Diagnostic performance of classification trees and hematological functions in hematologic disorders: an application of multidimensional scaling and cluster analysis

Background Several hematological indices have been already proposed to discriminate between iron deficiency anemia (IDA) and β‐thalassemia trait (βTT). This study compared the diagnostic performance of different hematological discrimination indices with decision trees and support vector machines, so as to discriminate IDA from βTT using multidimensional scaling and cluster analysis. In addition, decision trees were used to determine the diagnostic classification scheme of patients. Methods Consisting of 1178 patients with hypochromic microcytic anemia (708 patients with βTT and 470 patients with IDA), this cross-sectional study compared the diagnostic performance of 43 hematological discrimination indices with classification tree algorithms and support vector machines in order to discriminate IDA from βTT. Moreover, multidimensional scaling and cluster analysis were used to identify the homogeneous subgroups of discrimination methods with similar performance. Results All the classification tree algorithms except the LOTUS tree algorithm showed acceptable accuracy measures for discrimination between IDA and βTT in comparison with other hematological discrimination indices. The results indicated that the CRUISE and C5.0 tree algorithms had better diagnostic performance and efficiency among other discrimination methods. Moreover, the AUC of CRUISE and C5.0 tree algorithms indicated more precise classification with values of 0.940 and 0.999, indicating excellent diagnostic accuracy of such models. Moreover, the CRUISE and C5.0 tree algorithms showed that mean corpuscular volume can be considered as the main variable in discrimination between IDA and βTT. Conclusions CRUISE and C5.0 tree algorithms as powerful methods in data mining techniques can be used to develop accurate differential methods along with other laboratory parameters for the discrimination of IDA and βTT. In addition, the multidimensional scaling method and cluster analysis can be considered as the most appropriate techniques to determine the discrimination indices with similar performance for future hematological studies.

New Formula for the Identification of Liquefaction Based on the Investigation of the Songyuan Site

Based on the 5.7-magnitude earthquake that stroke Songyuan (China) and 172 groups of liquefaction data collected in mainland China, the hyperbolic liquefaction discriminant formula originally proposed by Sun Rui was revised, and a new formula for the liquefaction of sand was put forward. Groups of data derived from the Bachu earthquake in Xinjiang and an earthquake that occurred in New Zealand (47 and 195 groups, respectively) were used to carry out a back-judgment test, then, the results were compared with those of the existing standard method. Overall, the results showed that the new formula for hyperbolic liquefaction discrimination compensates for the conservative liquefaction discrimination of the older formula; moreover, it has a good applicability to different intensities, groundwater levels, and the deep sand layer of the Songyuan site, reflected by a more balanced success rate. Therefore, combining the existing liquefaction discrimination methods and the research results of discrimination, it is necessary to establish a suitable regional identification method through the continuous accumulation of liquefaction data and expanding database.

Analysis of Neural Interface When Using Modiolar Electrode Stimulation. Radiological Evaluation, Trans-Impedance Matrix Analysis and Effect on Listening Effort in Cochlear Implantation

Background: The proximity of the electrode to the modiolar wall may be of interest to investigate the effect of pitch discrimination. This research establishes the relation between these factors and whether perimodiolar positions may provide benefits regarding improved electrode discrimination. Methods: A prospective randomized study including 24 post-lingual deaf adults was performed. A psychoacoustic study was done by using a psychoacoustic research platform. Radiological study, and a cone-beam computed tomography was used to assess post cochlear implantation electrodes’ position. Trans-impedance matrix (TIM) analysis was performed after cochlear implant insertion in all cases, and pupillometry test was also performed. Results: 12 patients received a slim perimodiolar electrode array, and 12 patients received a straight electrode array. Although all the patients showed similar speech test results after 12 months follow-up, those implanted with a perimodiolar electrode obtained better scores in electrode discrimination test and pupillometry test, and showed more homogenous TIM patterns. Conclusions: The better positioning of the electrode array seams to provide a better hearing resolution and less listening effort trans-impedance matrix seems to be a useful tool to analyze positioning of the perimodiolar array.

A New Method for Haptic Shape Discriminability Detection

Touch shape discrimination is not only closely related to tactile mechanoreceptors but also higher cognitive function. However, previous shape discrimination methods are difficult to complete in a short time, and the devices are complicated to operate and not user-friendly for nonprofessionals. Here, we propose a new method, the evaluation quantity of which is the angle discrimination threshold. In addition, to make this method easy to use for nonprofessionals, we designed a haptic angle sorting system, including the device and software. To evaluate this method, the angle sorting and two-angle discrimination experiments were compared, and it was found that participants spent significantly less time in the former experiment than in the latter. At the same time, there is a strong correlation between the performance of angle sorting and two-angle discrimination, which shows that the angle threshold obtained by the new method can also be used to evaluate the ability of touch discrimination. Moreover, the angle sorting results of different age groups also further demonstrate the feasibility of the method. The efficiency of this new method and the effectiveness of the system also provide a convenient means for evaluating haptic shape discrimination, which may have potential clinical application value in the early diagnosis of peripheral neuropathy and even in the evaluation of cognitive function.

Comparison of Diagnostic Performance of Classification Trees and Hematological Discrimination Functions for Differential Diagnosis between the Two Common Hematologic Disorders: An Application of Multidimensional Scaling and Cluster Analysis

Background: Several hematological indices have been already proposed to discriminate between iron deficiency anemia (IDA) and β‐thalassemia trait (βTT). The aim of the present study was to compare the diagnostic performance of different hematological discrimination indices with statistical methods such as decision trees to discriminate IDA from βTT.Methods: Consisting of 1178 patients with hypochromic microcytic anemia (708 patients with βTT and 470 patients with IDA), this cross-sectional study intended to compare the diagnostic performance of 43 hematological discrimination indices and tree-based methods such as J48, CART, Evtree, Ctree, QUEST, CRUISE as well as GUIDE to discriminate IDA from βTT. Moreover, multidimensional scaling and cluster analysis were used to identify the homogeneous subgroups of discrimination methods with similar performances.Results: All the classification tree algorithms showed acceptable accuracy measures for discrimination between IDA and βTT in comparison with other hematological discrimination indices. The results indicated that CRUISE tree algorithm had better diagnostic performance and efficiency among other discrimination methods. In turn, this tree algorithm showed the high Youden's index (88.03%), accuracy (94.57%), diagnostic odds ratio (311.63) and F-measure (95.54%) in the differential diagnosis of IDA from βTT. In addition, AUC of this algorithm indicated more precise classification with a value of 0.94 and this model was found to have excellent diagnostic accuracy. Also, CRUISE tree algorithm showed that Mean corpuscular volume can be considered as the main variable in discrimination as it extracted six homogenous subgroups of patients.Conclusions: CRUISE tree algorithm as a powerful method in data mining techniques can be used to develop accurate differential methods along with other laboratory parameters to discriminate IDA from βTT.

Method of Profanity Detection Using Word Embedding and LSTM

With the rising number of Internet users, there has been a rapid increase in cyberbullying. Among the types of cyberbullying, verbal abuse is emerging as the most serious problem, for preventing which profanity is being identified and blocked. However, users employ words cleverly to avoid blocking. With the existing profanity discrimination methods, deliberate typos and profanity using special characters can be discriminated with high accuracy. However, as they cannot grasp the meaning of the words and the flow of sentences, standard words such as “Sibaljeom (starting point, a Korean word that sounds similar to a swear word)” and “Saekkibalgalag (little toe, a Korean word that sounds similar to another swear word)” are less accurately discriminated. Therefore, in order to solve this problem, this study proposes a method of discriminating profanity using a deep learning model that can grasp the meaning and context of words after separating Hangul into the onset, nucleus, and coda.

Analog Pulse Shape Discrimination Based on Time Duration and Pulse Height

Pulse shape discrimination is a name of a group of techniques used to detect and distinguish between different types of radiation interactions. Analog pulse shape discrimination methods can be more suitable than digital methods, for high-speed scintillators both from rate and power consumption perspectives. Common analog discrimination methods are based on pulse-height and pulse-energy discrimination techniques. Other techniques rely on the time difference in the pulse width such as the ZeroCrossing methods. Neither of the above combine both amplitude and time methods. We present a novel analog pulse shape discrimination topology that combines both height and time domain. The topology is based on discrimination according to the pulse duration in time combined with compensation function of the pulse height. Amplitude of the pulse is used as a restraining factor. Subsequently, our topology correctly identifies fast pulses that are prolonged in time due to their high amplitude. The topology yields superior discrimination capabilities, under degraded light collection conditions, with an uncertainty gap smaller than 1 ns in pulse width. The ability to control both the time and the amplitude parameters individually, provides tailored adjustment for various detectors and pulse shape discrimination applications.