Skip header and navigation

Refine By

19 records – page 1 of 2.

Collecting a citizen's digital footprint for health data mining.

https://arctichealth.org/en/permalink/ahliterature276567
Source
Conf Proc IEEE Eng Med Biol Soc. 2015;2015:7626-9
Publication Type
Article
Date
2015
Author
Oguzhan Gencoglu
Heidi Simila
Harri Honko
Minna Isomursu
Source
Conf Proc IEEE Eng Med Biol Soc. 2015;2015:7626-9
Date
2015
Language
English
Publication Type
Article
Keywords
Data Collection - methods
Data Mining - methods
Finland
Health
Humans
Registries
Abstract
This paper describes a case study for collecting digital footprint data for the purpose of health data mining. The case study involved 20 subjects residing in Finland who were instructed to collect data from registries which they evaluated to be useful for understanding their health or health behaviour, current or past. 11 subjects were active, sending 100 data requests to 49 distinct organizations in total. Our results indicate that there are still practical challenges in collecting actionable digital footprint data. Our subjects received a total of 75 replies (reply rate of 75.0%) and 61 datasets (reception rate of 61%). Out of the received data, 44 datasets (72.1%) were delivered in paper format, 4 (6.6%) in portable document format and 13 (21.3%) in structured digital form. The time duration between the sending of the information requests and reception of a reply was 26.4 days on the average.
PubMed ID
26738058 View in PubMed
Less detail

Compass: a hybrid method for clinical and biobank data mining.

https://arctichealth.org/en/permalink/ahliterature257981
Source
J Biomed Inform. 2014 Feb;47:160-70
Publication Type
Article
Date
Feb-2014
Author
K. Krysiak-Baltyn
T. Nordahl Petersen
K. Audouze
Niels Jørgensen
L. Angquist
S. Brunak
Author Affiliation
Center for Biological Sequence Analysis, Technical University of Denmark, Lyngby, Denmark.
Source
J Biomed Inform. 2014 Feb;47:160-70
Date
Feb-2014
Language
English
Publication Type
Article
Keywords
Algorithms
Biological Specimen Banks
Breast Neoplasms - epidemiology
Data Mining - methods
Denmark
Female
Humans
Infertility, Male - epidemiology
Information Storage and Retrieval
Male
Phenotype
Prostatic Neoplasms - epidemiology
Questionnaires
Toxicogenetics
Abstract
We describe a new method for identification of confident associations within large clinical data sets. The method is a hybrid of two existing methods; Self-Organizing Maps and Association Mining. We utilize Self-Organizing Maps as the initial step to reduce the search space, and then apply Association Mining in order to find association rules. We demonstrate that this procedure has a number of advantages compared to traditional Association Mining; it allows for handling numerical variables without a priori binning and is able to generate variable groups which act as "hotspots" for statistically significant associations. We showcase the method on infertility-related data from Danish military conscripts. The clinical data we analyzed contained both categorical type questionnaire data and continuous variables generated from biological measurements, including missing values. From this data set, we successfully generated a number of interesting association rules, which relate an observation with a specific consequence and the p-value for that finding. Additionally, we demonstrate that the method can be used on non-clinical data containing chemical-disease associations in order to find associations between different phenotypes, such as prostate cancer and breast cancer.
PubMed ID
24513869 View in PubMed
Less detail

Data mining: comparing the empiric CFS to the Canadian ME/CFS case definition.

https://arctichealth.org/en/permalink/ahliterature132382
Source
J Clin Psychol. 2012 Jan;68(1):41-9
Publication Type
Article
Date
Jan-2012
Author
Leonard A Jason
Beth Skendrovic
Jacob Furst
Abigail Brown
Angela Weng
Christine Bronikowski
Author Affiliation
DePaul University, USA. Ljason@depaul.edu
Source
J Clin Psychol. 2012 Jan;68(1):41-9
Date
Jan-2012
Language
English
Publication Type
Article
Keywords
Canada
Chicago
Chronic Disease
Data Mining - methods
Diagnostic and Statistical Manual of Mental Disorders
Fatigue - diagnosis
Fatigue Syndrome, Chronic - diagnosis
Follow-Up Studies
Health Surveys
Humans
Interview, Psychological
Psychiatric Status Rating Scales
Psychometrics - instrumentation
Reproducibility of Results
Risk
Sensitivity and specificity
Severity of Illness Index
Abstract
This article contrasts two case definitions for myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). We compared the empiric CFS case definition (Reeves et al., 2005) and the Canadian ME/CFS clinical case definition (Carruthers et al., 2003) with a sample of individuals with CFS versus those without. Data mining with decision trees was used to identify the best items to identify patients with CFS. Data mining is a statistical technique that was used to help determine which of the survey questions were most effective for accurately classifying cases. The empiric criteria identified about 79% of patients with CFS and the Canadian criteria identified 87% of patients. Items identified by the Canadian criteria had more construct validity. The implications of these findings are discussed.
Notes
Cites: Arch Intern Med. 2003 Jul 14;163(13):1530-612860574
Cites: BMC Health Serv Res. 2003 Dec 31;3(1):2514702202
Cites: Rev Infect Dis. 1991 Jan-Feb;13 Suppl 1:S8-112020806
Cites: Med Care. 1992 Jun;30(6):473-831593914
Cites: Ann Intern Med. 1994 Dec 15;121(12):953-97978722
Cites: J Psychosom Res. 1995 Apr;39(3):315-257636775
Cites: Am J Med. 1996 Jan;100(1):56-648579088
Cites: Arch Intern Med. 1999 Oct 11;159(18):2129-3710527290
Cites: BMC Med. 2005;3:1916356178
Cites: Int J Behav Med. 2006;13(3):244-5117078775
Cites: Disabil Rehabil. 2011;33(7):589-9820617920
Cites: J Health Psychol. 2011 Apr;16(3):445-5621224330
Cites: Breast Cancer Res Treat. 2001 Mar;66(1):51-711368410
PubMed ID
21823124 View in PubMed
Less detail

Detection of adverse drug events detection: data aggregation and data mining.

https://arctichealth.org/en/permalink/ahliterature148619
Source
Stud Health Technol Inform. 2009;148:75-84
Publication Type
Article
Date
2009
Author
Emmanuel Chazard
Grégoire Ficheur
Béatrice Merlin
Michael Genin
Cristian Preda
Régis Beuscart
Author Affiliation
Lille university hospital, EA2694, Lille, France. emmanuel@chazard.org
Source
Stud Health Technol Inform. 2009;148:75-84
Date
2009
Language
English
Publication Type
Article
Keywords
Data Collection
Data Mining - methods
Denmark
Drug-Related Side Effects and Adverse Reactions - diagnosis
France
Humans
Medical Records Systems, Computerized
Abstract
Adverse drug events (ADEs) are a public health issue. The objective of this work is to data-mine electronic health records in order to automatically identify ADEs and generate alert rules to prevent those ADEs. The first step of data-mining is to transform native and complex data into a set of binary variables that can be used as causes and effects. The second step is to identify cause-to-effect relationships using statistical methods. After mining 10,500 hospitalizations from Denmark and France, we automatically obtain 250 rules, 75 have been validated till now. The article details the data aggregation and an example of decision tree that allows finding several rules in the field of vitamin K antagonists.
PubMed ID
19745237 View in PubMed
Less detail

The development of a standardized software platform to support provincial population-based cancer outcomes units for multiple tumour sites: OaSIS - Outcomes and Surveillance Integration System.

https://arctichealth.org/en/permalink/ahliterature116533
Source
Stud Health Technol Inform. 2013;183:98-103
Publication Type
Article
Date
2013
Author
Jonn Wu
Cheryl Ho
Janessa Laskin
David Gavin
Paul Mak
Keith Duncan
John French
Colleen McGahan
Sherry Reid
Stephen Chia
Heidi Cheung
Author Affiliation
BC Cancer Agency, Vancouver, British Columbia. johnwu@bccancer.bc.ca
Source
Stud Health Technol Inform. 2013;183:98-103
Date
2013
Language
English
Publication Type
Article
Keywords
Canada - epidemiology
Data Mining - methods
Database Management Systems
Databases, Factual
Humans
Information Storage and Retrieval - methods
Neoplasms - epidemiology
Registries
Software
Software Design
Abstract
Understanding the impact of treatment policies on patient outcomes is essential in improving all aspects of patient care. The BC Cancer Agency is a provincial program that provides cancer care on a population basis for 4.5 million residents. The Lung and Head & Neck Tumour Groups planned to create a generic yet comprehensive software infrastructure that could be used by all Tumour Groups: the Outcomes and Surveillance Integration System (OaSIS). The primary goal was the development of an integrated database that will amalgamate existing provincial data warehouses of varying datasets and provide the infrastructure to support additional routes of data entry, including clinicians from multiple-disciplines, quality of life and survivorship data from patients, and three dimensional dosimetric information archived from the radiotherapy planning and delivery systems. The primary goal is to be able to capture any data point related to patient characteristics, disease factors, treatment details and survivorship, from the point of diagnosis onwards. Through existing and novel data-mining techniques, OaSIS will support unique population based research activities by promoting collaborative interactions between the research centre, clinical activities at the cancer treatment centres and other institutions. This will also facilitate initiatives to improve patient outcomes, decision support in achieving operational efficiencies and an environment that supports knowledge generation.
PubMed ID
23388263 View in PubMed
Less detail

Development of computational information technology for monitoring NCD risks in the Russian population: preliminary results.

https://arctichealth.org/en/permalink/ahliterature281794
Source
Stud Health Technol Inform. 2014;202:253-6
Publication Type
Article
Date
2014
Author
Svetlana P Chernykh
Sergey G Rudnev
Dmitriy V Nikolaev
Olga A Starunova
Source
Stud Health Technol Inform. 2014;202:253-6
Date
2014
Language
English
Publication Type
Article
Keywords
Adolescent
Adult
Age Distribution
Aged
Aged, 80 and over
Child
Child, Preschool
Chronic Disease - epidemiology
Comorbidity
Data Mining - methods
Electronic Health Records - statistics & numerical data
Female
Humans
Male
Middle Aged
Obesity - epidemiology
Pilot Projects
Population Surveillance - methods
Prevalence
Risk factors
Russia
Sex Distribution
Young Adult
Abstract
Here, we report first results on the development of computational health information technology for monitoring chronic non-communicable diseases (NCDs) risks in Russia based on data of the large-scale ongoing population survey in Health Centers (HCs). The technology involve algorithms for automated raw data process and generation of joint database, tools for data standardization and visualization, the assessment of risks, and other components. The data on physical status of Russians, including height, weight, and BMI are provided and compared with Belgian (1835), Swiss (2002), and US (1988-1994) reference datasets. The age-standardized prevalence of obesity in 5-85 years-old Russians according to the conventional WHO criteria was found to be high (18.9% in males and 26.7% in females) and varied significantly across federal subjects of Russia thus suggesting an importance of the Russian NCDs risks monitoring system for planning and evaluation of the effectiveness of preventive and therapeutic measures.
PubMed ID
25000064 View in PubMed
Less detail

Dictionary construction and identification of possible adverse drug events in Danish clinical narrative text.

https://arctichealth.org/en/permalink/ahliterature113635
Source
J Am Med Inform Assoc. 2013 Sep-Oct;20(5):947-53
Publication Type
Article
Author
Robert Eriksson
Peter Bjødstrup Jensen
Sune Frankild
Lars Juhl Jensen
Søren Brunak
Author Affiliation
Department of Disease Systems Biology, Faculty of Health and Medical Sciences, NNF Center for Protein Research, University of Copenhagen, Copenhagen, Denmark.
Source
J Am Med Inform Assoc. 2013 Sep-Oct;20(5):947-53
Language
English
Publication Type
Article
Keywords
Data Mining - methods
Denmark
Dictionaries, Medical
Drug-Related Side Effects and Adverse Reactions
Electronic Health Records
Humans
Narration
Abstract
Drugs have tremendous potential to cure and relieve disease, but the risk of unintended effects is always present. Healthcare providers increasingly record data in electronic patient records (EPRs), in which we aim to identify possible adverse events (AEs) and, specifically, possible adverse drug events (ADEs).
Based on the undesirable effects section from the summary of product characteristics (SPC) of 7446 drugs, we have built a Danish ADE dictionary. Starting from this dictionary we have developed a pipeline for identifying possible ADEs in unstructured clinical narrative text. We use a named entity recognition (NER) tagger to identify dictionary matches in the text and post-coordination rules to construct ADE compound terms. Finally, we apply post-processing rules and filters to handle, for example, negations and sentences about subjects other than the patient. Moreover, this method allows synonyms to be identified and anatomical location descriptions can be merged to allow appropriate grouping of effects in the same location.
The method identified 1 970 731 (35 477 unique) possible ADEs in a large corpus of 6011 psychiatric hospital patient records. Validation was performed through manual inspection of possible ADEs, resulting in precision of 89% and recall of 75%.
The presented dictionary-building method could be used to construct other ADE dictionaries. The complication of compound words in Germanic languages was addressed. Additionally, the synonym and anatomical location collapse improve the method.
The developed dictionary and method can be used to identify possible ADEs in Danish clinical narratives.
Notes
Cites: J Am Med Inform Assoc. 2010 Jan-Feb;17(1):19-2420064797
Cites: Nat Biotechnol. 2009 Jun;27(6):508-1019513049
Cites: Pharmacoepidemiol Drug Saf. 2010 Sep;19(9):901-1020623513
Cites: J Am Med Inform Assoc. 2010 Sep-Oct;17(5):507-1320819853
Cites: Nucleic Acids Res. 2011 Jan;39(Database issue):D507-1321030441
Cites: Pharmacoepidemiol Drug Saf. 2011 Jun;20(6):626-3421384463
Cites: PLoS Comput Biol. 2011 Aug;7(8):e100214121901084
Cites: J Am Med Inform Assoc. 2011 Dec;18 Suppl 1:i144-921946242
Cites: J Am Med Inform Assoc. 2001 May-Jun;8(3):254-6611320070
Cites: J Biomed Inform. 2001 Aug;34(4):249-6111977807
Cites: J Am Med Inform Assoc. 2003 Jul-Aug;10(4):339-5012668691
Cites: BMJ. 2004 Jul 3;329(7456):15-915231615
Cites: J Am Med Inform Assoc. 1994 Mar-Apr;1(2):161-747719797
Cites: Drug Saf. 1999 Feb;20(2):109-1710082069
Cites: Drug Saf. 2006;29(5):385-9616689555
Cites: BMC Med Inform Decis Mak. 2006;6:3016872495
Cites: JAMA. 2006 Oct 18;296(15):1858-6617047216
Cites: Yearb Med Inform. 2008;:128-4418660887
Cites: J Biomed Inform. 2010 Aug;43(4):595-60120362071
PubMed ID
23703825 View in PubMed
Less detail

EU-ADR healthcare database network vs. spontaneous reporting system database: preliminary comparison of signal detection.

https://arctichealth.org/en/permalink/ahliterature101665
Source
Stud Health Technol Inform. 2011;166:25-30
Publication Type
Article
Date
2011
Author
Gianluca Trifirò
Vaishali Patadia
Martijn J Schuemie
Preciosa M Coloma
Rosa Gini
Ron Herings
Julia Hippisley-Cox
Giampiero Mazzaglia
Carlo Giaquinto
Lorenza Scotti
Lars Pedersen
Paul Avillach
Miriam C J M Sturkenboom
Johan van der Lei
Eu-Adr Group
Author Affiliation
Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands. g.trifiro@erasmusmc.nl
Source
Stud Health Technol Inform. 2011;166:25-30
Date
2011
Language
English
Publication Type
Article
Keywords
Adverse Drug Reaction Reporting Systems - organization & administration
Data Mining - methods
Databases, Factual - statistics & numerical data
Drug Toxicity - epidemiology
Europe
Humans
Medical Records Systems, Computerized - statistics & numerical data
United States
United States Food and Drug Administration
World Health Organization
Abstract
The EU-ADR project aims to exploit different European electronic healthcare records (EHR) databases for drug safety signal detection. In this paper we report the preliminary results concerning the comparison of signal detection between EU-ADR network and two spontaneous reporting databases, the Food and Drug Administration and World Health Organization databases. EU-ADR data sources consist of eight databases in four countries (Denmark, Italy, Netherlands, and United Kingdom) that are virtually linked through distributed data network. A custom-built software (Jerboa©) elaborates harmonized input data that are produced locally and generates aggregated data which are then stored in a central repository. Those data are subsequently analyzed through different statistics (i.e. Longitudinal Gamma Poisson Shrinker). As potential signals, all the drugs that are associated to six events of interest (bullous eruptions - BE, acute renal failure - ARF, acute myocardial infarction - AMI, anaphylactic shock - AS, rhabdomyolysis - RHABD, and upper gastrointestinal bleeding - UGIB) have been detected via different data mining techniques in the two systems. Subsequently a comparison concerning the number of drugs that could be investigated and the potential signals detected for each event in the spontaneous reporting systems (SRSs) and EU-ADR network was made. SRSs could explore, as potential signals, a larger number of drugs for the six events, in comparison to EU-ADR (range: 630-3,393 vs. 87-856), particularly for those events commonly thought to be potentially drug-induced (i.e. BE: 3,393 vs. 228). The highest proportion of signals detected in SRSs was found for BE, ARF and AS, while for ARF, and UGIB in EU-ADR. In conclusion, it seems that EU-ADR longitudinal database network may complement traditional spontaneous reporting system for signal detection, especially for those adverse events that are frequent in general population and are not commonly thought to be drug-induced. The methodology for signal detection in EU-ADR is still under development and testing phase.
PubMed ID
21685607 View in PubMed
Less detail

Exploring the social determinants of mental health service use using intersectionality theory and CART analysis.

https://arctichealth.org/en/permalink/ahliterature256970
Source
J Epidemiol Community Health. 2014 Feb;68(2):145-50
Publication Type
Article
Date
Feb-2014
Author
John Cairney
Scott Veldhuizen
Simone Vigod
David L Streiner
Terrance J Wade
Paul Kurdyak
Author Affiliation
Departments of Family Medicine, Psychiatry & Behavioural Neurosciences, and Kinesiology, McMaster University, , Hamilton, Ontario, Canada.
Source
J Epidemiol Community Health. 2014 Feb;68(2):145-50
Date
Feb-2014
Language
English
Publication Type
Article
Keywords
Adult
Canada - epidemiology
Data Mining - methods
Female
Health Care Surveys
Humans
Male
Mental Disorders - epidemiology - therapy
Mental Health Services - utilization
Middle Aged
Models, Theoretical
Patient Acceptance of Health Care - ethnology - statistics & numerical data
Poverty Areas
Regression Analysis
Rural Population
Social Class
Social Determinants of Health
Young Adult
Abstract
Fewer than half of individuals with a mental disorder seek formal care in a given year. Much research has been conducted on the factors that influence service use in this population, but the methods generally used cannot easily identify the complex interactions that are thought to exist. In this paper, we examine predictors of subsequent service use among respondents to a population health survey who met criteria for a past-year mood, anxiety or substance-related disorder.
To determine service use, we use an administrative database including all physician consultations in the period of interest. To identify predictors, we use classification tree (CART) analysis, a data mining technique with the ability to identify unsuspected interactions. We compare results to those from logistic regression models.
We identify 1213 individuals with past-year disorder. In the year after the survey, 24% (n=312) of these had a mental health-related physician consultation. Logistic regression revealed that age, sex and marital status predicted service use. CART analysis yielded a set of rules based on age, sex, marital status and income adequacy, with marital status playing a role among men and by income adequacy important among women. CART analysis proved moderately effective overall, with agreement of 60%, sensitivity of 82% and specificity of 53%.
Results highlight the potential of data-mining techniques to uncover complex interactions, and offer support to the view that the intersection of multiple statuses influence health and behaviour in ways that are difficult to identify with conventional statistics. The disadvantages of these methods are also discussed.
PubMed ID
24098046 View in PubMed
Less detail

Functionality of Triggers for Epilepsy Patients Assessed by Text and Data Mining of Medical and Nursing Records.

https://arctichealth.org/en/permalink/ahliterature281933
Source
Stud Health Technol Inform. 2016;225:128-32
Publication Type
Article
Date
2016
Author
Eija Kivekäs
Ulla-Mari Kinnunen
Pekka Paananen
Reetta Kälviäinen
Kaisa Haatainen
Kaija Saranto
Source
Stud Health Technol Inform. 2016;225:128-32
Date
2016
Language
English
Publication Type
Article
Keywords
Causality
Data Mining - methods
Decision Support Systems, Clinical - organization & administration
Electronic Health Records - statistics & numerical data
Epilepsy - diagnosis - epidemiology - prevention & control
Finland - epidemiology
Humans
Machine Learning
Medical Errors - prevention & control - statistics & numerical data
Natural Language Processing
Nursing Records - statistics & numerical data
Patient Safety
Prognosis
Reproducibility of Results
Risk Assessment - methods
Sensitivity and specificity
Terminology as Topic
Abstract
A trigger is a powerful tool for identifying adverse events to measure the level of any kind of harm caused in patient care. Studies with epilepsy patients have illustrated that using triggers as a methodology with data mining may increase patient well-being. The purpose of this study is to test the functionality and validity of the previously defined triggers to describe the status of epilepsy patient's well-being. In both medical and nursing data, the triggers described patients' well-being comprehensively. The narratives showed that there was overlapping in triggers. The preliminary results of triggers encourage us to develop some reminders to the documentation of epilepsy patient well-being. These provide healthcare professionals with further and more detailed information when necessary.
PubMed ID
27332176 View in PubMed
Less detail

19 records – page 1 of 2.