1. A system for predicting acute exacerbation of COPD and respiratory failure, comprising:

a data acquisition module for acquiring clinical case data of a sample;

the data processing module is used for receiving the data information acquired by the data acquisition module, performing statistical analysis on the data information and acquiring variable parameters;

the risk factor acquisition module is used for receiving the variable parameters, carrying out regression analysis on the variable parameters and screening to obtain independent risk factors;

and the prediction module is used for receiving the independent risk factors, taking the independent risk factors as input parameters of a machine learning algorithm, establishing a machine learning prediction model by taking whether T2RF occurs as an ending event, and predicting the received data of the person to be measured by using the machine learning prediction model.

2. The system for predicting COPD acute exacerbation concurrent respiratory failure according to claim 1, further comprising a data filling module, wherein an input end of the data filling module is connected with an output end of the data acquisition module, the data filling module fills data with a missing rate of less than or equal to 30% by using a missfiest algorithm, and an output end of the data filling module is connected with an input end of the data processing module.

3. The system for predicting COPD acute exacerbation concurrent respiratory failure according to claim 1, further comprising a model evaluation module, wherein the model evaluation module stores credit evaluation parameters: the model evaluation module acquires corresponding data of the prediction model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the prediction model according to the comparison difference value.

4. The system according to claim 1, wherein the independent risk factors include lymphocyte count, creatinine, variation coefficient of erythrocyte distribution width, mean hemoglobin concentration, mean platelet volume, percentage of basophils, urea, glutamic pyruvic transaminase, and duration of disease.

5. The system of claim 1, wherein the risk factor acquiring module comprises a LASSO model and a multi-factor logistic regression analysis model, the variable parameters are inputted into the LASSO model, the variables outputted from the LASSO model enter the multi-factor logistic regression analysis model, and the multi-factor logistic regression analysis model outputs independent risk factors.

6. The system of claim 5, wherein the objective function of the LASSO algorithm is:

wherein, independent variableFor each oneIs provided withi represents a sample number, i is 1,2, …, m is the total number of samples, j represents an independent variable, j is 1,2, …, n, m, n are all positive integers, y is_iIs a dependent variable, b is an error term, and the regression coefficient w is (w)₁，w₂，…，w_n)^TAnd lambda is a regulating parameter,an L1 penalty term representing the regression coefficient w;

multifactor Logistic regression analysis:

wherein, independent variablei represents a sample number, n represents a total independent variable, Y ∈ {0, 1} represents a dependent variable, and a regression coefficient β ═ β (β [ - ])⁽¹⁾，β⁽²⁾，…，β⁽ⁿ⁾，b)^TB is an offset, and α · β is the inner product of α and β.

7. A COPD respiration monitoring apparatus comprising a prediction system according to any one of claims 1 to 6, and a respiration monitoring mechanism and a head-mounted respiration training mechanism;

the starting end of the respiration monitoring mechanism is connected with the output end of the prediction system, the respiration monitoring mechanism is used for collecting the respiration frequency of a patient and a respiration image of the patient, and the output end of the respiration monitoring mechanism is connected with a memory and is used for storing collected information;

the training mechanism is breathed to wear-type includes locating rack and two swinging arms, the middle part of two swinging arms is installed on the locating rack through the pivot, the swinging arms rotates with the pivot to be connected, two swinging arms cross arrangement, the tip of two swinging arms one side is located one side of human nose respectively, the tip of two swinging arms opposite sides is located the side of human mouth angle respectively, and this side is connected with the flexible band between both ends, be connected with the control mechanism of its swing angle of control between two swinging arms, the swinging arms swing can carry out the centre gripping to the nose, simultaneously with the middle extrusion of lip both sides, contract the lip and breathe, when the swinging arms swing and keep away from nose and lip, flexible band and lip laminating, shelter from the lip.

8. The COPD respiratory monitoring device of claim 7, wherein the control mechanism comprises a limiting rod and a pusher, the limiting rod is positioned between the included angles of the two swinging rods towards the side of the face, the two ends of the limiting rod are respectively connected with the two swinging rods in a sliding manner, the output end of the pusher is fixedly connected with the limiting rod, the output end of the pusher is perpendicular to the limiting rod, and the pusher is installed on the positioning frame.

9. The COPD respiratory monitoring device of claim 7 wherein a push plate is fixedly connected to each end of said oscillating rod, said push plate having a flexible protective layer thereon.

10. The COPD respiration monitoring apparatus of claim 7 further comprising an alarm, an input of the alarm being connected to an output of the respiration monitoring mechanism, the alarm being for emitting an alarm signal.

Background

Acute Exacerbation of Chronic Obstructive Pulmonary Disease (AECOPD) is defined as an acute exacerbation of respiratory symptoms, is a key stage of the course of Chronic Obstructive Pulmonary Disease (COPD) and is also a main factor determining the health condition and prognosis of COPD patients.

Most reports report that chronic obstructive pulmonary patients develop 0.5-3.5 acute exacerbations per year. In some studies, patients with AECOPD have a hospitalization mortality rate of 8.3% and a total three-year mortality rate of 49%. The respiratory muscle load-volume imbalance of AECOPD patients during hospitalization is easy to cause Type II respiratory failure (T2 RF), which causes hypoventilation, carbon dioxide retention and hypercapnia of patients, is one of the important complications of COPD patients, the disease course of which can be very rapid, seriously threatens the life health of patients, and is one of the main causes of death of patients suffering from chronic obstructive pulmonary acute exacerbation.

In recent years, machine learning has been increasingly used in the medical field, and results have been produced. In the prior art, a machine learning method is utilized to predict AECOPD and related events thereof, or the occurrence of respiratory failure is predicted, for example, Sanchez-Morillo D and the like utilize a K-means method to establish an early prediction COPD acute exacerbation model; bolouurani S et al predict the occurrence of respiratory failure after lobectomy using a random forest method modeling, but there is currently no study on predicting the occurrence of T2RF in AECOPD patients using machine learning methods. Some scholars at home and abroad find and prove that certain inspection indexes have certain significance for predicting respiratory failure of patients with chronic obstructive pulmonary disease, but the problems of single index, no establishment of a feasible prediction model and the like exist.

Disclosure of Invention

The invention aims to provide a prediction system and a monitoring device for COPD acute exacerbation complicated respiratory failure, which can predict whether a patient has T2RF or not, screen collected sample data and improve the prediction accuracy.

In order to achieve the purpose, the basic scheme of the invention is as follows: a system for predicting acute exacerbation of COPD and respiratory failure, comprising:

a data acquisition module for acquiring clinical case data of a sample;

the data processing module is used for receiving the data information acquired by the data acquisition module, performing statistical analysis on the data information and acquiring variable parameters;

the risk factor acquisition module is used for receiving the variable parameters, carrying out regression analysis on the variable parameters and screening to obtain independent risk factors;

and the prediction module is used for receiving the independent risk factors, taking the independent risk factors as input parameters of a machine learning algorithm, establishing a machine learning prediction model by taking whether T2RF occurs as an ending event, and predicting the received data of the person to be measured by using the machine learning prediction model.

The working principle and the beneficial effects of the basic scheme are as follows: the data acquisition module can acquire clinical case data of a sample and perform subsequent prediction operation by using the acquired data. The data processing module is used for preprocessing and statistically analyzing the data, primarily screening meaningful data, removing meaningless data, simplifying data types and facilitating the data operation of a subsequent prediction module. The risk factor acquisition module can further screen the preliminarily screened data, so that the predicted data type is more accurate, unnecessary calculation operation is avoided, and the running speed of the prediction module is increased. The independent risk factors are utilized to predict whether the patient has T2RF, the operation is simple and convenient, and the timely judgment on whether the patient has T2RF is realized, so that the patient can be treated timely.

The data processing system further comprises a data filling module, wherein the input end of the data filling module is connected with the output end of the data acquisition module, the data filling module fills data with the loss rate of less than or equal to 30% by adopting a missForest algorithm, and the output end of the data filling module is connected with the input end of the data processing module.

Data collection or storage failure caused by mechanical reasons or human reasons causes data loss, a loss value is generated, authenticity of the data cannot be guaranteed due to the loss value in the data, and therefore the data needs to be filled up, and reliability of the data is enhanced. And the data with too large missing rate has lower authenticity, does not have filling value and can be directly eliminated.

Further, the system also comprises a model evaluation module, wherein the model evaluation module is internally stored with quota evaluation parameters: the model evaluation module acquires corresponding data of the prediction model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the prediction model according to the comparison difference value.

And evaluating each item of data of the prediction module by using the model evaluation module so as to judge the operational performance of the prediction module, so that the prediction module is optimized at a later period, and meanwhile, the reliability of the prediction module is judged.

Further, the independent risk factors include lymphocyte count, creatinine, erythrocyte distribution width variation coefficient, mean hemoglobin concentration, mean platelet volume, percentage of basophils, urea, glutamic-pyruvic transaminase, and time to disease.

The relevance between the factors and whether the patient has T2RF is high, and the prediction module judges whether T2RF occurs according to the risk factors only, so that the judgment accuracy is higher.

Furthermore, an LASSO model and a multi-factor logistic regression analysis model are arranged in the risk factor acquisition module, variable parameters are firstly input into the LASSO model, variables output after the LASSO model enter the multi-factor logistic regression analysis model, and the multi-factor logistic regression analysis model outputs independent risk factors.

The LASSO model is combined with the multi-factor logistic regression analysis model, the operation precision is high, and the use is facilitated.

Further, the objective function of the LASSO algorithm:

wherein, independent variableFor each oneIs provided withDenotes the sample number, i is 1,2, …, m is the total number of samples, j denotes the independent variable, j is 1,2, …, n, m, n are all positive integers, y_iIs a dependent variable, b is an error term, and the regression coefficient w is (w)₁，w₂，…，w_n)^TAnd lambda is a regulating parameter,an L1 penalty term representing the regression coefficient w;

multifactor Logistic regression analysis:

wherein, independent variableDenotes a sample number, n denotes a total independent variable, Y ∈ {0, 1} denotes a dependent variable, and a regression coefficient β ═ β (β)⁽¹⁾，β⁽²⁾，…，β⁽ⁿ⁾，b)^TB is an offset, and α · β is the inner product of α and β.

The LASSO model and the multi-factor logistic regression analysis model are combined, so that independent risk factors are screened, and the accuracy of screening the independent risk factors is better.

The invention also provides a COPD respiration monitoring device, which comprises the prediction system, a respiration monitoring mechanism and a head-wearing respiration training mechanism;

the starting end of the respiration monitoring mechanism is connected with the output end of the prediction system, the respiration monitoring mechanism is used for collecting the respiration frequency of a patient and a respiration image of the patient, and the output end of the respiration monitoring mechanism is connected with a memory and is used for storing collected information;

the training mechanism is breathed to wear-type includes locating rack and two swinging arms, the middle part of two swinging arms is installed on the locating rack through the pivot, the swinging arms rotates with the pivot to be connected, two swinging arms cross arrangement, the tip of two swinging arms one side is located one side of human nose respectively, the tip of two swinging arms opposite sides is located the side of human mouth angle respectively, and this side is connected with the flexible band between both ends, be connected with the control mechanism of its swing angle of control between two swinging arms, the swinging arms swing can carry out the centre gripping to the nose, simultaneously with the middle extrusion of lip both sides, contract the lip and breathe, when the swinging arms swing and keep away from nose and lip, flexible band and lip laminating, shelter from the lip.

When the prediction system predicts that the patient is likely to have T2RF, the respiration monitoring mechanism is started to monitor the respiratory frequency of the patient in real time, and simultaneously acquire the image information of the patient, so that medical personnel can check the condition of the patient at any time, and when the patient is in an abnormal condition, treatment measures can be taken in time.

The head-mounted breathing training mechanism can assist a patient in lip contraction breathing training and help the patient to reduce the probability of respiratory failure. The lip contraction breathing prolongs the expiration time through weak resistance formed by the lip contraction breathing, increases the pressure of the airway, and delays the collapse of the airway. The patient ventilates nasally with the mouth closed, then slowly exhales through the constricted lips (whistling), while contracting the abdomen. When the patient breathes in, the tip of two swinging arms is located the side of patient's nose head and lip respectively, and the flexible band is laminated with the lip, hinders the patient lip and breathes in, and supplementary patient only adopts the nasal cavity to breathe in. When the patient exhales, the two swinging rods swing to simultaneously clamp the nose head part and the lips of the patient, so that the nasal cavity of the patient is closed, the lips of the patient contract when being squeezed, and the flexible belt assists the lip contraction and exhalation of the patient.

Further, control mechanism includes gag lever post and pusher, the gag lever post is located between the contained angle of two swinging arms orientation face side, the both ends of gag lever post respectively with two swinging arms sliding connection, the output and the gag lever post fixed connection of pusher, the output perpendicular to gag lever post of pusher, pusher install on the locating rack.

The pusher controls the limiting rod to move, the limiting rod moves, and the angle between the two swinging rods is changed, so that the nose and the lips are clamped and loosened by the swinging rods, the structure is simple, and the operation is facilitated.

Furthermore, the equal fixedly connected with of tip of swinging arms bulldozes the board, is equipped with flexible protective layer on bulldozing the board.

Set up and bulldoze the board, bulldoze the board and compare with the tip of swinging arms, the area that bulldozes the board is bigger, then bulldoze the board and the area of contact of nose or lip bigger, more do benefit to and bulldoze nose or lip, and the flexible inoxidizing coating can avoid bulldozing the board and carry out the rigidity bulldoze and harm the human body to the human body.

Further, the respiration monitoring device also comprises an alarm, wherein the input end of the alarm is connected with the output end of the respiration monitoring mechanism, and the alarm is used for sending out an alarm signal.

When the breathing monitoring mechanism detects that the abnormal condition of the patient occurs, the breathing monitoring mechanism outputs a control signal to the alarm, and the alarm sends out an alarm signal.

Drawings

FIG. 1 is a schematic flow diagram of a system for predicting acute exacerbation of COPD complicated by respiratory failure in accordance with the present invention;

FIG. 2 is a schematic representation of a LASSO regression model of the prediction system for COPD acute exacerbation concurrent respiratory failure of the present invention;

fig. 3 is a front view schematic diagram of a head-mounted respiratory training mechanism of a COPD respiratory monitoring apparatus of the present invention.

Reference numerals in the drawings of the specification include: the device comprises a swing rod 1, a rotating shaft 2, a pushing plate 3, a sliding groove 4, a limiting rod 5 and an output end 6 of a pusher.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.

In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.

In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.

As shown in FIG. 1, the invention discloses a prediction system for COPD acute exacerbation complicated respiratory failure, which comprises a data acquisition module, a data processing module, a risk factor acquisition module and a prediction module.

The data acquisition module is used for acquiring clinical case data of a sample and acquiring 2864 electronic medical records of a patient suffering from chronic obstructive pulmonary acute exacerbation. Based on the hospitalized blood gas analysis, 388 patients meeting the criteria for type II respiratory failure were assigned to the T2RF group (case group) and the remaining 2476 patients were assigned to the T2-free 2RF group (control group), excluding the index of > 30% missing values.

The data processing module is used for receiving the data information acquired by the data acquisition module, performing statistical analysis on the data information and acquiring variable parameters. Statistical analysis is carried out on the data by adopting SPSS 24.0 and R3.6.1, and missForest algorithm is used for filling indexes with the loss rate less than or equal to 30%. Normally distributed metrology data toIt shows that the mean value comparison between two groups adopts independent sample t test, which is also called Student's t test,mainly for small sample contents (e.g. n)<30) The overall standard deviation σ is an unknown normal distribution. The non-normally distributed metric is represented by M (Q)_L，Q_U) It is shown that the Mann-Whitney U test (Mann-Whitney rank sum test), which is one of the nonparametric tests, was used for the comparison between the two groups, assuming that the two samples are respectively from two populations that are identical except for the mean of the populations, in order to test whether the mean values of the two populations differ significantly. The counting data is represented by frequency or rate, and X2 test (chi-square test) is adopted for comparison between two groups, and is a hypothesis test method, and the basic formula of the test is as follows:

a is an actual number, T is a theoretical number deduced according to a test hypothesis, and the obtained characteristic parameters are shown in Table 1. The measurement data is data of blood pressure, height and the like, and the data can be directly used for measuring the size. The counting data is data such as gender and whether hypertension exists, and is used for measuring the number of the data. The single factor analysis results in statistics show that the difference between 20 indexes such as neutrophil count, basophil count and the like in a case group and a control group has statistical significance, and whether the difference between 13 indexes such as smoking and white blood cell count has no statistical significance is shown in table 1.

TABLE 1 statistical analysis of the T2 RF-related indices associated with AECOPD in case and control groups

And the risk factor acquisition module is used for receiving the variable parameters, carrying out regression analysis on the variable parameters and screening to obtain independent risk factors. Independent risk factors include lymphocyte count, creatinine, coefficient of variation of erythrocyte distribution width, mean hemoglobin concentration, mean platelet volume, percentage of basophils, urea, glutamate pyruvate transaminase, and duration of illness. The risk factor obtaining module is internally provided with an LASSO model and a multi-factor logistic regression analysis model, variable parameters (namely the 20 indexes) are firstly input into the LASSO model, and when 11 variables are obtained through screening, a model with the best effect is obtained, as shown in FIG. 2. The 11 variables output after the LASSO model are input into the multi-factor logistic regression analysis model, the multi-factor logistic regression analysis model outputs independent risk factors, and the obtained 10 indexes (namely the independent risk factors) have statistical significance as shown in Table 2.

TABLE 2 AECOPD concurrent T2RF multifactor logistic regression results

Predictor	OR(95％CI)	P value	B	VIF
					BASO ratio	0.570(0.335-0.970)	0.038	-0.062	1.104
MCV	1.040(1.019-1.062)	<0.001	0.004	1.090
					MPV	0.898(0.828-0.974)	0.009	-0.013	1.031
LYMPH count	0.356(0.276-0.460)	<0.001	-0.063	1.054
					RDW-CV	0.941(0.915-0.968)	<0.001	-0.003	1.110
MCHC	1.018(1.010-1.025)	<0.001	0.002	1.071
					CREA	0.980(0.973-0.987)	<0.001	-0.002	1.461
ALT	1.001(1.000-1.002)	0.016	0.000	1.103
					UA	1.089(1.035-1.145)	0.001	0.011	1.512
Duration of disease	1.059(1.049-1.070)	<0.001	0.008	1.013

Objective function of LASSO algorithm:

wherein, independent variableFor each oneIs provided withDenotes the sample number, i is 1,2, …, m is the total number of samples, j denotes the independent variable, j is 1,2, …, n, m, n are all positive integers, y_iIs a dependent variable, b is an error term, and the regression coefficient w is (w)₁，w₂，…，w_n)^TAnd lambda is a regulating parameter,an L1 penalty term representing the regression coefficient w;

multifactor Logistic regression analysis:

wherein, independent variableDenotes a sample number, n denotes a total independent variable, Y ∈ {0, 1} denotes a dependent variable, and a regression coefficient β ═ β (β)⁽¹⁾，β⁽²⁾，…，β⁽ⁿ⁾，b)^TB is an offset, and α · β is the inner product of α and β.

The prediction module is used for receiving the independent risk factors, taking the independent risk factors as input parameters of a machine learning algorithm, establishing a machine learning prediction model by taking whether T2RF occurs as an ending event, and predicting the received data of the person to be measured by using the machine learning prediction model. Dividing 2864 samples into a training set (2004) and a testing set (860) through a random number table, wherein the training set is used for variable screening and model construction and comprises 268 cases (13%) of a case group and 1736 cases (87%); the test set was used to verify model performance and contained 120 cases in the case group and 740 cases in the control group. The training set is used for training and establishing a model, the testing set is used for verifying the performance of the model, and AUC is used as a model performance judgment standard.

In a preferred mode of the present invention, the prediction system further includes a data padding module. The input end of the data filling module is connected with the output end of the data acquisition module, the data filling module fills data with the missing rate of less than or equal to 30% by adopting a missForest algorithm, and the output end of the data filling module is electrically connected with the input end of the data processing module.

In a preferred embodiment of the present invention, the prediction system further includes a model evaluation module, and the model evaluation module stores a quota evaluation parameter: the model evaluation module acquires corresponding data of the prediction model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the prediction model according to the comparison difference value.

The invention also provides a COPD respiratory monitoring device comprising the prediction system of the invention, a respiratory monitoring mechanism and a head-mounted respiratory training mechanism.

The starting end of the respiration monitoring mechanism is connected with the output end of the prediction system, the respiration monitoring mechanism is used for collecting the respiratory frequency of a patient and the respiratory image of the patient, and the output end of the respiration monitoring mechanism is electrically connected with a memory and used for storing collected information. The respiration monitoring mechanism comprises a respiration frequency sensor and a camera, and the output end of the camera can be electrically connected with the display screen and is used for displaying images.

As shown in fig. 3, the head-mounted respiration training mechanism includes a positioning frame (not shown) on which the respiration monitoring mechanism can be mounted and two swing levers 1. The middle parts of the two swing rods 1 are arranged on a positioning frame through a rotating shaft 2, the swing rods 1 are rotatably connected with the rotating shaft 2, and the rotating shaft 2 is welded on the positioning frame. Two swing rods 1 are arranged in a crossed manner, the end part of one side of each of the two swing rods 1 is located on one side of the nose of a human body, the end part of the other side of each of the two swing rods 1 is located on the side edge of the mouth corner of the human body, a flexible belt is connected between the two end parts of the side, the two ends of the flexible belt are fixedly connected (such as welding, bonding and the like) with the end parts of the swing rods 1 located on the two sides of the mouth corner, and the swing rods 1 can be arc-shaped rods with the two ends bent towards the middle part. Preferably, the end parts of the swing rods 1 are fixedly connected with push plates 3, the push plates 3 are located below the swing rods 1, and flexible protective layers are arranged on the push plates 3.

A control mechanism for controlling the swing angle of the two swing rods 1 is connected between the two swing rods 1 and comprises a limiting rod 5 and a pusher, and the control mechanism can be arranged on one side or two sides of the two swing rods 1. Spacing rod 5 is located between the contained angle of two swinging arms 1 orientation face side, and the both ends of spacing rod 5 respectively with two swinging arms 1 sliding connection, if seted up spout 4 on the sliding rod, and the both ends fixed connection of spacing rod 5 or universal articulated have the slider, slider and 4 sliding connection of spout. Output 6 and gag lever post 5 fixed connection of pusher, 6 perpendicular to gag lever post 5 of output of pusher, the pusher is installed on the locating rack, and cylinder or pneumatic cylinder etc. can be chooseed for use to the pusher.

When the patient breathes in, the tip of two swinging arms 1 is located patient nose both sides and lip both sides respectively, and the flexible band shelters from the lip with the lip laminating, hinders the patient lip and breathes in, and supplementary patient only adopts the nasal cavity to breathe in. When the patient exhales, the two swing rods 1 swing to simultaneously clamp the nose head part and the lips of the patient, so that the nasal cavity of the patient is closed, the lips of the patient contract when being squeezed, and the flexible band assists the lip contraction and exhalation of the patient.

In a preferred mode of the present invention, the COPD respiration monitoring apparatus further comprises an alarm (not shown), an input end of the alarm is electrically connected to an output end of the respiration monitoring mechanism, and the alarm is configured to send an alarm signal. The alarm can be selected from a buzzer, an LED lamp and the like, and can be arranged on a positioning frame or in the office area of medical staff.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.