Large Margin Graph Embedding-Based Discriminant Dimensionality Reduction

Discriminant graph embedding-based dimensionality reduction methods have attracted more and more attention over the past few decades. These methods construct an intrinsic graph and penalty graph to preserve the intrinsic geometry structures of intraclass samples and separate the interclass samples. However, the marginal samples cannot be accurately characterized only by penalty graphs since they treat every sample equally. In practice, these marginal samples often influence the classification performance, which needs to be specially tackled. In this study, the near neighbors’ hypothesis margin of marginal samples has been further maximized to separate the interclass samples and improve the discriminant ability by integrating intrinsic graph and penalty graph. A novel discriminant dimensionality reduction named LMGE-DDR has been proposed. Several experiments on public datasets have been conducted to verify the effectiveness of the proposed LMGE-DDR such as ORL, Yale, UMIST, FERET, CMIU-PIE09, and AR. LMGE-DDR performs better than other compared methods, and the corresponding standard deviation of LMGE-DDR is smaller than others. This demonstrates that the evaluation method verifies the effectiveness of the introduced method.

Potencial Use of Near Infrared Spectroscopy (NIRS) to Categorise Chorizo Sausages from Iberian Pigs According to Several Quality Standards

The ability of Near Infrared Spectroscopy (NIRS) to classify pre-sliced Iberian chorizo modified atmosphere packaged (MAP) according to the animal material used in their production (Black, Red, White) in their production in accordance with the official trade categories (which includes the handling system and the different inter-racial crossbreeds) without opening the package was assayed. Furthermore, various spectra pre-treatments and supervised classification chemometric tools; Partial least square-discriminant analysis (PLS-DA), soft independent modelling of class analogies (SIMCA) and linear discriminant analysis (LDA), were assessed. The highest sensitivity values in both calibration and external validation were achieved with SIMCA followed by PLS-DA approaches, while LDA had more provided values among sensitivity and specificity and between the different commercial categories in both sample sets, thus yielding the highest discriminant ability. These results could be a resource to support the traceability and authentication control of individual pre-sliced MAP Iberian chorizo according to the commercial category of the raw material in a non-destructive way.

Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions

To improve the classification results of high-resolution remote sensing images (RSIs), it is necessary to use feature transfer methods to mine the relevant information between high-resolution RSIs and low-resolution RSIs to train the classifiers together. Most of the existing feature transfer methods can only handle homogeneous data (i.e., data with the same dimension) and are susceptible to the quality of the RSIs, while RSIs with different resolutions present different feature dimensions and samples obtained from illumination conditions. To obtain effective classification results, unlike existing methods that focus only on the projection transformation in feature space, a joint feature-space and sample-space heterogeneous feature transfer (JFSSS-HFT) method is proposed to simultaneously process heterogeneous multi-resolution images in feature space using projection matrices of different dimensions and reduce the impact of outliers by adaptive weight factors in the sample space simultaneously to reduce the occurrence of negative transfer. Moreover, the maximum interclass variance term is embedded to improve the discriminant ability of the transferred features. To solve the optimization problem of JFSSS-HFT, the alternating-direction method of multipliers (ADMM) is introduced to alternatively optimize the parameters of JFSSS-HFT. Using different types of ship patches and airplane patches with different resolutions, the experimental results show that the proposed JFSSS-HFT obtains better classification results than the typical feature transferred methods.

Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant

Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive models based on random forest classifiers (RF) and an artificial neural network called multi-layer perceptron (MLP). All designed models had four common input parameters, determining the best accuracy and discriminant ability: donor’s eGFR, recipient’s BMI, donor’s BMI, and recipient–donor weight difference. RF and MLP designs, using these parameters, achieved an accuracy of 84.38% and an area under curve (AUC) 0.84. The model additionally implementing a donor’s age, gender, and Kidney Donor Profile Index (KDPI) accomplished an accuracy of 93.75% and an AUC of 0.91. The other configuration with the estimated post-transplant survival (EPTS) and the kidney donor risk profile (KDRI) achieved an accuracy of 93.75% and an AUC of 0.92. Using machine learning, we were able to assess the risk of DGF in recipients after kidney transplant from a deceased donor. Our solution is scalable and can be improved during subsequent transplants. Based on the new data, the models can achieve better outcomes.

Credit Rating Model of Small Enterprises Based on Optimal Discriminant Ability and Its Empirical Study

As an important part of the national economy, small enterprises are now facing the problem of financing difficulties, so a scientific and reasonable credit rating method for small enterprises is very important. This paper proposes a credit rating model of small enterprises based on optimal discriminant ability; the credit score gap of small enterprises within the same credit rating is the smallest, and the credit score gap of small enterprises between different credit ratings is the largest, which is the dividing principle of credit rating of small enterprises based on the optimal discriminant ability. Based on this principle, a nonlinear optimization model for credit rating division of small enterprises is built, and the approximate solution of the model is solved by a recursive algorithm with strong reproducibility and clear structure. The small enterprise credit rating division not only satisfies the principle that the higher the credit grade, the lower the default loss rate, but also satisfies the principle that the credit group of small enterprises matches the credit grade, with credit data of 3111 small enterprises from a commercial bank for empirical analysis. The innovation of this study is the maximum ratio of the sum of the dispersions of credit scores between different credit ratings and the sum of the dispersions of credit scores within the same credit rating as the objective function, as well as the default loss rate of the next credit grade strictly larger than the default loss rate of the previous credit grade as the inequality constraint; a nonlinear credit rating optimal partition model is constructed. It ensures that the small enterprises with small credit score gap are of the same credit grade, while the small enterprises with large credit score gap are of different credit grades, overcoming the disadvantages of the existing research that only considers the small enterprises with large credit score gap and ignores the small enterprises with small credit score gap. The empirical results show that the credit rating of small enterprises in this study not only matches the reasonable default loss rate but also matches the credit status of small enterprises. The test and comparative analysis with the existing research based on customer number distribution, K-means clustering, and default pyramid division show that the credit rating model in this study is reasonable and the distribution of credit score interval is more stable.

Establishment and Verification On A Death Risk Model of Sepsis Patients Within 30 Days

Background/Objective: To establish and validate an individualized nomogram to predict the probability of death within 30 days in patients with sepsis would help clinical physicians to make correct decision. Methods We collected data of 1,205 patients with sepsis. These included 16 indexes like age and blood, randomly assigned to the modeling and verification groups. In the modeling group, the independent risk factors related to death within 30 days were analyzed. Besides, a nomogram was established to draw the receiver-operating characteristic (ROC) curve of the subjects. Subsequently, the discriminant ability of the model was evaluated by the area under the ROC curve (AUC). Then, a calibration chart and Hosmer-Lemeshow test were employed to evaluate the calibration degree of the model, and the Decline Curve Analysis (DCA) test was used to evaluate the clinical effect of the model. Results The different independent risk factors related to the death of sepsis patients within 30 days included pro-brain natriuretic peptide (pro.bnp), albumin, lactic acid (lac), oxygenation index, mean arterial pressure (map), and hematocrit (hct). The AUC of the modeling and verification groups were 0.815 and 0.806, respectively. Moreover, the P-values of the Hosmer-Lemeshow test in the two groups were 0.391 and 0.100, respectively, and the DCA curves of the two groups were both above the two extreme curves. Conclusion Our model presents good significance for predicting the death of sepsis patients within 30 days. Therefore, there is a need to implement this model in clinical practice, as prompt prediction could help tailor treatment regimens and enhance survival outcomes.

Development and Evaluation of the MAINTAIN Instrument, Selecting Patients Suitable for Secondary or Tertiary Preventive Manual Care – The Nordic Maintenance Care Program

BackgroundChiropractic Maintenance Care (MC) has been found to be effective for patients classified as dysfunctional (high pain severity, marked interference with everyday life due to pain, high affective distress, low perception of life control, and low activity levels) by the Swedish equivalent of the West Haven-Yale Multidimensional Pain Inventory (MPI-S). Although displaying good psychometric properties such as validity and reliability, the instrument was not designed to be used in clinical practice to screen patients for stratified care pathways. To effectively be able to screen for individuals suitable for MC, the aim was to develop a clinical instrument with the intent of identifying dysfunctional patients with acceptable sensitivity, specificity, and discriminant ability.MethodsData from 249 patients with a complete MPI dataset from an RCT that investigated the effect and cost-effectiveness of MC with a 12-month follow-up was used in this cross-sectional analysis. The MPI’s data was used to develop a short screening instrument to identify dysfunctional patients, with a summary measure, based on the original instrument. Different cutoffs were considered with regards to sensitivity, specificity, and discriminant ability and compared to the original instrument’s classification of dysfunctional patients. The instrument was then tested in 3 other existing datasets to assess validity across populations.ResultsUsing an explorative approach, the MAINTAIN instrument with 10 questions (0-6 Likert responses) with 5 dimensions (pain severity, interference, life control, affective distress, and support) was developed, generating an algorithm-based score ranging from -12 to 48. Reporting a MAINTAIN score of 18 or higher, 146 out of the 249 patients were classified as dysfunctional with 95.8% sensitivity and 64.3% specificity. At a score of 22 or higher, 109/249 were classified as dysfunctional with 81.1% sensitivity and 79.2% specificity. Discriminant ability (area under the curve (AUC)) was estimated to 0.87 (95% CI: 0.83, 0.92; p <0.001) and Youden’s index was highest (0.70) at a score of 20. The discriminant ability is similar and acceptable across populations with minor differences in optimal thresholds for identifying dysfunctional individuals.ConclusionThe MAINTAIN instrument had an acceptable performance with regards to identifying dysfunctional patients and may be used as a decision aid in clinical practice. By using 2 thresholds, patients can be categorized into “low probability (-12 to 17)”, “moderate probability (18 to 21)”, and “high probability (22 to 48)” of having a good outcome from maintenance care for Low Back Pain (LBP).Trial registrationClinical trials.gov; NCT01539863; registered February 28, 2012; https://clinicaltrials.gov/ct2/show/NCT01539863

Prognostic Factors for Overall Survival In Chronic Myeloid Leukemia Patients: A Multicentric Cohort Study by the Italian CML GIMEMA Network

An observational prospective study was conducted by the CML Italian network to analyze the role of baseline patient characteristics and first line treatments on overall survival and CML-related mortality in 1206 newly diagnosed CML patients, 608 treated with imatinib (IMA) and 598 with 2nd generation tyrosine kinase inhibitors (2GTKI). IMA-treated patients were much older (median age 69 years, IQR 58-77) than the 2GTKI group (52, IQR 41-63) and had more comorbidities. Estimated 4-year overall survival of the entire cohort was 89% (95%CI 85.9-91.4). Overall, 73 patients (6.1%) died: 17 (2.8%) in the 2GTKI vs 56 (9.2%) in the IMA cohort (adjusted HR=0.50; 95% CI=0.26-0.94), but no differences were detected for CML-related mortality (10 (1.7%) vs 11 (1.8%) in the 2GTKIs vs IMA cohort (sHR=1.61; 0.52-4.96). The ELTS score was associated to CML mortality (high risk vs low, HR=9.67; 95%CI 2.94-31.74; p&lt;0.001), while age (per year, HR=1.03; 95%CI 1.00-1.06; p=0.064), CCI (4-5 vs 2, HR=5.22; 95%CI 2.56-10.65; p&lt;0.001), ELTS score (high risk vs low, HR=3.11; 95%CI 1.52-6.35, p=0.002) and 2GTKI vs IMA (HR=0.26; 95%CI 0.10-0.65, p=0.004) were associated to an increased risk of non-related CML mortality. The ELTS score showed a better discriminant ability than the Sokal score in all comparisons.