Use of generalised additive models to categorise continuous variables in clinical prediction

13 P.

Clinical prediction of occupational and non-specific low back pain

Non-specific Occupational Low Back Pain (NOLBP) is a health condition that generates a high absenteeism and disability. Due to multifactorial causes is difficult to determine accurate diagnosis and prognosis. The clinical prediction of NOLBP is identified as a series of models that integrate a multivariate analysis to determine early diagnosis, course, and occupational impact of this health condition. Objective: to identify predictor factors of NOLBP, and the type of material referred to in the scientific evidence and establish the scopes of the prediction. Materials and method: the title search was conducted in the databases PubMed, Science Direct, and Ebsco Springer, between1985 and 2012. The selected articles were classified through a bibliometric analysis allowing to define the most relevant ones. Results: 101 titles met the established criteria, but only 43 metthe purpose of the review. As for NOLBP prediction, the studies varied in relation to the factors for example: diagnosis, transition of lumbar pain from acute to chronic, absenteeism from work, disability and return to work. Conclusion: clinical prediction is considered as a strategic to determine course and prognostic of NOLBP, and to determine the characteristics that increase the risk of chronicity in workers with this health condition. Likewise, clinical prediction rules are tools that aim to facilitate decision making about the evaluation, diagnosis, prognosis and intervention for low back pain, which should incorporate risk factors of physical, psychological and social.

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.

Stable feature selection for clinical prediction: Exploiting ICD tree structure using Tree-Lasso

Modern healthcare is getting reshaped by growing Electronic Medical Records (EMR). Recently, these records have been shown of great value towards building clinical prediction models. In EMR data, patients' diseases and hospital interventions are captured through a set of diagnoses and procedures codes. These codes are usually represented in a tree form (e.g. ICD-10 tree) and the codes within a tree branch may be highly correlated. These codes can be used as features to build a prediction model and an appropriate feature selection can inform a clinician about important risk factors for a disease. Traditional feature selection methods (e.g. Information Gain, T-test, etc.) consider each variable independently and usually end up having a long feature list. Recently, Lasso and related l1-penalty based feature selection methods have become popular due to their joint feature selection property. However, Lasso is known to have problems of selecting one feature of many correlated features randomly. This hinders the clinicians to arrive at a stable feature set, which is crucial for clinical decision making process. In this paper, we solve this problem by using a recently proposed Tree-Lasso model. Since, the stability behavior of Tree-Lasso is not well understood, we study the stability behavior of Tree-Lasso and compare it with other feature selection methods. Using a synthetic and two real-world datasets (Cancer and Acute Myocardial Infarction), we show that Tree-Lasso based feature selection is significantly more stable than Lasso and comparable to other methods e.g. Information Gain, ReliefF and T-test. We further show that, using different types of classifiers such as logistic regression, naive Bayes, support vector machines, decision trees and Random Forest, the classification performance of Tree-Lasso is comparable to Lasso and better than other methods. Our result has implications in identifying stable risk factors for many healthcare problems and therefore can potentially assist clinical decision making for accurate medical prognosis.

Validation of the Asthma Predictive Index and comparison with simpler clinical prediction rules

Background The loose and stringent Asthma Predictive Indices (API), developed in Tucson, are popular rules to predict asthma in preschool children. To be clinically useful, they require validation in different settings. Objective To assess the predictive performance of the API in an independent population and compare it with simpler rules based only on preschool wheeze. Methods We studied 1954 children of the population-based Leicester Respiratory Cohort, followed up from age 1 to 10 years. The API and frequency of wheeze were assessed at age 3 years, and we determined their association with asthma at ages 7 and 10 years by using logistic regression. We computed test characteristics and measures of predictive performance to validate the API and compare it with simpler rules. Results The ability of the API to predict asthma in Leicester was comparable to Tucson: for the loose API, odds ratios for asthma at age 7 years were 5.2 in Leicester (5.5 in Tucson), and positive predictive values were 26% (26%). For the stringent API, these values were 8.2 (9.8) and 40% (48%). For the simpler rule early wheeze, corresponding values were 5.4 and 21%; for early frequent wheeze, 6.7 and 36%. The discriminative ability of all prediction rules was moderate (c statistic ≤ 0.7) and overall predictive performance low (scaled Brier score < 20%). Conclusion Predictive performance of the API in Leicester, although comparable to the original study, was modest and similar to prediction based only on preschool wheeze. This highlights the need for better prediction rules.

Prognostic clinical prediction rules to identify a low-risk pulmonary embolism: a systematic review and meta-analysis

Prognostic assessment is important for the management of patients with a pulmonary embolism (PE). A number of clinical prediction rules (CPRs) have been proposed for stratifying PE mortality risk. The aim of this systematic review was to assess the performance of prognostic CPRs in identifying a low-risk PE.

Improving the clinical prediction of psychosis by combining ultra-high risk criteria and cognitive basic symptoms

OBJECTIVE Cognitive impairments are regarded as a core component of schizophrenia. However, the cognitive dimension of psychosis is hardly considered by ultra-high risk (UHR) criteria. Therefore, we studied whether the combination of symptomatic UHR criteria and the basic symptom criterion "cognitive disturbances" (COGDIS) is superior in predicting first-episode psychosis. METHOD In a naturalistic 48-month follow-up study, the conversion rate to first-episode psychosis was studied in 246 outpatients of an early detection of psychosis service (FETZ); thereby, the association between conversion, and the combined and singular use of UHR criteria and COGDIS was compared. RESULTS Patients that met UHR criteria and COGDIS (n=127) at baseline had a significantly higher risk of conversion (hr=0.66 at month 48) and a shorter time to conversion than patients that met only UHR criteria (n=37; hr=0.28) or only COGDIS (n=30; hr=0.23). Furthermore, the risk of conversion was higher for the combined criteria than for UHR criteria (n=164; hr=0.56 at month 48) and COGDIS (n=158; hr=0.56 at month 48) when considered irrespective of each other. CONCLUSIONS Our findings support the merits of considering both COGDIS and UHR criteria in the early detection of persons who are at high risk of developing a first psychotic episode within 48months. Applying both sets of criteria improves sensitivity and individual risk estimation, and may thereby support the development of stage-targeted interventions. Moreover, since the combined approach enables the identification of considerably more homogeneous at-risk samples, it should support both preventive and basic research.

A clinical prediction model to identify patients at high risk of death in the emergency department.

PURPOSE Rapid assessment and intervention is important for the prognosis of acutely ill patients admitted to the emergency department (ED). The aim of this study was to prospectively develop and validate a model predicting the risk of in-hospital death based on all available information available at the time of ED admission and to compare its discriminative performance with a non-systematic risk estimate by the triaging first health-care provider. METHODS Prospective cohort analysis based on a multivariable logistic regression for the probability of death. RESULTS A total of 8,607 consecutive admissions of 7,680 patients admitted to the ED of a tertiary care hospital were analysed. Most frequent APACHE II diagnostic categories at the time of admission were neurological (2,052, 24 %), trauma (1,522, 18 %), infection categories [1,328, 15 %; including sepsis (357, 4.1 %), severe sepsis (249, 2.9 %), septic shock (27, 0.3 %)], cardiovascular (1,022, 12 %), gastrointestinal (848, 10 %) and respiratory (449, 5 %). The predictors of the final model were age, prolonged capillary refill time, blood pressure, mechanical ventilation, oxygen saturation index, Glasgow coma score and APACHE II diagnostic category. The model showed good discriminative ability, with an area under the receiver operating characteristic curve of 0.92 and good internal validity. The model performed significantly better than non-systematic triaging of the patient. CONCLUSIONS The use of the prediction model can facilitate the identification of ED patients with higher mortality risk. The model performs better than a non-systematic assessment and may facilitate more rapid identification and commencement of treatment of patients at risk of an unfavourable outcome.

External validation study of a clinical prediction rule for ambulation outcomes after traumatic spinal cord injury

The main objective of this study was to determine the external validity of a clinical prediction rule developed by the European Multicenter Study on Human Spinal Cord Injury (EM-SCI) to predict the ambulation outcomes 12 months after traumatic spinal cord injury. Data from the North American Clinical Trials Network (NACTN) data registry with approximately 500 SCI cases were used for this validity study. The predictive accuracy of the EM-SCI prognostic model was evaluated using calibration and discrimination based on 231 NACTN cases. The area under the receiver-operating-characteristics curve (ROC) curve was 0.927 (95% CI 0.894 – 0.959) for the EM-SCI model when applied to NACTN population. This is lower than the AUC of 0.956 (95% CI 0.936 – 0.976) reported for the EM-SCI population, but suggests that the EM-SCI clinical prediction rule distinguished well between those patients in the NACTN population who were able to achieve independent ambulation and those who did not achieve independent ambulation. The calibration curve suggests that higher the prediction score is, the better the probability of walking with the best prediction for AIS D patients. In conclusion, the EM-SCI clinical prediction rule was determined to be generalizable to the adult NACTN SCI population.^

Clinical prediction of large vessel occlusion in anterior circulation stroke: mission impossible?

Simple clinical scores to predict large vessel occlusion (LVO) in acute ischemic stroke would be helpful to triage patients in the prehospital phase. We assessed the ability of various combinations of National Institutes of Health Stroke Scale (NIHSS) subitems and published stroke scales (i.e., RACE scale, 3I-SS, sNIHSS-8, sNIHSS-5, sNIHSS-1, mNIHSS, a-NIHSS items profiles A-E, CPSS1, CPSS2, and CPSSS) to predict LVO on CT or MR arteriography in 1085 consecutive patients (39.4 % women, mean age 67.7 years) with anterior circulation strokes within 6 h of symptom onset. 657 patients (61 %) had an occlusion of the internal carotid artery or the M1/M2 segment of the middle cerebral artery. Best cut-off value of the total NIHSS score to predict LVO was 7 (PPV 84.2 %, sensitivity 81.0 %, specificity 76.6 %, NPV 72.4 %, ACC 79.3 %). Receiver operating characteristic curves of various combinations of NIHSS subitems and published scores were equally or less predictive to show LVO than the total NIHSS score. At intersection of sensitivity and specificity curves in all scores, at least 1/5 of patients with LVO were missed. Best odds ratios for LVO among NIHSS subitems were best gaze (9.6, 95 %-CI 6.765-13.632), visual fields (7.0, 95 %-CI 3.981-12.370), motor arms (7.6, 95 %-CI 5.589-10.204), and aphasia/neglect (7.1, 95 %-CI 5.352-9.492). There is a significant correlation between clinical scores based on the NIHSS score and LVO on arteriography. However, if clinically relevant thresholds are applied to the scores, a sizable number of LVOs are missed. Therefore, clinical scores cannot replace vessel imaging.

Proposal and validation of methodologies for the categorisation of continuous variables in the development of prediction models

158 p.

Current tools for prediction of arteriovenous fistula outcomes

It remains challenging to accurately predict whether an individual arteriovenous fistula (AVF) will mature and be useable for haemodialysis vascular access. Current best practice involves the use of routine clinical assessment and ultrasonography complemented by selective venography and magnetic resonance imaging. The purpose of this literature review is to describe current practices in relation to pre-operative assessment prior to AVF formation and highlight potential areas for future research to improve the clinical prediction of AVF outcomes.

Variable definitions: implications for the prediction of pulmonary complications after adult cardiac surgery

Aim: The aim of this paper was to review the implications that variable definitions have for the prediction of post-operative pulmonary complications after cardiac surgery.

Method: A review of the literature from 1980 to 2002. Selected studies demonstrated an original attempt to examine multivariate associations between pre, intra or post-operative antecedents and pulmonary outcomes in patients undergoing coronary artery bypass grafting (CABG). Reports that described the validation of established clinical prediction rules, testing interventions or research conducted in non-human cohorts were excluded from this review.

Results: Consistently, variable factor and outcome definitions are combined for the development of multivariate prediction models that subsequently have limited clinical value. Despite being prevalent there are very few attempts to examine post-operative pulmonary complications (PPC) as endpoints in isolation. The trajectory of pulmonary dysfunction that precedes complications in the post-operative context is not clear. As such there is little knowledge of post-operative antecedents to PPC that are invariably excluded from model development.

Conclusion: Multivariate clinical prediction rules that incorporate antecedent patient and process factors from the continuum of cardiovascular care for specific pulmonary outcomes are recommended. Models such as these would be useful for practice, policy and quality improvement.

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.

Clinical decision rules and D-Dimer in venous thromboembolism: current controversies and future research priorities

Venous thromboembolism (VTE) is a potentially lethal clinical condition that is suspected in patients with common clinical complaints, in many and varied, clinical care settings. Once VTE is diagnosed, optimal therapeutic management (thrombolysis, IVC filters, type and duration of anticoagulants) and ideal therapeutic management settings (outpatient, critical care) are also controversial. Clinical prediction tools, including clinical decision rules and D-Dimer, have been developed, and some validated, to assist clinical decision making along the diagnostic and therapeutic management paths for VTE. Despite these developments, practice variation is high and there remain many controversies in the use of the clinical prediction tools. In this narrative review, we highlight challenges and controversies in VTE diagnostic and therapeutic management with a focus on clinical decision rules and D-Dimer.