Investigation of decision making issues in the use of current clinical information systems

Clinical information systems have become important tools in contemporary clinical patient care. However, there is a question of whether the current clinical information systems are able to effectively support clinicians in decision making processes. We conducted a survey to identify some of the decision making issues related to the use of existing clinical information systems. The survey was conducted among the end users of the cardiac surgery unit, quality and safety unit, intensive care unit and clinical costing unit at The Prince Charles Hospital (TPCH). Based on the survey results and reviewed literature, it was identified that support from the current information systems for decision-making is limited. Also, survey results showed that the majority of respondents considered lack in data integration to be one of the major issues followed by other issues such as limited access to various databases, lack of time and lack in efficient reporting and analysis tools. Furthermore, respondents pointed out that data quality is an issue and the three major data quality issues being faced are lack of data completeness, lack in consistency and lack in data accuracy. Conclusion: Current clinical information systems support for the decision-making processes in Cardiac Surgery in this institution is limited and this could be addressed by integrating isolated clinical information systems.

Exploiting SNOMED CT concepts and relationships for clinical information retrieval : Australian e-Health Research Centre and Queensland University of Technology at the TREC 2012 Medical Track

The Australian e-Health Research Centre and Queensland University of Technology recently participated in the TREC 2012 Medical Records Track. This paper reports on our methods, results and experience using an approach that exploits the concept and inter-concept relationships defined in the SNOMED CT medical ontology. Our concept-based approach is intended to overcome specific challenges in searching medical records, namely vocabulary mismatch and granularity mismatch. Queries and documents are transformed from their term-based originals into medical concepts as defined by the SNOMED CT ontology, this is done to tackle vocabulary mismatch. In addition, we make use of the SNOMED CT parent-child `is-a' relationships between concepts to weight documents that contained concept subsumed by the query concepts; this is done to tackle the problem of granularity mismatch. Finally, we experiment with other SNOMED CT relationships besides the is-a relationship to weight concepts related to query concepts. Results show our concept-based approach performed significantly above the median in all four performance metrics. Further improvements are achieved by the incorporation of weighting subsumed concepts, overall leading to improvement above the median of 28% infAP, 10% infNDCG, 12% R-prec and 7% Prec@10. The incorporation of other relations besides is-a demonstrated mixed results, more research is required to determined which SNOMED CT relationships are best employed when weighting related concepts.

Understanding negation and family history to improve clinical information retrieval

We present a study to understand the effect that negated terms (e.g., "no fever") and family history (e.g., "family history of diabetes") have on searching clinical records. Our analysis is aimed at devising the most effective means of handling negation and family history. In doing so, we explicitly represent a clinical record according to its different content types: negated, family history and normal content; the retrieval model weights each of these separately. Empirical evaluation shows that overall the presence of negation harms retrieval effectiveness while family history has little effect. We show negation is best handled by weighting negated content (rather than the common practise of removing or replacing it). However, we also show that many queries benefit from the inclusion of negated content and that negation is optimally handled on a per-query basis. Additional evaluation shows that adaptive handing of negated and family history content can have significant benefits.

External knowledge and query strategies in active learning: A study in clinical information extraction

This paper presents a new active learning query strategy for information extraction, called Domain Knowledge Informativeness (DKI). Active learning is often used to reduce the amount of annotation effort required to obtain training data for machine learning algorithms. A key component of an active learning approach is the query strategy, which is used to iteratively select samples for annotation. Knowledge resources have been used in information extraction as a means to derive additional features for sample representation. DKI is, however, the first query strategy that exploits such resources to inform sample selection. To evaluate the merits of DKI, in particular with respect to the reduction in annotation effort that the new query strategy allows to achieve, we conduct a comprehensive empirical comparison of active learning query strategies for information extraction within the clinical domain. The clinical domain was chosen for this work because of the availability of extensive structured knowledge resources which have often been exploited for feature generation. In addition, the clinical domain offers a compelling use case for active learning because of the necessary high costs and hurdles associated with obtaining annotations in this domain. Our experimental findings demonstrated that 1) amongst existing query strategies, the ones based on the classification model’s confidence are a better choice for clinical data as they perform equally well with a much lighter computational load, and 2) significant reductions in annotation effort are achievable by exploiting knowledge resources within active learning query strategies, with up to 14% less tokens and concepts to manually annotate than with state-of-the-art query strategies.

Analysis of word embeddings and sequence features for clinical information extraction

This study investigates the use of unsupervised features derived from word embedding approaches and novel sequence representation approaches for improving clinical information extraction systems. Our results corroborate previous findings that indicate that the use of word embeddings significantly improve the effectiveness of concept extraction models; however, we further determine the influence that the corpora used to generate such features have. We also demonstrate the promise of sequence-based unsupervised features for further improving concept extraction.

Integration of clinical information systems in Saudi Arabian health care contexts: A grounded theory exploration

This research examined the implementation of clinical information system technology in a large Saudi Arabian health care organisation. The research was underpinned by symbolic interactionism and grounded theory methods informed data collection and analysis. Observations, a review of policy documents and 38 interviews with registered nurses produced in-depth data. Analysis generated three abstracted concepts that explained how imported technology increased practice and health care complexity rather than enhance quality patient care. The core category, Disseminating Change, also depicted a hierarchical and patriarchal culture that shaped the implementation process at the levels of government, organisation and the individual.

Evaluation of coronary angiographic projections to balance the clinical yield with the radiation risk

Objective: Radiation safety principles dictate that imaging procedures should minimise the radiation risks involved, without compromising diagnostic performance. This study aims to define a core set of views that maximises clinical information yield for minimum radiation risk. Angiographers would supplement these views as clinically indicated. Methods: An algorithm was developed to combine published data detailing the quality of information derived for the major coronary artery segments through the use of a common set of views in angiography with data relating to the dose–area product and scatter radiation associated with these views. Results: The optimum view set for the left coronary system comprised four views: left anterior oblique (LAO) with cranial (Cr) tilt, shallow right anterior oblique (AP-RAO) with caudal (Ca) tilt, RAO with Ca tilt and AP-RAO with Cr tilt. For the right coronary system three views were identified: LAO with Cr tilt, RAO and AP-RAO with Cr tilt. An alternative left coronary view set including a left lateral achieved minimally superior efficiency (,5%), but with an ,8% higher radiation dose to the patient and 40% higher cardiologist dose. Conclusion: This algorithm identifies a core set of angiographic views that optimises the information yield and minimises radiation risk. This basic data set would be supplemented by additional clinically determined views selected by the angiographer for each case. The decision to use additional views for diagnostic angiography and interventions would be assisted by referencing a table of relative radiation doses for the views being considered.

Information Accountability of Healthcare Big Data

Huge amount of data are generated from a variety of information sources in healthcare while the data sources originate from a veracity of clinical information systems and corporate data warehouses. The data derived from the above data sources are used for analysis and trending purposes thus playing an influential role as a real time decision-making tool. The unstructured, narrative data provided by these data sources qualify as healthcare big-data and researchers argue that the application of big-data in healthcare might enable the accountability and efficiency.

Medical free-text to concept mapping as an information retrieval problem

Concept mapping involves determining relevant concepts from a free-text input, where concepts are defined in an external reference ontology. This is an important process that underpins many applications for clinical information reporting, derivation of phenotypic descriptions, and a number of state-of-the-art medical information retrieval methods. Concept mapping can be cast into an information retrieval (IR) problem: free-text mentions are treated as queries and concepts from a reference ontology as the documents to be indexed and retrieved. This paper presents an empirical investigation applying general-purpose IR techniques for concept mapping in the medical domain. A dataset used for evaluating medical information extraction is adapted to measure the effectiveness of the considered IR approaches. Standard IR approaches used here are contrasted with the effectiveness of two established benchmark methods specifically developed for medical concept mapping. The empirical findings show that the IR approaches are comparable with one benchmark method but well below the best benchmark.

The clinical reasoning characteristics of diagnostic experts

The aim of this study was to identify and describe the clinical reasoning characteristics of diagnostic experts. A group of 21 experienced general practitioners were asked to complete the Diagnostic Thinking Inventory (DTI) and a set of 10 clinical reasoning problems (CRPs) to evaluate their clinical reasoning. Both the DTI and the CRPs were scored, and the CRP response patterns of each GP examined in terms of the number and type of errors contained in them. Analysis of these data showed that six GPs were able to reach the correct diagnosis using significantly less clinical information than their colleagues. These GPs also made significantly fewer interpretation errors but scored lower on both the DTI and the CRPs. Additionally, this analysis showed that more than 20% of misdiagnoses occurred despite no errors being made in the identification and interpretation of relevant clinical information. These results indicate that these six GPs diagnose efficiently, effectively and accurately using relatively few clinical data and can therefore be classified as diagnostic experts. They also indicate that a major cause of misdiagnoses is failure to properly integrate clinical data. We suggest that increased emphasis on this step in the reasoning process should prove beneficial to the development of clinical reasoning skill in undergraduate medical students.

What health problems overcrowd hospital emergency departments in Queensland and has this changed over time? A case study of two hospitals in Queensland 2001 - 2009

Aim: to describe what health problems patients attending emergency department with and whether this changed over time. Methods: Electronic data was retrieved from EDIS (Emergency Department Information System) and HBCIS (Hospital Based Clinical Information System) in two hospitals in Queensland in the period 2001-2009. The ICD-10 code of patient's diagnosis was then extrapolated and then group into ICD-10 chapters, such that the health problem can be presented. Results: Among the specific health problems, Chapter XIX 'Injury and poisoning' ranked number one consistently (ranging from 22.1% to 31.2% of the total presentations) in both the urban and remote hospitals in Queensland. The top ten specific presenting health problems in both the urban and remote hospital include Chapter XI 'Digestive system', Chapter XIV 'Genitourinary system', Chapter IX 'Circulatory system', and Chapter XIII 'Musculoskeletal system and connective tissue'. Chapter X 'Respiratory system' made the top ten presenting Chapters in both hospitals, but ranked much higher (number four consistently for the eight years, ranging from 6.8% to 8.3%) in the remote hospital. Chapter XV 'Pregnancy childbirth and puerperium' made to the top ten in the urban hospital only while Chapter XII 'Skin and subcutaneous tissue', Chapter I 'Infectious and parasitic diseases' made the top ten in the remote hospital only. Conclusion: The number one health problem presenting to both the urban and remote hospitals in Queensland is Chapter XIX 'Injury and poisoning', and it did not change in the period 211 - 2009.

How to Improve Cardiac Surgery Decision Making? In Data Warehousing Perspective

The health system is one sector dealing with very large amount of complex data. Many healthcare organisations struggle to utilise these volumes of health data effectively and efficiently. Therefore, there is a need for very effective system to capture, collate and distribute this health data. There are number of technologies have been identified to integrate data from different sources. Data warehousing is one technology can be used to manage clinical data in the healthcare. This paper addresses how data warehousing assist to improve cardiac surgery decision making. This research used the cardiac surgery unit at the Prince Charles Hospital (TPCH) as the case study. In order to deal with other units efficiently, it is important to integrate disparate data to a single point interrogation. We propose implementing a data warehouse for the cardiac surgery unit at TPCH. The data warehouse prototype developed using SAS enterprise data integration studio 4.2 and data was analysed using SAS enterprise edition 4.3. This improves access to integrated clinical and financial data with, improved framing of data to the clinical context, giving potentially better informed decision making for both improved management and patient care.

The Large Allen Cognitive Level Screen as an indicator for medication adherence among adults accessing community mental health services

Background: Medication remains the cornerstone treatment for mental illness. Cognition is one of the strongest predictors of non-adherence. The aim of this preliminary investigation was to examine the association between the Large Allen Cognitive Level Screen (LACLS) and medication adherence among a small sample of mental health service users to determine whether the LACLS has potential as a screening tool for capacity to manage medication regimens. Method: Demographic and clinical information was collected from a small sample of people who had recently accessed community mental health services. Participants then completed the LACLS and the Medication Adherence Rating Scale (MARS) at a single time point. The strength of association between the LACLS and MARS was examined using Spearman rank-order correlation. Results: A strong positive correlation between the LACLS and medication adherence (r = 0.71, p = 0.01) was evident. No participants reported the use of medication aids despite evidence of impaired cognitive functioning. Conclusion: This investigation has provided the first empirical evidence indicating that the LACLS may have utility as a screening instrument for capacity to manage medication adherence among this population. While promising, this finding should be interpreted with caveats given its preliminary nature.

A comparative analysis of risk stratification tools for emergency department patients with chest pain

Background: Appropriate disposition of emergency department (ED) patients with chest pain is dependent on clinical evaluation of risk. A number of chest pain risk stratification tools have been proposed. The aim of this study was to compare the predictive performance for major adverse cardiac events (MACE) using risk assessment tools from the National Heart Foundation of Australia (HFA), the Goldman risk score and the Thrombolysis in Myocardial Infarction risk score (TIMI RS). Methods: This prospective observational study evaluated ED patients aged ≥30 years with non-traumatic chest pain for which no definitive non-ischemic cause was found. Data collected included demographic and clinical information, investigation findings and occurrence of MACE by 30 days. The outcome of interest was the comparative predictive performance of the risk tools for MACE at 30 days, as analyzed by receiver operator curves (ROC). Results: Two hundred eighty-one patients were studied; the rate of MACE was 14.1%. Area under the curve (AUC) of the HFA, TIMI RS and Goldman tools for the endpoint of MACE was 0.54, 0.71 and 0.67, respectively, with the difference between the tools in predictive ability for MACE being highly significant [chi2 (3) = 67.21, N = 276, p < 0.0001]. Conclusion: The TIMI RS and Goldman tools performed better than the HFA in this undifferentiated ED chest pain population, but selection of cutoffs balancing sensitivity and specificity was problematic. There is an urgent need for validated risk stratification tools specific for the ED chest pain population.

Towards a smart cancer registry

Aims Pathology notification for a Cancer Registry is regarded as the most valid information for the confirmation of a diagnosis of cancer. In view of the importance of pathology data, an automatic medical text analysis system (Medtex) is being developed to perform electronic Cancer Registry data extraction and coding of important clinical information embedded within pathology reports. Methods The system automatically scans HL7 messages received from a Queensland pathology information system and analyses the reports for terms and concepts relevant to a cancer notification. A multitude of data items for cancer notification such as primary site, histological type, stage, and other synoptic data are classified by the system. The underlying extraction and classification technology is based on SNOMED CT1 2. The Queensland Cancer Registry business rules3 and International Classification of Diseases – Oncology – Version 34 have been incorporated. Results The cancer notification services show that the classification of notifiable reports can be achieved with sensitivities of 98% and specificities of 96%5, while the coding of cancer notification items such as basis of diagnosis, histological type and grade, primary site and laterality can be extracted with an overall accuracy of 80%6. In the case of lung cancer staging, the automated stages produced were accurate enough for the purposes of population level research and indicative staging prior to multi-disciplinary team meetings2 7. Medtex also allows for detailed tumour stream synoptic reporting8. Conclusions Medtex demonstrates how medical free-text processing could enable the automation of some Cancer Registry processes. Over 70% of Cancer Registry coding resources are devoted to information acquisition. The development of a clinical decision support system to unlock information from medical free-text could significantly reduce costs arising from duplicated processes and enable improved decision support, enhancing efficiency and timeliness of cancer information for Cancer Registries.