Fracture risk (FRISK) score : Geelong Osteoporosis Study

Purpose: To develop and evaluate a fracture risk (FRISK) score based on multiple-site bone mineral density (BMD) measurements and other risk factors, to enable prediction of future fracture occurrence.

Materials and Methods: All participants gave written informed consent, and the study was approved by the Barwon Health Research and Ethics Advisory Committee. BMD was measured at the femoral neck and spine in two concurrently recruited groups: women 60 years of age or older who had sustained a low-trauma fracture of the hip, spine, humerus or distal forearm during a 2-year ascertainment period (n = 231; mean age, 74 years ± 7 [standard deviation]) and a population-based random sample of women who had not sustained a fracture during the recruitment period (n = 448; mean age, 72 years ± 8). Falls in the previous year and the number of self-reported fractures in adult life were recorded. Coefficients of a multiple logistic regression model were used as weightings for a combined model. A longitudinal population-based sample was used to assess the fracture risk equation (n = 600; median age, 74 years; interquartile range, 67–82 years).

Results: The FRISK score was obtained from the following equation: 9.304 − 4.735BMDSP − 4.530BMDFN + 1.127FS + 0.344NPF + 0.037W, where BMDSP is spinal BMD (in grams per square centimeter), BMDFN is femoral neck BMD, FS is falls score, NPF is number of previous fractures, and W is weight (in kilograms). The FRISK score successfully predicted 75% of fractures 2 years after baseline measurements in subjects in the longitudinal study with 68% specificity.

Conclusion: This study resulted in the derivation of a fracture risk score that successfully predicted 75% of fractures 2 years after baseline.

Using clinical trial data and linked administrative health data to reduce the risk of adverse events associated with the uptake of newly released drugs by older Australians : a model process

Background
The study was undertaken to evaluate the contribution of a process which uses clinical trial data plus linked de-identified administrative health data to forecast potential risk of adverse events associated with the use of newly released drugs by older Australian patients.

Methods
The study uses publicly available data from the clinical trials of a newly released drug to ascertain which patient age groups, gender, comorbidities and co-medications were excluded in the trials. It then uses linked de-identified hospital morbidity and medications dispensing data to investigate the comorbidities and co-medications of patients who suffer from the target morbidity of the new drug and who are the likely target population for the drug. The clinical trial information and the linked morbidity and medication data are compared to assess which patient groups could potentially be at risk of an adverse event associated with use of the new drug.

Results
Applying the model in a retrospective real-world scenario identified that the majority of the sample group of Australian patients aged 65 years and over with the target morbidity of the newly released COX-2-selective NSAID rofecoxib also suffered from a major morbidity excluded in the trials of that drug, indicating a substantial potential risk of adverse events amongst those patients. This risk was borne out in post-release morbidity and mortality associated with use of that drug.

Conclusions
Clinical trial data and linked administrative health data can together support a prospective assessment of patient groups who could be at risk of an adverse event if they are prescribed a newly released drug in the context of their age, gender, comorbidities and/or co-medications. Communication of this independent risk information to prescribers has the potential to reduce adverse events in the period after the release of the new drug, which is when the risk is greatest.

Note: The terms 'adverse drug reaction' and 'adverse drug event' have come to be used interchangeably in the current literature. For consistency, the authors have chosen to use the wider term 'adverse drug event' (ADE).

An agile IT security model for project risk assessment

There are two fundamental challenges in effectively performing security risk assessment in today's IT projects.The first is the project manager's need to know what IT security risks face the project before the project begins. At this stage IT security staff are unable to answer this question without first knowing the system requirements for the project which are yet to be defined. Second organisations that deal with a large project throughput each year find the current IT security risk assessment process to be tedious and expensive, especially when the same process has to be repeated for each individual project. This also makes it difficult for an organisation to prioritise which projects require more investment in IT security in order to fit within budget constraints. This paper presents a conceptual model that is based on an agile approach to alleviate these challenges. We do this by first analysing two online database resources of vulnerabilities by comparing them to each other, and then compare them to the agile criteria of the conceptual model which we define. The conceptual model is then presented and an example is given of how it can be applied to an actual project. We then briefly discuss what further work needs to be done to implement the conceptual model and validate it against an existing IT project.

Modelling SME credit risk : a Thai empirical evidence

This paper develops and tests a model to predict small and medium enterprise (SME) financial distress based on empirical evidence from Thailand. A sample comprising 198 financial statements of non-financially distressed and 68 statements of financially distressed SMEs were used. A parametric t-test was conducted to establish differences between financial characteristics of the two groups of SMEs.

Results show statistically significant differences (t values significant at .001) between the two groups of SMEs in the financial ratios used for the study. Discriminant analysis was then conducted to develop a model for predicting the likelihood of an SME experiencing financial distress.

The model hits an accuracy level of 97%, which compares favourably with the probability of accurate classification by chance (i.e., 65% after adjusting for the unequal sample sizes of the two groups of SMEs). A test of the model with a new sample shows the validity of the model beyond the original sample, confirming that Thai SME financial distress is amenable to prediction to a statistically significant extent. The model is expected to serve SME managers and creditors in assessing financial health of SMEs before making important decisions. The results are also expected to inform policymakers in formulating economic policies concerning SMEs.

Validation and development of a clinical prediction rule in clinically suspected community-acquired pneumonia

To develop a mathematical model to predict the probability of having community-acquired pneumonia and to evaluate an already developed prediction rule that has not been validated in a clinical scenario.

Prediction of FLD of sheet metals based on crystal plasticity model

 In some advanced sheet metal forming processes such as the incremental forming process, a local fracture strain after necking is very important. In order to accurately predict necking and fracture phenomena, a crystal plasticity model is introduced in the finite element analysis of tensile tests. A tensile specimen is modeled by many grains that have their own crystalline orientation. And each of the grains is discretized by many elements. Using this analysis, necking behavior of a tensile specimen can be predicted without any initial imperfections. A damage model is also implemented to predict sudden drops of load carrying capacity after necking and to reflect the void nucleation and growth of the severely deformed region. From an analysis of the tensile test, the necking behavior is well predicted. Finally, analyses are carried out for various strain paths, and FLDs up to necking and fracture are predicted.

Characterization and prediction of issue-related risks in software projects

Identifying risks relevant to a software project and planning measures to deal with them are critical to the success of the project. Current practices in risk assessment mostly rely on high-level, generic guidance or the subjective judgements of experts. In this paper, we propose a novel approach to risk assessment using historical data associated with a software project. Specifically, our approach identifies patterns of past events that caused project delays, and uses this knowledge to identify risks in the current state of the project. A set of risk factors characterizing “risky” software tasks (in the form of issues) were extracted from five open source projects: Apache, Duraspace, JBoss, Moodle, and Spring. In addition, we performed feature selection using a sparse logistic regression model to select risk factors with good discriminative power. Based on these risk factors, we built predictive models to predict if an issue will cause a project delay. Our predictive models are able to predict both the risk impact (i.e. the extend of the delay) and the likelihood of a risk occurring. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 48%-81% precision, 23%-90% recall, 29%-71% F-measure, and 70%-92% Area Under the ROC Curve. Our predictive models also have low error rates: 0.39-0.75 for Macro-averaged Mean Cost-Error and 0.7-1.2 for Macro-averaged Mean Absolute Error.

Using clinical trial data and linked administrative health data to reduce the risk of adverse events associated with the uptake of newly released drugs by older Australians: a model process

BACKGROUND: The study was undertaken to evaluate the contribution of a process which uses clinical trial data plus linked de-identified administrative health data to forecast potential risk of adverse events associated with the use of newly released drugs by older Australian patients. METHODS: The study uses publicly available data from the clinical trials of a newly released drug to ascertain which patient age groups, gender, comorbidities and co-medications were excluded in the trials. It then uses linked de-identified hospital morbidity and medications dispensing data to investigate the comorbidities and co-medications of patients who suffer from the target morbidity of the new drug and who are the likely target population for the drug. The clinical trial information and the linked morbidity and medication data are compared to assess which patient groups could potentially be at risk of an adverse event associated with use of the new drug. RESULTS: Applying the model in a retrospective real-world scenario identified that the majority of the sample group of Australian patients aged 65 years and over with the target morbidity of the newly released COX-2-selective NSAID rofecoxib also suffered from a major morbidity excluded in the trials of that drug, indicating a substantial potential risk of adverse events amongst those patients. This risk was borne out in post-release morbidity and mortality associated with use of that drug. CONCLUSIONS: Clinical trial data and linked administrative health data can together support a prospective assessment of patient groups who could be at risk of an adverse event if they are prescribed a newly released drug in the context of their age, gender, comorbidities and/or co-medications. Communication of this independent risk information to prescribers has the potential to reduce adverse events in the period after the release of the new drug, which is when the risk is greatest.Note: The terms 'adverse drug reaction' and 'adverse drug event' have come to be used interchangeably in the current literature. For consistency, the authors have chosen to use the wider term 'adverse drug event' (ADE).

Stabilizing high-dimensional prediction models using feature graphs

We investigate feature stability in the context of clinical prognosis derived from high-dimensional electronic medical records. To reduce variance in the selected features that are predictive, we introduce Laplacian-based regularization into a regression model. The Laplacian is derived on a feature graph that captures both the temporal and hierarchic relations between hospital events, diseases, and interventions. Using a cohort of patients with heart failure, we demonstrate better feature stability and goodness-of-fit through feature graph stabilization.

Stabilizing l1-norm prediction models by supervised feature grouping

Emerging Electronic Medical Records (EMRs) have reformed the modern healthcare. These records have great potential to be used for building clinical prediction models. However, a problem in using them is their high dimensionality. Since a lot of information may not be relevant for prediction, the underlying complexity of the prediction models may not be high. A popular way to deal with this problem is to employ feature selection. Lasso and l1-norm based feature selection methods have shown promising results. But, in presence of correlated features, these methods select features that change considerably with small changes in data. This prevents clinicians to obtain a stable feature set, which is crucial for clinical decision making. Grouping correlated variables together can improve the stability of feature selection, however, such grouping is usually not known and needs to be estimated for optimal performance. Addressing this problem, we propose a new model that can simultaneously learn the grouping of correlated features and perform stable feature selection. We formulate the model as a constrained optimization problem and provide an efficient solution with guaranteed convergence. Our experiments with both synthetic and real-world datasets show that the proposed model is significantly more stable than Lasso and many existing state-of-the-art shrinkage and classification methods. We further show that in terms of prediction performance, the proposed method consistently outperforms Lasso and other baselines. Our model can be used for selecting stable risk factors for a variety of healthcare problems, so it can assist clinicians toward accurate decision making.