrid, Spain
MD Anderson Cancer Center
Madrid, Spain
Hospital Son Llatzer
Palma de Mallorca, Spain
Hospital Universitari Son Espases
Palma de Mallorca, Spain
Clínica Universidad de Navarra
Pamplona, Spain
Complejo Hospitalario de Navarra
Pamplona, Spain
Hospital Clinico Universitario de Salamanca
Salamanca, Spain
Hospital Clinico Universitario
Santiago de Compostela, Spain
Hospital Universitario Virgen del Rocio
Sevilla, Spain
Hospital Universitari "La Fe"
Valencia, Spain
Sweden
Sunderby Hospital
Luleå, Sweden
Skåne Universitetssjukhus Univ Hospital Lund
Lund, Sweden
Switzerland
Inselspital Bern
Bern, Switzerland
United Kingdom
Kings College Hospital and Guys and St Thomas' Hospital
London, United Kingdom
-
-
-
-
-
-
- Open or close this module -IPDSharing -
- - - - - - - - - -
Plan to Share IPD: No
-
-
-
-
-
-
- Open or close this module -References -
- - - - - - - - - - - - - - -
Citations: [Study Results] Kantarjian, H.M.; Begna, K.H.; Altman, J.K.; Goldberg, S.L.; Sekeres, M.A.; Strickland, S.A.; Rubenstein, S.E.; Arellano, M.L.; Claxton, D.F.; Baer, M.R.; et al. Results of a Phase 3 Study of Elderly Patients with Newly Diagnosed AML Treated with Sapacitabine and Decitabine Administered in Alternating Cycles. Blood 2017, vol. 130 no. Suppl 1 891. http://www.bloodjournal.org/content/130/Suppl_1/891.
Links:
Available IPD/Information:
-
-
-
-
-
-
-
Scroll up to access the controls -Scroll to the Study top
-
U.S. National Library of Medicine | U.S. National Institutes of Health | U.S. Department of Health & Human Services
- - - - + + History of Changes for Study: NCT01303796 + + + + + + + + + + +
ClinicalTrials.gov +
+
+
+
History of Changes for Study: + NCT01303796
+
A Study of Oral Sapacitabine in + Elderly Patients With Newly Diagnosed Acute Myeloid Leukemia (SEAMLESS)
+
Latest version (submitted October 28, 2018) on + ClinicalTrials.gov
+
+
+
+
+
+
    +
  • A study version is represented by a row in the table.
    • +
  • Select two study versions to compare. One each from columns A and B.
    • +
  • Choose either the "Merged" or "Side-by-Side" comparison format to specify how the + two study versions are to be displayed. The Side-by-Side format only applies to the Protocol section of + the study.
    • +
  • Click "Compare" to do the comparison and show the differences.
    • +
  • Select a version's Submitted Date link to see a rendering of the study for that version.
    • +
  • The yellow A/B choices in the table indicate the + study versions currently compared below. A yellow + table row indicates the study version currently being viewed.
    • +
  • Hover over the "Recruitment Status" to see how the + study's recruitment status changed.
    • +
  • Study edits or deletions are displayed in red.
    • +
  • Study additions are displayed in green.
    • +
+
+
+
+
+
+
+ Study Record Versions + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
VersionAB + Submitted DateChanges
1 + February + 24, 2011 + None (earliest Version on record) +
2 + + March 23, + 2011 + Contacts/Locations and Study Status
3 + + April 11, + 2011 + Contacts/Locations and Study Status
4 + + November + 7, 2011 + Sponsor/Collaborators, Study Status, + Contacts/Locations and Oversight
5 + + May 2, 2012 + Study Status, Outcome Measures, Arms and + Interventions, Study Description, Contacts/Locations and Study Design
6 + + May 3, 2012 + Contacts/Locations and Study Status
7 + + May 4, 2012 + Contacts/Locations and Study Status
8 + + May 7, 2012 + Contacts/Locations and Study Status
9 + + May 14, + 2012 + Contacts/Locations and Study Status
10 + + July 11, + 2012 + Contacts/Locations and Study Status
11 + + September 25, 2012 + Study Status and Contacts/Locations
12 + + December 14, 2012 + Contacts/Locations and Study Status
13 + + November 14, 2013 + Contacts/Locations and Study Status
14 + + February 10, 2014 + Contacts/Locations and Study Status
15 + + March 25, + 2014 + Contacts/Locations and Study Status
16 + + September 8, 2014 + Contacts/Locations and Study Status
17 + + April 13, + 2015 + Recruitment Status, Study Status and + Contacts/Locations
18 + + August + 17, 2015 + Contacts/Locations and Study Status
19 + + October + 18, 2018 + Recruitment Status, Study Status, Arms and + Interventions, Outcome Measures, Contacts/Locations, Study Design, Study Description, Oversight, + IPDSharing, References and Eligibility
20 + October + 28, 2018 + Arms and Interventions and Study + Status
+
+ Show
+ + 		+
Results Submission Events
+
+
+ +
+ Comparison Format: +
    +
    • +
    • +
+
+
+
+
+
+
+
+
+
+ +
+
Scroll up to access the controls
+
+
+ Changes (Merged) for Study: NCT01303796
+ February 24, 2011 (v1) -- October 28, 2018 (v20)

Changes in: Study Status, Sponsor/Collaborators, Oversight, Study Description, Study + Design, Arms and Interventions, Outcome Measures, Eligibility, Contacts/Locations, IPDSharing, References + +
+ +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+
+ Open or close this module + Study Identification +
+ + + + + + + + + + + + + + + + + + + + + + + + + +
Unique Protocol ID:CYC682-12
Brief Title:A Study of Oral Sapacitabine in Elderly Patients With Newly Diagnosed Acute Myeloid Leukemia + (SEAMLESS)
Official Title:A Phase III Randomized Study of Oral Sapacitabine in Elderly Patients With Newly Diagnosed + Acute Myeloid Leukemia
Secondary IDs:
+
+
+
+
+
+
+
+
+ Open or close this module + Study Status +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Record Verification:February 2011 October 2018 +
Overall Status:Recruiting Completed
Study Start:January 2011 October 1, + 2011
Primary Completion:September 2013 [Anticipated] December 15, 2016 [Actual]
Study Completion:March 2014 [Anticipated] July 31, + 2017 [Actual]
First Submitted:February 21, 2011
First Submitted that
Met QC Criteria:		February 24, 2011
First Posted:February 25, 2011 [Estimate]
Last Update Submitted that
Met QC Criteria: + 		February 24, 2011 October 28, + 2018
Last Update Posted:February 25, 2011 [Estimate] October 31, 2018 [Actual]
+
+
+
+
+
+
+
+
+ Open or close this module + Sponsor/Collaborators +
+ + + + + + + + + + + + + + + + + + + + +
Sponsor:Cyclacel Pharmaceuticals, Inc.
Responsible Party: Sponsor
Collaborators:
+
+
+
+
+
+
+
+
+ Open or close this module + Oversight +
+ + + + + + + + + + + + + + + + + + + + + +
U.S. FDA-regulated Drug: Yes
U.S. FDA-regulated Device: No
Data Monitoring: Yes
+
+
+
+
+
+
+
+
+ Open or close this module + Study Description +
+ + + + + + + + + + + + + + + + + +
Brief Summary:This Phase 3 study assesses three two drug regimens as the initial treatment of patients who are at + least 70 years of age and have newly diagnosed acute myeloid leukemia (AML) for whom the + doctor does not recommend the use of standard intensive treatment or the patient has decided + not to receive standard intensive treatment after being fully informed about its benefits and + risks by his/her doctor. The three two drug regimens are sapacitabine administered in alternating + cycles with decitabine, sapacitabine alone or decitabine + or decitabine alone. The purpose of the study is to learn + which drug regimen is more likely to keep AML in check as long as possible.
Detailed Description:This is a multicenter, randomized, Phase 3 study ("SEAMLESS") comparing three + two drug regimens (arms) as the front-line treatment + of elderly patients aged 70 years or older with newly diagnosed acute myeloid leukemia (AML) + who are not candidates for intensive induction chemotherapy. In Arm A, sapacitabine is + administered in alternating cycles with decitabine, in Arm B + sapacitabine is administered alone and in Arm C decitabine is administered alone. + The primary efficacy endpoint is overall survival. The study is designed to demonstrate an + improvement in overall survival of either of two pairwise + comparisons: (1) Arm A versus Arm C or (2) Arm B versus + Arm C.
+
+
+
+
+
+
+
+
+ Open or close this module + Conditions +
+ + + + + + + + + + + + + + + + + +
Conditions:Acute Myeloid Leukemia
Keywords:AML
+
+
+
+
+
+
+
+
+ Open or close this module + Study Design +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Study Type:Interventional
Primary Purpose:Treatment
Study Phase:Phase 3
Interventional Study Model:Parallel Assignment
Number of Arms:3 2
Masking:None (Open Label)
Allocation:Randomized
Enrollment:470 [Anticipated] 482 + [Actual]
+
+
+
+
+
+
+
+
+ Open or close this module + Arms and Interventions +
+ + + + + + + + + + + + +
+ + + + + + + + + + + + + + + + + + + + + +
ArmsAssigned Interventions
Experimental: Arm A Experimental: Sapacitabine-decitabine alternating +
Sapacitabine and decitabine + Arm A sapacitabine administered in alternating cycles with + decitabine
+ 		Drug: Sapacitabine and decitabine Drug: Sapacitabine +
Sapacitabine administered in + alternating cycles with decitabine oral + sapacitabine capsules
Drug: + Decitabine +
decitabine intravenous + +
+
Active Comparator: Arm B +
Sapacitabine + +
+ 		Drug: Sapacitabine +
Sapacitabine alone + +
+
Active Comparator: Arm C Decitabine +
Arm C Decitabine
+ 		Drug: Decitabine
Decitabine + alone decitabine intravenous
+
+
+
+
+
+
+
+
+
+
+ Open or close this module + Outcome Measures +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Primary Outcome Measures:
1.Overall survival
[ Time Frame: up to 39 43 months ]

OS + +
Secondary Outcome Measures:
1.Complete remission with duration
[ Time Frame: Up up to 39 43 months ]

CR with duration + +
2.Complete remission with incomplete platelet count recovery and duration
[ Time Frame: up + to 39 43 months + ]

CRp with duration + +
3.Partial remission with duration
[ Time Frame: up to 39 + 43 months ]

PR with duration + +
4.Hematological improvement with duration
[ Time Frame: up to 39 + 43 months ]

HI with + duration + +
5.Stable disease with duration
[ Time Frame: up to 39 + 43 months ]

SD with duration + +
6.Number of units of blood product transfused
[ Time Frame: up to 39 43 months ]

7.Hospitalized days
[ Time Frame: up to 39 43 months ]

8.1-year survival
[ Time Frame: up to 39 43 months ]

In % + +
+
+
+
+
+
+
+
+
+ Open or close this module + Eligibility +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Minimum Age:70 Years
Maximum Age:
Sex:All
Gender Based:
Accepts Healthy Volunteers:No
Criteria: +

Inclusion Criteria:

+
    +
  • Newly diagnosed AML based on WHO (World Health Organization) + classification
    • +
  • Age 70 years or older for whom the treatment of choice is low-intensity therapy by + investigator assessment or who has refused intensive induction therapy recommended by + investigator
    • +
  • ECOG (Eastern Cooperative Oncology Group) performance + status 0-2
    • +
  • Adequate renal function
    • +
  • Adequate liver function
    • +
  • Able to swallow capsules
    • +
  • Agree to practice effective contraception
    • +
  • Ability to understand and willingness to sign the informed consent form
    • +
+

Exclusion Criteria:

+
    +
  • AML is of the sub-type of acute promyelocytic leukemia or extramedullary myeloid tumor + without bone marrow involvement
    • +
  • Having received any systemic anti-cancer therapy for AML or received treatment with + hypomethylating agents or cytotoxic chemotherapy for the + preceding MDS myelodysplastic + syndrome (MDS) or myeloproliferative disease + (MPD)
    • +
  • Known or suspected central nervous system (CNS) involvement by leukemia
    • +
  • Uncontrolled intercurrent illness
    • +
  • Known hypersensitivity to decitabine
    • +
  • Known to be HIV-positive
    • +
+
+
+
+
+
+
+
+
+
+ Open or close this module + Contacts/Locations +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Central Contact Person:Judy H Chiao, MD
Telephone: + 908-517-7330
Email: jchiao@cyclacel.com +
Study Officials: Hagop M Kantarjian, M.D.
Study + Chair
M.D. Anderson Cancer Center
Locations: United States, + Alabama
University of Alabama Comprehensive Cancer Center
Birmingham, Alabama, United States, 35294
United States, + California
Scripps Cancer Center
La Jolla, + California, United States, 92037
UCLA Ronald Reagan Medical Center
Los + Angeles, California, United States, 90095
United States, + Connecticut
Norwalk Hospital
Norwalk, Connecticut, + United States, 06850
United States, + Connecticut
Cancer Center of Central Connecticut
[Recruiting]
Southington, Connecticut, United States, 06489
Contact:Contact: Mark Turney + 860-621-9316
Contact:Principal Investigator: Peter Byeff, MD +
United States, + Florida
Shands Cancer Hospital at University of Florida
Gainesville, Florida, United States, 32608
Cleveland Clinic Florida
Weston, Florida, + United States, 33331
United States, + Georgia
Winship Cancer Institute, Emory University
Atlanta, Georgia, United States, 30322
Blood and Marrow Transplant Group of Georgia
Atlanta, Georgia, United States, 30342
United States, Illinois
The University of Chicago Medical Center
[Recruiting]
Chicago, Illinois, United States, 60637
Contact:Contact: Margaret Green, RN + 773-702-0267
Contact:Principal Investigator: Wendy Stock, MD + Northwestern Memorial Hospital
Chicago, Illinois, United States, 60611
Rush University Medical Center
Chicago, + Illinois, United States, 60612
The University of Chicago Medical Center
Chicago, Illinois, United States, 60637
United States, + Indiana
St. Francis Medical Group Oncology and Hematology + Specialists
Indianapolis, Indiana, United States, + 46237
United States, Iowa +
University of Iowa Hospitals and Clinics
Iowa City, Iowa, United States, 52242
United States, + Maryland
University of Maryland Greenbaum Cancer Center
Baltimore, Maryland, United States, 21201
United States, + Massachusetts
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States, 02215
United States, + Michigan
Henry Ford Health System
Detroit, + Michigan, United States, 48202
United States, + Minnesota
Mayo Clinic
Rochester, Minnesota, United + States, 55905
United States, + Missouri
Saint Luke's Cancer Institute
Kansas + City, Missouri, United States, 64111
St. Louis University Cancer Center
Saint + Louis, Missouri, United States, 63110
United States, + Nebraska
University of Nebraska Medical Center
Omaha, Nebraska, United States, 68198
United States, New + Hampshire
Dartmouth - Hitchcock Medical Center
Lebanon, New Hampshire, United States, 03756
United States, New + Jersey
John Theurer Cancer Center at the Hackensack University Medical + Center
Hackensack, New Jersey, United States, 07601 +
United States, New + York
Westchester Hematology Oncology Group, PC
Hawthorne, New York, United States, 10532
Beth Israel Medical Center
New York, New + York, United States, 10003
Memorial Sloan Kettering Cancer Center
New York, New York, United States, 10065
Stony Brook University Medical Center
Stony Brook, New York, United States, 11794
United States, North + Carolina
Duke University Medical Center
Durham, + North Carolina, United States, 27710
United States, Ohio +
Gabrail Cancer Center Research
Canton, + Ohio, United States, 44718
University of Cincinnati
Cincinnati, + Ohio, United States, 45267
Cleveland Clinic Foundation
Cleveland, + Ohio, United States, 44195
United States, + Pennsylvania
Penn State Milton S. Hershey Medical Center
Hershey, Pennsylvania, United States, 17033
Abramson Cancer Center of the University of Pennsylvania
Philadelphia, Pennsylvania, United States, 19104
United States, South + Carolina
Saint Francis Hospital
Greenville, South + Carolina, United States, 29601
United States, + Tennessee
Vanderbilt University Medical Center
Nashville, Tennessee, United States, 37232
United States, Texas +
Baylor University Medical Center
Dallas, + Texas, United States, 75246
United States, Texas +
MD Anderson Cancer Center
[Recruiting]
Houston, Texas, United States, 77030-3387
Contact:Contact: Patricia Boone, RN + 713-792-9191
Contact:Principal Investigator: Hagop Kantarjian, MD + MD Anderson Cancer Center
Houston, Texas, United States, 77030-3387
Joe Arrington Cancer Research and Treatment Center
Lubbock, Texas, United States, 79410
United States, Utah +
Huntsman Cancer Institute at the University of Utah
Salt Lake City, Utah, United States, 84112
United States, + Wisconsin
The Medical College of Wisconsin
Milwaukee, Wisconsin, United States, 53226
Austria
Medizinische Universitaetsklinik
Innsbruck, Austria
Elisabethinen Krankenhaus
Linz, + Austria
Krankenhaus der Barmherzigen Schwestern
Linz, Austria
Univ. Klinik fur Innere Medizin III LKH
Salzburg, Austria
Klinikum Wels-Grieskirchen GmbH
Wels, + Austria
AKH Wien
Wien, Austria
Hanusch Krankenhaus
Wien, + Austria
Belgium
Ziekenhuis Netwerk Antwerpen Stuivenberg
Antwerpen, Belgium
AZ Sint-Jan Brugge-Oostende
Brugge, + Belgium
Universite Catholique de Louvain
Brussels, Belgium
Centre Hospitalier De Jolimont-Lobbes
La + Louviere, Belgium
Cliniques Universitaires UCL de Mont-Godinne
Yvoir, Belgium
France
CHU d'Amiens Hopital Sud
Amiens, + France
Centre Hospitalier de la Cote Basque
Bayonne, France
CHU de Lyon - Hopital Edouard Herriot
Lyon, France
Institut Paoli Calmettes
Marseille, + France
CHRU De Montpellier Hopital St. Eloi
Montpellier, France
Centre Hospitalier De Mulhouse
Mulhouse, + France
Hopital St Louis Universite Paris 7
Paris, France
Centre Hospitalier de Perigueux
Perigueux, France
Centre Hospitalier d'Annecy
Pringy, + France
Centre Hospitalier de Saint-Brieuc Yves Ie Foll
St Brieuc, France
CHU de Strasbourg - Hopital Civil
Strasbourg, France
Strasbourg Oncologie Liberale
Strasbourg, + France
CHU de Tours Hopital Bretonneau
Tours, + France
Germany
Universitaetsklinikum Charite Berlin, Campus Benjamin + Franklin
Berlin, Germany
Universitaetsklinikum Carl-Gustav-Carus Dresden
Dresden, Germany
St. Johannes Hospital
Duisburg, + Germany
Klinikum Frankfurt Hoechst
Frankfurt, + Germany
Asklepios Klinik Altona
Hamburg, + Germany
Medizinische Hochschule Hannover
Hannover, Germany
SLK Kliniken Heilbronn
Heilbronn, + Germany
Klinikum St. Georg
Leipzig, + Germany
Johannes Wesling Klinikum
Minden, + Germany
TU Muenchen
Muenchen, + Germany
Universitaetsklinikum Muenster
Muenster, + Germany
Hungary
University of Debrecen
Debrecen, + Hungary
Petz Aladar Megyei Oktato Korhaz
Győr, + Hungary
Kaposi Mor Oktato Korhaz
Kaposvár, + Hungary
Italy
AOU Ospedali Riuniti Umberto I
Ancona, + Italy
AO Ospedali Riuniti di Bergamo
Bergamo, + Italy
Universita di Bologna Ist Ematologia Oncologia Medica + Seragnoli
Bologna, Italy
AO Spedali Civili di Brescia
Brescia, + Italy
Universita Cattolica del Sacro Cuore
Campobasso, Italy
AOU Careggi
Firenze, Italy +
AOU San Martino IST
Genova, + Italy
PO Vito Fazzi
Lecce, Italy +
Ospedale San Raffaele
Milano, + Italy
AORN Antonio Cardarelli
Napoli, + Italy
Uni. Napoli Ospedale Federico lI
Napoli, + Italy
AOU Maggiore della Carità di Novara
Novara, Italy
AOOR Villa Sofia Cervello di Palermo
Palermo, Italy
Policlinico San Matteo Di Pavia
Pavia, + Italy
AOU San Luigi Gonzaga
Torino, + Italy
Poland
Akademickie Centrum Kliniczne Szpital Akademii Medycznej w + Gdansku
Gdansk, Poland
Wojewodzki Szpital Specjalistyczny
Legnica, Poland
Wojewódzki Szpital Specjalistyczny w Legnicy
Legnica, Poland
University of Lodz N. Copernicus Memorial Hospital
Lodz, Poland
IHT Instytut Hematologii I Transfuzjologii w Warszawie
Warsaw, Poland
Samodzielny Publiczny Szpital Kliniczny Nr 1 w Wroclawiu
Wroclaw, Poland
Spain
Hospital Universitari Germans Trias i Pujol ICO Badalona
Badalona, Spain
Hospital Clinic de Barcelona
Barcelona, + Spain
Hospital De La Santa Creu Sant Pau
Barcelona, Spain
Hospital Universitario Vall d'Hebron
Barcelona, Spain
Hospital Universitario de Canarias
La + Laguna, Spain
Hospital Universitario Ramon y Cajal
Madrid, Spain
MD Anderson Cancer Center
Madrid, + Spain
Hospital Son Llatzer
Palma de Mallorca, + Spain
Hospital Universitari Son Espases
Palma + de Mallorca, Spain
Clínica Universidad de Navarra
Pamplona, + Spain
Complejo Hospitalario de Navarra
Pamplona, Spain
Hospital Clinico Universitario de Salamanca
Salamanca, Spain
Hospital Clinico Universitario
Santiago + de Compostela, Spain
Hospital Universitario Virgen del Rocio
Sevilla, Spain
Hospital Universitari "La Fe"
Valencia, + Spain
Sweden
Sunderby Hospital
Luleå, + Sweden
Skåne Universitetssjukhus Univ Hospital Lund
Lund, Sweden
Switzerland
Inselspital Bern
Bern, + Switzerland
United Kingdom
Kings College Hospital and Guys and St Thomas' Hospital
London, United Kingdom
+
+
+
+
+
+
+
+
+ Open or close this module + IPDSharing +
+ + + + + + + + + + + + + +
Plan to Share IPD: No
+
+
+
+
+
+
+
+
+ Open or close this module + References +
+ + + + + + + + + + + + + + + + + + + + + +
Citations: [Study Results] Kantarjian, + H.M.; Begna, K.H.; Altman, J.K.; Goldberg, S.L.; Sekeres, M.A.; Strickland, S.A.; + Rubenstein, S.E.; Arellano, M.L.; Claxton, D.F.; Baer, M.R.; et al. Results of a Phase 3 + Study of Elderly Patients with Newly Diagnosed AML Treated with Sapacitabine and Decitabine + Administered in Alternating Cycles. Blood 2017, vol. 130 no. Suppl 1 891. + http://www.bloodjournal.org/content/130/Suppl_1/891.
Links:
Available IPD/Information:
+
+
+
+
+
+
+
Scroll up to access the controls + Scroll to the Study top +
+
+
U.S. National Library of + Medicine | U.S. National + Institutes of Health | U.S. Department of Health & Human Services
+ + + + + + \ No newline at end of file diff --git a/Parser/extraction-lib.py b/Parser/extraction-lib.py index 8202d15..4a11cce 100644 --- a/Parser/extraction-lib.py +++ b/Parser/extraction-lib.py @@ -1,9 +1,9 @@ from collections import namedtuple from copy import copy from datetime import datetime - +import psycopg2 from bs4 import BeautifulSoup -import textprocessing as tp #cuz tp is important +#import textprocessing as tp #cuz tp is important #requires Python 3.10 @@ -28,12 +28,14 @@ class VersionData(): """ def __init__(self,nct_id,version_id): #identifiers - self.nct_id = nct_id + self.nct_id = nct_id.strip() self.version_id = version_id #Study Status self._primary_completion_date = None self._primary_completion_date_category = None + self._start_date = None + self._start_date_category = None self._completion_date = None self._completion_date_category = None self._overall_status = None @@ -49,9 +51,73 @@ class VersionData(): #self._responsible_party_category = None #I don't believe this is included in the raw data #self._collaborators = None #currently going to ignore as I've not fount it in AACT - def load_to_db(db_cursor): + def load_to_db(self,db_connection): #load to initial table, then load any extra details into other tables - pass + sql = """ + INSERT INTO history.trial_snapshots + ( + nct_id, + version, + primary_completion_date, + primary_completion_date_category, + start_date, + start_date_category, + completion_date, + completion_date_category, + overall_status, + enrollment, + enrollment_category, + sponsor, + responsible_party + ) + VALUES + ( + %s, + %s, + %s, + %s, + %s, + %s, + %s, + %s, + %s, + %s, + %s, + %s, + %s + ) + """ + + with db_connection.cursor() as db_cursor: + try: + db_cursor.execute( + sql, + ( + self.nct_id, + self.version_id, + self._primary_completion_date, + self._primary_completion_date_category, + self._start_date, + self._start_date_category, + self._completion_date, + self._completion_date_category, + self._overall_status, + self._enrollment, + self._enrollment_category, + self._sponsor, + self._responsible_party + ) + ) + except Exception as err: + #catch any error, print the applicable information, and raise the error. + print(self) + raise err + +def optional_strip(possible_string): + if type(possible_string) == str: + return possible_string.strip() + else: + return possible_string def extract_study_statuses(study_status_form, version_a,version_b): """ @@ -70,26 +136,36 @@ def extract_study_statuses(study_status_form, version_a,version_b): old,new = split_by_version(tag) tagdate1 = extract_date_and_tag(old.text) version_a._primary_completion_date = tagdate1.date - version_a._primary_completion_date_category = tagdate1.tag + version_a._primary_completion_date_category = optional_strip(tagdate1.tag) tagdate2 = extract_date_and_tag(new.text) version_b._primary_completion_date = tagdate2.date - version_b._primary_completion_date_category = tagdate2.tag + version_b._primary_completion_date_category = optional_strip(tagdate2.tag) + + case ["Study Start:" as row_label, tag]: + old,new = split_by_version(tag) + tagdate1 = extract_date_and_tag(old.text) + version_a._start_date = tagdate1.date + version_a._start_date_category = optional_strip(tagdate1.tag) + + tagdate2 = extract_date_and_tag(new.text) + version_b._start_date = tagdate2.date + version_b._start_date_category = optional_strip(tagdate2.tag) case ["Study Completion:" as row_label, tag]: old,new = split_by_version(tag) tagdate1 = extract_date_and_tag(old.text) version_a._completion_date = tagdate1.date - version_a._completion_date_category = tagdate1.tag + version_a._completion_date_category = optional_strip(tagdate1.tag) tagdate2 = extract_date_and_tag(new.text) version_b._completion_date = tagdate2.date - version_b._completion_date_category = tagdate2.tag + version_b._completion_date_category = optional_strip(tagdate2.tag) case ["Overall Status:" as row_label, tag]: old,new = split_by_version(tag) - version_a._overall_status = old.text - version_b._overall_status = new.text + version_a._overall_status = optional_strip(old.text) + version_b._overall_status = optional_strip(new.text) def extract_study_design(study_status_form, version_a,version_b): @@ -108,11 +184,11 @@ def extract_study_design(study_status_form, version_a,version_b): old,new = split_by_version(tag) tagdate1 = extract_text_and_tag(old.text) version_a._enrollment = tagdate1.text - version_a._enrollment_category = tagdate1.tag + version_a._enrollment_category = optional_strip(tagdate1.tag) tagdate2 = extract_text_and_tag(new.text) version_b._enrollment = tagdate2.text - version_b._enrollment_category = tagdate2.tag + version_b._enrollment_category = optional_strip(tagdate2.tag) def extract_sponsor_data(study_status_form, version_a,version_b): @@ -129,13 +205,13 @@ def extract_sponsor_data(study_status_form, version_a,version_b): match tr_to_td(trow): case ["Sponsor:" as row_label, tag]: old, new = split_by_version(tag) - version_a._sponsor = old.text - version_b._sponsor = new.text + version_a._sponsor = optional_strip(old.text) + version_b._sponsor = optional_strip(new.text) case ["Responsible Party:" as row_label, tag]: old, new = split_by_version(tag) - version_a._responsible_party = old.text - version_b._responsible_party = new.text + version_a._responsible_party = optional_strip(old.text) + version_b._responsible_party = optional_strip(new.text) case ["Collaborators:" as row_label, tag]: #old, new = split_by_version(tag) @@ -285,8 +361,14 @@ def get_data_from_versions(nct_id,html, version_a_int, version_b_int): if __name__ == "__main__": - for file in ["./NCT00658567.html", "./NCT01303796.html"]: - with open(file) as fh: + for file in ["NCT00658567", "NCT01303796"]: + with open("./{}.html".format(file)) as fh: version1, version2 = get_data_from_versions(file, fh.read(), 1,2) print(version1.__dict__) #order messed up somewhere:w print(version2.__dict__) #order messed up somewhere:w + + + with psycopg2.connect(dbname="aact_db", user="root", password="root",host="will-office") as db_connection: + version1.load_to_db(db_connection) + version2.load_to_db(db_connection) + #print(db_connection) \ No newline at end of file diff --git a/Parser/prototype_history.sql b/Parser/prototype_history.sql index 49eef82..334ec70 100644 --- a/Parser/prototype_history.sql +++ b/Parser/prototype_history.sql @@ -87,7 +87,7 @@ ALTER TYPE history.study_statuses -- Table: history.trial_snapshots --- DROP TABLE IF EXISTS history.trial_snapshots; +DROP TABLE IF EXISTS history.trial_snapshots; CREATE TABLE IF NOT EXISTS history.trial_snapshots ( @@ -95,6 +95,8 @@ CREATE TABLE IF NOT EXISTS history.trial_snapshots version integer NOT NULL, primary_completion_date timestamp without time zone, primary_completion_date_category history.updatable_catetories, + start_date timestamp without time zone, + start_date_category history.updatable_catetories, completion_date timestamp without time zone, completion_date_category history.updatable_catetories, overall_status history.study_statuses, @@ -103,7 +105,7 @@ CREATE TABLE IF NOT EXISTS history.trial_snapshots sponsor character varying(255) COLLATE pg_catalog."default", responsible_party character varying(255) COLLATE pg_catalog."default", CONSTRAINT trial_snapshots_pkey PRIMARY KEY (nct_id, version) -) +); TABLESPACE pg_default; diff --git a/Parser/textprocessing.py b/Parser/textprocessing.py deleted file mode 100644 index 56a1aeb..0000000 --- a/Parser/textprocessing.py +++ /dev/null @@ -1,184 +0,0 @@ -from copy import copy -from datetime import datetime -from bs4 import BeautifulSoup -import re - -form = """ - - -
-
-
- Open or close this module - Study Status -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Record Verification:April 2008 2017
Overall Status:Recruiting Completed
Study Start:March 2008
Primary Completion: December 2009 [Actual]
Study Completion:December 2009 [ Anticipated Actual]
First Submitted:April 10, 2008
First Submitted that
Met QC Criteria:		April 10, 2008
First Posted:April 15, 2008 [Estimate]
Results First Submitted: February 6, 2014
Results First Submitted that
Met QC - Criteria:		 August 29, 2014
Results First Posted: September 9, 2014 [Estimate]
Last Update Submitted that
Met QC Criteria: - 		April 10 18, 2008 2017
Last Update Posted:April 15, 2008 [Estimate] May 19, - 2017 [Actual]
-
-
-
-
- - -""" - - -entry1 = """ - -Record Verification: -April 2008 2017 - -""" - - -entry2 = ' December 2009 [Actual] ' - -DROP_HILITE_re = re.compile('[\[\]\w]*\s?') -ADD_HILITE_re = re.compile('\w*\s?') -TAGS_RE = re.compile('<[=-_,.:;"/\w\s]+>') - -def extract_new_data(td): - text = td.__str__() - return TAGS_RE.sub("",DROP_HILITE_re.sub(" ",text)).strip() - -def extract_old_data(td): - text = td.__str__() - return TAGS_RE.sub("",ADD_HILITE_re.sub(" ",text)).strip() - -def delete_tags(td): - text = td.__str__() - return TAGS_RE.sub(" ",text).strip() - - -def extract_date_and_tag(text, date_format): - """ - Extracts a datetype according to the date format - and the estimate tag based on - - """ - if not text: - return " " - - date_split = text.split("[") - if len(date_split) > 1: - estimate_tag = date_split[1].split("]")[0].strip() - else: - estimate_tag = None - date_object = datetime.strptime(date_split[0].strip(), date_format) - - return estimate_tag, date_object - #TODO: Write test - -def extract_text_and_tag(text): - """ - - """ - pass - -if __name__ == "__main__": - Entry = BeautifulSoup(entry1, "lxml") - Form = BeautifulSoup(form, "lxml") - - - - print(extract_new_data(Entry.find_all("td")[1])) - print(extract_old_data(Entry.find_all("td")[1])) - - for tr in Form.find_all("tr"): - data = tr.find_all("td") - match len(data): - case 0: print("no data") - case 1: print("1\t",data[0]) - case _: print(len(data), "\t", extract_new_data(data[1]) ,"\t|\t", extract_old_data(data[1])) - - #print(extract_date_and_tag(extract_old_data(Entry.find_all("td")[1]), "%B %Y")) - print(extract_date_and_tag("April 2008 [ test ]", "%B %Y")) - - - Entry2 = BeautifulSoup(entry2,"lxml") - print(extract_old_data(Entry2)) #error here. - print(extract_new_data(Entry2)) - - - Entry3 = copy(Entry2) - print(Entry3) - Entry4 = Entry3.find_all(class_="add_hilite")[0].extract() - print(Entry3.text) - print(Entry4.text) \ No newline at end of file