Search tips
Search criteria

Results 1-9 (9)

Clipboard (0)
more »
Year of Publication
Document Types
1.  Preparation of name and address data for record linkage using hidden Markov models 
Record linkage refers to the process of joining records that relate to the same entity or event in one or more data collections. In the absence of a shared, unique key, record linkage involves the comparison of ensembles of partially-identifying, non-unique data items between pairs of records. Data items with variable formats, such as names and addresses, need to be transformed and normalised in order to validly carry out these comparisons. Traditionally, deterministic rule-based data processing systems have been used to carry out this pre-processing, which is commonly referred to as "standardisation". This paper describes an alternative approach to standardisation, using a combination of lexicon-based tokenisation and probabilistic hidden Markov models (HMMs).
HMMs were trained to standardise typical Australian name and address data drawn from a range of health data collections. The accuracy of the results was compared to that produced by rule-based systems.
Training of HMMs was found to be quick and did not require any specialised skills. For addresses, HMMs produced equal or better standardisation accuracy than a widely-used rule-based system. However, acccuracy was worse when used with simpler name data. Possible reasons for this poorer performance are discussed.
Lexicon-based tokenisation and HMMs provide a viable and effort-effective alternative to rule-based systems for pre-processing more complex variably formatted data such as addresses. Further work is required to improve the performance of this approach with simpler data such as names. Software which implements the methods described in this paper is freely available under an open source license for other researchers to use and improve.
PMCID: PMC140019  PMID: 12482326
2.  Effects of systematic asymmetric discounting on physician-patient interactions: a theoretical framework to explain poor compliance with lifestyle counseling 
This study advances the use of a utility model to model physician-patient interactions from the perspectives of physicians and patients.
Presentation of the hypothesis
In cases involving acute care, patient counseling involves a relatively straightforward transfer of information from the physician to a patient. The patient has less information than the physician on the impact the condition and its treatment have on utility. In decisions involving lifestyle changes, the patient may have more information than the physician on his/her utility of consumption; moreover, differences in discounting future health may contribute significantly to differences between patients' preferences and physicians' recommendations.
Testing the hypothesis
The expectation of differences in internal discount rate between patients and their physicians is discussed.
Implications of the hypothesis
This utility model provides a conceptual basis for the finding that educational approaches alone may not effect changes in patient behavior and suggests other economic variables that could be targeted in the attempt to produce healthier behavior.
PMCID: PMC140018  PMID: 12445325
utility; patient education; counseling; risk behavior
3.  The quality case for information technology in healthcare 
As described in the Institute of Medicine's Crossing the Quality Chasm report, the quality of health care in the U.S. today leaves much to be desired.
One major opportunity for improving quality relates to increasing the use of information technology, or IT. Health care organizations currently invest less in IT than in any other information-intensive industry, and not surprisingly current systems are relatively primitive, compared with industries such as banking or aviation. Nonetheless, a number of organizations have demonstrated that quality can be substantially improved in a variety of ways if IT use is increased in ways that improve care. Specifically, computerization of processes that are error-prone and computerized decision support may substantially improve both efficiency and quality, as well as dramatically facilitate quality measurement. This report discusses the current levels of IT and quality in health care, how quality improvement and management are currently done, the evidence that more IT might be helpful, a vision of the future, and the barriers to getting there.
This report suggests that there are five key policy domains that need to be addressed: standards, incentives, security and confidentiality, professional involvement, and research, with financial incentives representing the single most important lever.
PMCID: PMC137695  PMID: 12396233
4.  Medical informatics in an undergraduate curriculum: a qualitative study 
There is strong support for educating physicians in medical informatics, and the benefits of such education have been clearly identified. Despite this, North American medical schools do not routinely provide education in medical informatics.
We conducted a qualitative study to identify issues facing the introduction of medical informatics into an undergraduate medical curriculum. Nine key informants at the University of Toronto medical school were interviewed, and their responses were transcribed and analyzed to identify consistent themes.
The field of medical informatics was not clearly understood by participants. There was, however, strong support for medical informatics education, and the benefits of such education were consistently identified. In the curriculum we examined, medical informatics education was delivered informally and inconsistently through mainly optional activities. Issues facing the introduction of medical informatics education included: an unclear understanding of the discipline; faculty and administrative detractors and, the dense nature of the existing undergraduate medical curriculum.
The identified issues may present serious obstacles to the introduction of medical informatics education into an undergraduate medicine curriculum, and we present some possible strategies for addressing these issues.
PMCID: PMC126228  PMID: 12207827
5.  Interactive decision support in hepatic surgery 
Hepatic surgery is characterized by complicated operations with a significant peri- and postoperative risk for the patient. We developed a web-based, high-granular research database for comprehensive documentation of all relevant variables to evaluate new surgical techniques.
To integrate this research system into the clinical setting, we designed an interactive decision support component. The objective is to provide relevant information for the surgeon and the patient to assess preoperatively the risk of a specific surgical procedure.
Based on five established predictors of patient outcomes, the risk assessment tool searches for similar cases in the database and aggregates the information to estimate the risk for an individual patient.
The physician can verify the analysis and exclude manually non-matching cases according to his expertise. The analysis is visualized by means of a Kaplan-Meier plot.
To evaluate the decision support component we analyzed data on 165 patients diagnosed with hepatocellular carcinoma (period 1996–2000). The similarity search provides a two-peak distribution indicating there are groups of similar patients and singular cases which are quite different to the average. The results of the risk estimation are consistent with the observed survival data, but must be interpreted with caution because of the limited number of matching reference cases.
Critical issues for the decision support system are clinical integration, a transparent and reliable knowledge base and user feedback.
PMCID: PMC113749  PMID: 12003639
6.  Selecting information technology for physicians' practices: a cross-sectional study 
Many physicians are transitioning from paper to electronic formats for billing, scheduling, medical charts, communications, etc. The primary objective of this research was to identify the relationship (if any) between the software selection process and the office staff's perceptions of the software's impact on practice activities.
A telephone survey was conducted with office representatives of 407 physician practices in Oregon who had purchased information technology. The respondents, usually office managers, answered scripted questions about their selection process and their perceptions of the software after implementation.
Multiple logistic regression revealed that software type, selection steps, and certain factors influencing the purchase were related to whether the respondents felt the software improved the scheduling and financial analysis practice activities. Specifically, practices that selected electronic medical record or practice management software, that made software comparisons, or that considered prior user testimony as important were more likely to have perceived improvements in the scheduling process than were other practices. Practices that considered value important, that did not consider compatibility important, that selected managed care software, that spent less than $10,000, or that provided learning time (most dramatic increase in odds ratio, 8.2) during implementation were more likely to perceive that the software had improved the financial analysis process than were other practices.
Perhaps one of the most important predictors of improvement was providing learning time during implementation, particularly when the software involves several practice activities. Despite this importance, less than half of the practices reported performing this step.
PMCID: PMC102764  PMID: 11936958
7.  The equivalence of numbers: The social value of avoiding health decline: An experimental web-based study 
Health economic analysis aimed at informing policy makers and supporting resource allocation decisions has to evaluate not only improvements in health but also avoided decline. Little is known however, whether the "direction" in which changes in health are experienced is important for the public in prioritizing among patients. This experimental study investigates the social value people place on avoiding (further) health decline when directly compared to curative treatments in resource allocation decisions.
127 individuals completed an interactive survey that was published in the World Wide Web. They were confronted with a standard gamble (SG) and three person trade-off tasks, either comparing improvements in health (PTO-Up), avoided decline (PTO-Down), or both, contrasting health changes of equal magnitude differing in the direction in which they are experienced (PTO-WAD). Finally, a direct priority ranking of various interventions was obtained.
Participants strongly prioritized improving patients' health rather than avoiding decline. The mean substitution rate between health improvements and avoided decline (WAD) ranged between 0.47 and 0.64 dependent on the intervention. Weighting PTO values according to the direction in which changes in health are experienced improved their accuracy in predicting a direct prioritization ranking. Health state utilities obtained by the standard gamble method seem not to reflect social values in resource allocation contexts.
Results suggest that the utility of being cured of a given health state might not be a good approximation for the societal value of avoiding this health state, especially in cases of competition between preventive and curative interventions.
PMCID: PMC100787  PMID: 11879529
8.  Deconstructing patient centred communication and uncovering shared decision making: an observational study 
Patient centred communication (PCC) has been described as a method for doctor-patient communication. The principles of shared decision making (SDM) have been proposed more recently.
This study aimed to examine PCC and SDM empirically with respect to their mutual association, the variation in practitioners' working styles, and the associations with patient characteristics.
Sixty general practitioners recruited 596 adult patients who gave written consent to have their consultations videotaped. The tapes were assessed by two researchers, using a standardised instrument for global communication. For the purpose of this exploratory study, scales for PCC and SDM were based on subsamples of items in the MAAS.
The scales for PCC and SDM were weakly associated (Pearson correlation: 0.25). Physicians varied more on SDM than on PCC. The intracluster correlation of the PCC and SDM scales were, respectively, 0.34 and 0.19. However, hypotheses regarding associations with patient characteristics were not confirmed. Neither PCC nor SDM scores were related to patient gender, education, age, functional health status or existence of chronic conditions.
The study provides evidence that PCC and SDM can be differentiated and comprise approaches to communication between clinicians and patients which may be more clearly distinguished by further focused research and training developments.
PMCID: PMC65523  PMID: 11835698
9.  Prediction models in the design of neural network based ECG classifiers: A neural network and genetic programming approach 
Classification of the electrocardiogram using Neural Networks has become a widely used method in recent years. The efficiency of these classifiers depends upon a number of factors including network training. Unfortunately, there is a shortage of evidence available to enable specific design choices to be made and as a consequence, many designs are made on the basis of trial and error. In this study we develop prediction models to indicate the point at which training should stop for Neural Network based Electrocardiogram classifiers in order to ensure maximum generalisation.
Two prediction models have been presented; one based on Neural Networks and the other on Genetic Programming. The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop. Training and testing of the models was based on the results from 44 previously developed bi-group Neural Network classifiers, discriminating between Anterior Myocardial Infarction and normal patients.
Our results show that both approaches provide close fits to the training data; p = 0.627 and p = 0.304 for the Neural Network and Genetic Programming methods respectively. For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047).
The approaches provide reverse engineering solutions to the development of Neural Network based Electrocardiogram classifiers. That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.
PMCID: PMC65522  PMID: 11846893

Results 1-9 (9)