Prediction models for cyclomatic complexity

BackgroundConservative treatments are beneficial for people with hand osteoarthritis (OA). ObjectiveIt was the purpose of this study to develop and internally validate both a basic model and a more complex model that could predict responders to conservative treatments in people with hand OA. DesignThis was a secondary analysis of a single-centre, randomised feasibility study. MethodsFifty-nine participants (34 responders) with hand osteoarthritis were recruited from the general population. Participants were randomised to receive either advice alone, or advice in combination with blood flow restriction training (BFRT), or traditional high intensity training (HIT). Participants underwent supervised hand exercises three times per week for six weeks. The OMERACT-OARSI criteria were utilised to determine responders vs non responders to treatment at the end of six weeks. A basic logistic regression model (treatment type, expectations, adherence) and a more complex logistic regression model (basic model variables plus pain catastrophising and neuropathic pain features) were created. Discrimination ability, and calibration were assessed. Internal model validation through bootstrapping (200 repetitions) was utilised to calculate the prediction model optimism. ResultsThe results showed that the basic model presented with acceptable discrimination (optimism corrected c-statistic: 0.72, 95% CI 0.71–0.73) and calibration (slope = 1.41; intercept = 0.68). The more complex model had better discrimination but poorer calibration. ConclusionA prediction tool was created to provide an individualised estimate of treatment response in people with hand OA. Future studies will need to validate this model in other groups of patients. Trial registrationhttps://www.anzctr.org.au/- ACTRN12617001270303.

This paper introduces the prediction model of workforce competency & defect density for Vehicle navigation system, and shows the methods to improve the software project quality. The study shows that the average programming competency level of the developers and cyclomatic complexity are related to the coding stage defect density. Further, a prediction model of competency, cyclomatic complexity and coding stage defect density is drawn on the basis of statistics; meanwhile, according to the research result some methods to improve the navigation software project quality are concluded.

Road noise pollution is one of the most topical environmental issues for local authorities, under the circumstances of increasingly demanding legislation in this area. In this context, the use of road noise models is of particular importance - on the one hand, in the design of new road infrastructures - in order to assess the acoustic impact and avoid further passive noise protection measures that can be very costly, and, on the other hand, for the existing road networks, to minimize noise measurement campaigns only to the volume required to calibrate the model. After a brief presentation of the most commonly used road noise prediction models, a series of simulations were carried out using the Dutch 2002 software based on the British CoRTN model for different values of traffic characteristics on the road artery in front of Building T of the University of Pitesti. Immediate noise measurement at the level of the building, under the same road traffic conditions as in the simulation, confirms the veracity of the results obtained by means of simulation. Finally, a complex model is proposed for predicting the immission of road noise on the basis of road traffic and noise propagation characteristics, where, in the case of long and narrow road arteries, when traffic simulation is carried out at a macro level, the complex model is operable on the basis of already existing noise emission models.

A novel MINLP-based representation of the original complex model for predicting gasoline emissions

Modern control strategies for district-level heating and cooling supply systems pose a difficult challenge. In order to integrate a wide range of hot and cold sources, these new systems will rely heavily on accumulation and much lower operating temperatures. This means that predictive models advising the control strategy must take into account long-lasting thermal effects but must not be computationally too expensive, because the control would not be possible in practice. This paper presents a simple but powerful systematic approach to reducing the complexity of individual components of such models. It makes it possible to combine human engineering intuition with machine learning and arrive at comprehensive and accurate models. As an example, a simple steady-state heat loss of buried pipes is extended with dynamics observed in a much more complex model. The results show that the process converges quickly toward reasonable solutions. The new auto-generated model performs 5 × 104 times faster than its complex equivalent while preserving essentially the same accuracy. This approach has great potential to enhance the development of fast predictive models not just for district heating. Only open-source software was used, while OpenModelica, Python, and FEniCS were predominantly used.

We present a framework for automatic grading of programming exercises using property-based testing, a form of model-based black-box testing. Models are developed to assess both the functional behaviour of programs and their algorithmic complexity. From the functional correctness model a large number of test cases are derived automatically. Executing them on the body of exercises gives rise to a (partial) ranking of programs, so that a program A is ranked higher than program B if it fails a strict subset of the test cases failed by B. The model for algorithmic complexity is used to compute worst-case complexity bounds. The framework moreover considers code structural metrics, such as McCabe's cyclomatic complexity, giving rise to a composite program grade that includes both functional, non-functional, and code structural aspects. The framework is evaluated in a course teaching algorithms and data structures using Java.

To develop a predictive model by 18F-FDG PET/CT radiomic features and to validate the predictive value of the model for distinguishing solitary lung adenocarcinoma from tuberculosis. A total of 235 18F-FDG PET/CT patients with pathologically or follow-up confirmed lung adenocarcinoma (n = 131) or tuberculosis (n = 104) were retrospectively and randomly divided into a training (n = 163) and validation (n = 72) cohort. Based on the Transparent Reporting of Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), this work was belonged to TRIPOD type 2a study. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) algorithm were used to select the optimal predictors from 92 radiomic features that were extracted from PET/CT, and the optimal predictors were used to build the radiomic model in the training cohort. The meaningful clinical variables comprised the clinical model, and the combination of the radiomic model and clinical model was a complex model. The performances of the models were assessed by the area under the receiver operating characteristic curve (AUC) in the training and validation cohorts. In the training cohort, 9 radiomic features were selected as optimal predictors to build the radiomic model. The AUC of the radiomic model was significantly higher than that of the clinical model in the training cohort (0.861 versus 0.686, p < 0.01), and this was similar in the validation cohort (0.889 versus 0.644, p < 0.01). The AUC of the radiomic model was slightly lower than that of the complex model in the training cohort (0.861 versus 0.884, p > 0.05) and validation cohort (0.889 versus 0.909, p > 0.05), but there was no significant difference. 18F-FDG PET/CT radiomic features have a significant value in differentiating solitary lung adenocarcinoma from tuberculosis.

ABSTRACTRecent advances in artificial intelligence have produced powerful predictive models for chemical analysis, but model interpretability remains a challenge. Here, we introduce Unsupervised Hierarchical Symbolic Regression (UHSR), providing an explainable solution while maintaining competitive predictive performance. With a focus on thin‐layer chromatography (TLC), a crucial technique in molecular polarity analysis, UHSR automatically distills chemically‐intuitive retention indices and discovers explainable equations that link molecular structures to chromatographic behavior. Experiments have shown UHSR's capability to derive concise and accurate governing equations linking polarity to molecular structures from the TLC dataset. A survey of 100 expert chemists demonstrates that our UHSR model gains more trust from chemists compared to traditional models. Additionally, we also show its adaptability to other property prediction tasks beyond molecular polarity.

Introduction &amp; Objectives: Early identification of individuals at elevated risk of developing diabetic kidney disease (DKD) could improve clinical care and prognosis through enhanced cost-effective surveillance and better management of underlying health conditions. The aim of this study was to develop an effective and practical model for predicting early DKD risk in a community-based prospective cohort. Methods: A prospective community-based cohort study was undertaken from 2013 to 2018. We analyzed data from 1545 people with diabetes and normal kidney function at baseline. The least absolute shrinkage and selection operator regression with cross-validation was used to identify potential predictive variables. A less complex DKD prediction model was derived from logistic regression and presented as a nomogram. The performance of the novel DKD prediction model was compared with that of the existing prediction model by assessing model discrimination. Results: Six predictors of DKD were identified: diabetes duration, family history of diabetes, systolic blood pressure, urine albumin-to-creatinine ratio, estimated glomerular filtration rate, and glycated albumin (GA). The new DKD predictive model demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.797 and was internally validated with a corrected AUC of 0.786. There were no significant deviations between observed probability and predicted probability. The predictive performance of the existing DKD risk prediction model was significantly lower than our new DKD risk prediction model (AUC: 0.681 vs. 0.797, P &amp;lt;0.001). In addition, the predictive value of GA was higher than that of Hemoglobin A1c and fasting plasma glucose. Conclusions: The 5-year early DKD predictive model, derived from a community-based cohort, demonstrates good performance. Additionally, GA holds more significant importance than other glucose indicators in predicting DKD. Disclosure X. Hou: None. X. Ye: None. W. Jia: None.

BackgroundAccurate risk stratification in heart failure (HF) populations is crucial. Existing simple scores, such as MAGGIC, show limited discrimination (C-index < 0.80) and require specialised tests like echocardiography. Conversely, while advanced Artificial Intelligence (AI) models offer greater accuracy, their operational complexity and data access requirements often hinder clinical adoption.PurposeTo develop and validate a parsimonious, high-performing AI-based risk model for all-cause mortality in HF patients by leveraging insights from a complex AI model and feature engineering.MethodsUsing a cohort of 373,389 patients with HF (≥18 years; 1,153 English practices for derivation, 289 for validation) from the Clinical Practice Research Datalink (CPRD) Aurum dataset, we developed and validated an AI-based risk prediction model for all-cause mortality. A MAGGIC-based Cox proportional hazards model adapted for electronic health records (EHR) was established as a performance benchmark. An initial Multi-layer Perceptron (MLP) model with a survival framework was trained with MAGGIC variables. This MLP model was then enhanced by incorporating highly predictive comorbidity features—identified by an explainable Transformer model trained on longitudinal electronic health record (EHR) data—and feature distillation to derive a final, optimised 11-variable model (named MLP-Distilled). The model employed readily ascertainable variables including age, BMI, year of birth (as a proxy for birth cohort effects), and key comorbidities such as cancers.ResultsMLP-Distilled demonstrated significantly improved discriminatory performance (C-index: 0.801, 95% CI [0.796, 0.806]) compared to the benchmark MAGGIC-EHR model (0.735, [0.729, 0.742]), while maintaining excellent calibration. This parsimonious model uses fewer and more accessible variables than MAGGIC (11 vs. 13) and requires no specialised tests. The model was validated for secondary outcomes of cardiovascular events and rehospitalisation.ConclusionUtilising knowledge from a complex EHR-trained AI model combined with feature distillation yielded a parsimonious yet powerful risk score for HF mortality. This novel approach offers a pathway to clinically implementable tools that balance predictive accuracy with pragmatic utility, potentially improving routine HF risk stratification.Discrimination_Calibration.jpegImpact_Analysis_50_Threshold.jpeg

BackgroundTriage trauma scores are utilised to determine patient disposition, interventions and prognostication in the care of trauma patients. Heart rate variability (HRV) and heart rate complexity (HRC) reflect the autonomic nervous system and are derived from electrocardiogram (ECG) analysis. In this study, we aimed to develop a model incorporating HRV and HRC, to predict the need for life-saving interventions (LSI) in trauma patients, within 24 h of emergency department presentation.MethodsWe included adult trauma patients (≥ 18 years of age) presenting at the emergency department of Singapore General Hospital between October 2014 and October 2015. We excluded patients who had non-sinus rhythms and larger proportions of artefacts and/or ectopics in ECG analysis. We obtained patient demographics, laboratory results, vital signs and outcomes from electronic health records. We conducted univariate and multivariate analyses for predictive model building.ResultsTwo hundred and twenty-five patients met inclusion criteria, in which 49 patients required LSIs. The LSI group had a higher proportion of deaths (10, 20.41% vs 1, 0.57%, p < 0.001). In the LSI group, the mean of detrended fluctuation analysis (DFA)-α1 (1.24 vs 1.12, p = 0.045) and the median of DFA-α2 (1.09 vs 1.00, p = 0.027) were significantly higher. Multivariate stepwise logistic regression analysis determined that a lower Glasgow Coma Scale, a higher DFA-α1 and higher DFA-α2 were independent predictors of requiring LSIs. The area under the curve (AUC) for our model (0.75, 95% confidence interval, 0.66–0.83) was higher than other scoring systems and selected vital signs.ConclusionsAn HRV/HRC model outperforms other triage trauma scores and selected vital signs in predicting the need for LSIs but needs to be validated in larger patient populations.

Erosion prediction models are useful tools for assessing the impact of land use practices on soil and water conservation. These models are often used by environmental protection authorities for the establishment of guidelines. This study examines the application of three erosion models of different complexity to predict soil loss in a small basin located in the center of the Iberian Peninsula, under a semi-arid Mediterranean climate. The models applied are: the Universal Soil Loss Equation (USLE), the Revised Universal Soil Loss Equation (RUSLE) and an adaptation of the USLE model, which we have called AUSLE, to include soil characteristics not included in the original model. The average value of erosion at the watershed level obtained by the AUSLE model does not show significant differences with respect to the value obtained with RUSLE 1.06c, while the USLE shows an overestimation with respect to the other two models. The AUSLE model allows obtaining values similar to the more complex model (RUSLE) in a simple way, which makes it interesting for its application in conservation plans.

Non-destructive prediction of soluble solids content of pear based on fruit surface feature classification and multivariate regression analysis

Advanced driver assistance systems have been an active research topic for decades, for which many approaches have been developed not only to reduce the number of traffic accidents but also to increase the driver’s comfort. Among the many different solutions proposed, learning-based prediction approaches have gained considerable attention in recent years. Within this scope, this work focuses on the implementation aspects of a linear learning-based regression model for detecting unintended lane-departures, where the goal is to achieve a prediction model with good predictive performance while keeping the computational complexity as low as possible. Aspects under consideration include input signal selection and down-sampling. The linear prediction model is analyzed using a real world data set, and benchmarked against a kinematic constant velocity model and a non-linear regression model. The results show that the linear regression model has a significantly higher prediction performance when compared to a kinematic model. It is also shown that the predictive performance remains comparable to the more complex nonlinear regression model, even though the computational complexity of the linear model is significantly lower.

Glioblastoma (GBM) is the most common and aggressive primary brain tumour; we aimed to evaluate T2 relaxivity in their follow. Fifty-one newly diagnosed GBM followed at our department after surgery and combined chemo-radiotherapy were included (&amp;gt; 180 days progression-free survival [PFS] as determined by RANO, ≥ 3 MRI examinations in the PFS interval). All data used were prior to progression. T2 relaxation rates (1/T2f) were calculated voxel-wise assuming mono-exponential decay. Whole-brain (WB) values were extracted including skewness, kurtosis, mean, median, 15 and 85 percentile histogram values and variance. We additionally segmented the 1/T2f volumes using a 5 compartment Gaussian mixture model, producing mean, variance and percent per component. To evaluate predictive potential with respect to PFS, we used a deep long short-term memory (LSTM) model in tensorflow (4 timesteps). Twenty subjects were included in the predictive model, as inclusion criteria differed (progression, ≤ 120 days between all MRIs [mean 44.3 days], ≥ 4 PFS MRIs). Two models were tested: a regression model (days to progression) and a classification model (±18 months PFS; models differed in output layer). Both models were run 10 times; mean results are presented. We found WB median 1/T2f correlated with PFS, as values decreased prior to progression. WB median 1/T2f linear regression slopes also differed in progression vs. pseudo-progression. The deep LSTM regression model achieved an R2 of 86%. The deep LSTM classification model achieved a mean macro precision of 85%, recall 84% and F1 accuracy of 84% in classifying progression/no progression at an 18 month cutoff. We found very intriguing results with WB median 1/T2f measurements in distinguishing progression from pseudo-progression, and in suggesting progression despite otherwise unremarkable imaging. A more complex predictive model, using a fully-automated segmentation method followed by deep learning, was very promising. Our results may find utility in the monitoring of GBM patients.