TWI777833B - Method of predicting chronic kidney disease and system thereof - Google Patents

Abstract

A method of predicting chronic kidney disease is disclosed in the present invention. The method includes the following steps: establishes a prediction rule, wherein the prediction rule has a breath ammonia threshold value; obtains an exhaled breath of a user; compares the exhaled breath concentration and the breath ammonia threshold value; and generates alerted information when the exhaled breath concentration is higher than the breath ammonia threshold value, wherein the alerted information represents that the user is suspected of having chronic kidney disease.

Description

Chronic kidney disease prediction method and system

The present invention relates to a method and system, especially a method and system for predicting chronic kidney disease.

Chronic Kidney Disease (CKD) is a serious public health problem, not just in Taiwan, but with an increasing morbidity and often irreversible damage worldwide. In addition, chronic kidney disease not only causes End Stage Renal Disease (ESRD), but is also an important factor in causing death and cardiovascular disease. Therefore, the problem of chronic kidney disease has been paid more and more attention in the world. Regular checks of functionality are required. However, due to the low awareness rate of patients with chronic kidney disease, the high prevalence of chronic kidney disease, and the absence of symptoms in the early stage of chronic kidney disease, most patients do not notice it. When patients begin to have related symptoms, they often have entered the middle and late stages of chronic kidney disease.

Regular examinations for chronic kidney disease in the prior art mainly include urine tests, blood draws, X-ray examinations, intravenous pyelography (IVP), Computed Tomography (CT), renal ultrasound, renal Slices and other methods, especially clinically, use blood to detect serum creatinine (serum creatinine) concentration and then use formula to derive estimated glomerular filtration rate (estimated Glomerular Filtration Rate; eGFR).

However, the inspection method is too professional and involves invasive medical behaviors, which makes it difficult for patients to develop the habit of regular inspections, and is extremely inconvenient for areas where medical resources are not widely available, those who are inconvenient to seek medical care, and those who have difficulty in drawing blood. In addition, the global epidemic is severe, and patients will not want to go to high-risk areas such as medical institutions without relevant symptoms. Therefore, there is room for improvement in the prior art.

In view of the problem that in the prior art, the regular examination items for chronic kidney disease are too professional and invasive medical behaviors are not easy for patients to develop the habit of regular examinations. It is extremely inconvenient for people who have difficulty in drawing blood, and the problem that patients do not want to go to high-risk areas such as medical institutions for related examinations under severe epidemic conditions. One of the main objectives of the present invention is to provide a method for predicting chronic kidney disease to solve at least one problem in the prior art.

In order to solve the problem of the prior art, the necessary technical means adopted by the present invention is to provide a method for predicting chronic kidney disease, which includes the following steps: establishing a database, storing a prediction rule in the database, and defining at least one prediction rule in the prediction rule Threshold value of exhaled ammonia concentration; obtain one of the exhaled air of a screener; sense one of the exhaled air to measure the measured exhaled ammonia concentration; compare the measured exhaled ammonia concentration with the threshold value of exhaled ammonia concentration, When the gas ammonia concentration is greater than the threshold value of the exhaled ammonia concentration, it is judged that the prediction rule is met, and a warning information is generated, and the warning information represents that one of the screening results of the screening person is suspected of having chronic kidney disease.

On the basis of the above-mentioned necessary technical means, a subsidiary technical means derived from the present invention is a step in the method for predicting chronic kidney disease, further comprising the following steps: receiving a plurality of measured breath ammonia concentrations of a plurality of subjects. With a plurality of kidney disease diagnosis results, a preset threshold value is set, the measured exhaled ammonia concentration is compared with the preset threshold value, and multiple kidney disease prediction results are generated; the kidney disease prediction results are compared with the kidney disease diagnosis results. A comparison is performed to obtain a sensitivity and a specificity under the judging benchmark with the preset threshold value; the preset threshold value is adjusted, and the above steps are repeated until the sensitivity and the judging benchmark based on the preset threshold value are When the specificity reaches an acceptable condition, the preset threshold value is defined as a first threshold value among the threshold values of exhaled ammonia concentration.

On the basis of the above-mentioned necessary technical means, a subsidiary technical means derived from the present invention is a step in the method for predicting chronic kidney disease, further comprising the following steps: receiving a plurality of measured breath ammonia concentrations of a plurality of subjects. With a plurality of kidney disease diagnosis results, a preset threshold value is set, the measured exhaled ammonia concentration is compared with the preset threshold value, and multiple kidney disease prediction results are generated; the kidney disease prediction results are compared with the kidney disease diagnosis results. Carry out a comparison, so as to count a sensitivity and a specificity under the judgment standard with the preset threshold value; adjust the preset threshold value, and repeat the above steps until a plurality of the above-mentioned preset threshold values are under the judgment basis When the above-mentioned sensitivity and above-mentioned specificity reach an acceptable condition, the preset threshold value is defined as a first threshold value and a second threshold value among the threshold values of exhaled ammonia concentration, and the first threshold value corresponds to a first threshold value. In the age interval, the second threshold value is smaller than the first threshold value and corresponds to a second age interval, and a first age lower limit value of the first age interval is greater than a second age upper limit value of the second age interval.

On the basis of the above necessary technical means, an auxiliary technical means derived from the present invention is a step in the method for predicting chronic kidney disease, further comprising the following steps: using a first pipeline and a pump to transport the exhaled gas to a drying cylinder; drying the exhaled gas by using the drying cylinder; using a second pipeline and a pump to transport the exhaled gas to a container; using a container to hold the exhaled gas after drying.

On the basis of the above-mentioned necessary technical means, an auxiliary technical means derived from the present invention is to use a third pipeline and a pump after the steps in the method for predicting chronic kidney disease, and further include the following steps: using a third pipeline and a pump to remove the exhaled gas from the container send out.

On the basis of the above-mentioned necessary technical means, an auxiliary technical means derived from the present invention is a step in the method for predicting chronic kidney disease, further comprising the following steps: using an ammonia sensing module to sense the measured exhaled ammonia in exhaled air concentration.

On the basis of the above-mentioned necessary technical means, an auxiliary technical means derived from the present invention is a method for predicting chronic kidney disease, further comprising the following steps: displaying warning information by using a display module.

In order to solve the problems of the prior art, the necessary technical means adopted by the present invention is to provide a chronic kidney disease prediction system, which includes a database, an acquisition module, an ammonia sensing module, a comparison module and an early warning module Group. The database stores a prediction rule, and at least one threshold value of exhaled ammonia concentration is defined in the prediction rule. The acquisition module acquires the exhaled breath of one of the screeners. The ammonia sensing module is used for sensing one of the measured exhaled ammonia concentration in exhaled air. The comparison module is electrically connected to the database and the ammonia sensing module to compare the measured exhaled ammonia concentration and the threshold value of exhaled ammonia concentration, and when the measured exhaled ammonia concentration is greater than the threshold value of exhaled ammonia concentration, it is judged that it is in line with the prediction rule. The early warning module is electrically connected to the comparison module, and is used for generating early warning information when the prediction rule is met, and the early warning information represents that a preliminary screening result of one of the screening persons is suspected of suffering from chronic kidney disease.

On the basis of the above-mentioned necessary technical means, an auxiliary technical means derived from the present invention is that the chronic kidney disease prediction system further includes a display module, which is electrically connected to the early warning module for displaying early warning information.

On the basis of the above necessary technical means, an auxiliary technical means derived from the present invention is that the database in the chronic kidney disease prediction system includes a receiving unit, a setting unit, a first comparison unit, a second A comparison unit, a statistical unit, a definition unit and a storage unit. The receiving unit is used for receiving a plurality of measured breath ammonia concentrations and a plurality of kidney disease diagnosis results of a plurality of subjects. The setting unit is used for setting and adjusting a preset threshold value. The first comparison unit is electrically connected to the receiving unit and the setting unit, and compares the measured exhaled ammonia concentration with a preset threshold to generate a plurality of kidney disease prediction results. The second comparison unit is electrically connected to the receiving unit and the first comparison unit, and is used to compare the kidney disease prediction result with the kidney disease diagnosis result; the statistics unit is electrically connected to the second comparison unit, so as to calculate the predetermined The critical value is a sensitivity and a specificity under the judgment criteria. The defining unit is electrically connected to the statistical unit, and is used to define the preset threshold as the threshold of exhaled ammonia concentration in the prediction rule when the sensitivity and specificity reach an acceptable condition. The storage unit is electrically connected to the definition unit for storing the prediction rule.

Based on the above, the present invention uses the acquired exhaled gas of the screener for prediction, and when the measured exhaled ammonia concentration is greater than the threshold value of exhaled ammonia concentration, it is determined that the screener is suspected of suffering from chronic kidney disease. Compared with the existing and derived problems of the prior art requiring the use of invasive medical behaviors such as blood drawing, the present invention utilizes the exhaled gas of the screener for sensing and non-invasive rapid kidney function screening prediction, which can achieve Quickly, conveniently and inexpensively screen out those who need to pay attention to renal function, so as to prevent and treat early chronic kidney disease. In addition, the present invention can also define a first threshold value and a second threshold value in the threshold value of exhaled ammonia concentration for groups of different ages, so as to achieve the same prediction effect for groups of different ages.

The specific embodiments of the present invention will be described in more detail below with reference to the schematic diagrams. The advantages and features of the present invention will become more apparent from the following description and the scope of the claims. It should be noted that the drawings are all in a very simplified form and use inaccurate scales, and are only used to facilitate and clearly assist the purpose of explaining the embodiments of the present invention.

Please refer to the first to the second B, wherein the first is a block diagram showing the chronic kidney disease prediction system provided by the preferred embodiment of the present invention; and, the second A and the second B are the The flow chart of the method for predicting chronic kidney disease provided by the preferred embodiment of the invention. A method for predicting chronic kidney disease includes the following steps S101 to S113. A chronic kidney disease prediction system 1 can be used to implement the above-mentioned chronic kidney disease prediction method, and includes a database 11 , an acquisition module 12 , an ammonia sensing module 13 , a comparison module 14 and an early warning module 15 .

Step S101 : Receive the measured breath ammonia concentration and the diagnosis result of kidney disease of the tested subject.

Step S102: Set a preset threshold value, compare the measured breath ammonia concentration with the preset breath ammonia concentration threshold value, and generate a plurality of kidney disease prediction results.

Step S103 : Comparing the kidney disease prediction result with the kidney disease diagnosis result, so as to calculate the sensitivity and specificity based on the predetermined threshold value.

Step S104: Adjust the preset threshold value, and repeat the above steps.

Step S105 : when the sensitivity and specificity reach acceptable conditions, define the preset threshold value as the threshold value of exhaled ammonia concentration.

The database 11 stores a prediction rule, and at least one threshold value of exhaled ammonia concentration is defined in the prediction rule.

Step S106: Obtain the exhaled breath of the screener.

The obtaining module 12 obtains an exhaled breath of a screening person.

The acquisition module 12 may include a first pipeline, a pump, a drying cylinder, a second pipeline and a container. The pump makes the exhaled gas enter the drying cylinder through the first pipeline, and the exhaled gas is dried by the drying cylinder. Then, the pump makes the exhaled gas enter the container through the second pipeline, and is contained in the container, but not limited thereto. In other embodiments of the present invention, the acquisition module 12 may also include other components or devices that can acquire the exhaled breath of the screening person.

Step S107 : use the ammonia sensing module to sense the measured exhaled ammonia concentration of exhaled air.

The ammonia sensing module 13 is used for sensing a measured exhaled ammonia concentration of exhaled air. The ammonia sensing module 13 may be a sensing chip, a sensing device or other modules capable of sensing ammonia concentration.

In this embodiment, the acquisition module 12 may further include a third pipeline. After the ammonia sensing module 13 senses the measured exhaled ammonia concentration, the pumping causes exhaled air to be delivered from the container through the third pipeline.

Step S108: Compare the measured exhaled ammonia concentration with the threshold value of exhaled ammonia concentration.

Step S109: Whether the measured breath ammonia concentration is greater than the threshold value of breath ammonia concentration.

The comparison module 14 is electrically connected to the database 11 and the ammonia sensing module 13 for comparing the measured breath ammonia concentration with the threshold value of the breath ammonia concentration, and when the measured breath ammonia concentration is greater than the threshold value of the breath ammonia concentration, The judgment conforms to the prediction rule.

When it is judged as YES in step S109, it goes to step S110; and when it is judged as NO in step S109, it goes to step S112.

Step S110 : generating early warning information, and the warning information represents that the preliminary screening result of the screening person is suspected of suffering from chronic kidney disease.

Step S111 : display the warning information by using the display module.

In this embodiment, the chronic kidney disease prediction system 1 further includes a display module 16 . The display module is used for displaying early warning information, wherein the early warning information represents that the first screening result of the screening person is suspected of suffering from chronic kidney disease. Therefore, the present invention can utilize the non-invasive medical behavior of exhalation to achieve the effect of screening and predicting that the screening persons are suspected of suffering from chronic kidney disease, thereby achieving early prevention and treatment of chronic kidney disease.

Step S112: Generate matching information, and the matching information represents the matching result of the screener.

Step S113: Display the comparison information by using the display module.

In addition, in this embodiment, the chronic kidney disease prediction system 1 further includes an information generating module 17 . The information generation module 17 generates comparison information when the measured breath ammonia concentration is not greater than the threshold value of the breath ammonia concentration, wherein the comparison information represents the difference between the measured breath ammonia concentration of the screener and the threshold value of the breath ammonia concentration. The comparison result can be displayed by the display module 16 . Therefore, in the case that the screening results of the screeners are not suspected of having chronic kidney disease, the screeners can also know the relationship between the actual measured breath ammonia concentration and the threshold value of breath ammonia concentration. When it is shown that the measured exhaled ammonia concentration is very close to the threshold value of exhaled ammonia concentration, the screener can also be alerted.

Next, please refer to the first to sixth figures together; the third figure is a graph showing the measured breath ammonia concentration and blood urea ammonia concentration; the fourth figure shows the measured breath ammonia concentration and serum muscle concentration The graph of acid anhydride concentration; the fifth graph is a graph showing the measured exhaled ammonia concentration and the estimated glomerular filtration rate; the sixth graph is a graph showing the comparison of the measured exhaled ammonia concentration and different stages of chronic kidney disease. As shown in the figure, the database 11 includes a receiving unit 111 , a setting unit 112 , a first comparison unit 113 , a second comparison unit 114 , a statistics unit 115 , a definition unit 116 and a storage unit 117 .

The receiving unit 111 receives a plurality of measured breath ammonia concentrations and a plurality of kidney disease diagnosis results of a plurality of subjects. The diagnosis results of kidney disease usually include the blood urea ammonia (Blood Urea Nitrogen; BUN) concentration, serum creatinine (serum creatinine) concentration, estimated glomerular filtration rate (eGFR), age, gender and other information.

At present, the most widely used and accepted indicator of renal function is the glomerular filtration rate (GFR). Either the glomerular filtration rate or the estimated glomerular filtration rate is relevant. In addition, with the deterioration of renal function, the concentration of urea ammonia in the blood will also increase.

Chronic kidney disease is divided into five stages based on estimated glomerular filtration rate, with eGFR greater than 90 mL/min as the first stage; eGFR between 60 and 90 mL/min as the second stage; eGFR between 30 and 60 mL/min Stage 3; eGFR between 15 and 30 mL/min is Stage 4; and eGFR less than 15 mL/min is Stage 5.

The inventors of the present application collected the measured breath ammonia concentration and the diagnosis results of kidney disease of a plurality of subjects, wherein the subjects included patients with chronic kidney disease stage I to stage V.

It can be clearly seen from the third figure that there is a good positive correlation between the measured breath ammonia concentration and the blood urea ammonia concentration. Breath ammonia concentration and blood urea ammonia concentration, R=0.723, p<0.001.

It can be clearly seen from the fourth figure that the measured breath ammonia concentration and serum creatinine concentration also have a good positive correlation. Among them, from a statistical point of view, the measured breath in the fourth figure Ammonia concentration and serum creatinine concentration, R=0.735, P<0.001.

Therefore, the inventor deduced from the most widely used and accepted indicators of renal function, the third and fourth figures, that the measured exhaled ammonia concentration will also be related to eGFR, and it should be a good negative correlation. From the statistical chart in Figure 5, it can be clearly seen that there is indeed a negative correlation between the measured breath ammonia concentration and eGFR of the tested subjects. From a statistical point of view, the measured breath in Figure 5 Ammonia concentration and eGFR, R=-0.535, p<0.001. Therefore, the inventor's inference that the measured breath ammonia concentration would be related to eGFR was confirmed.

In addition, as can be seen from the sixth figure, the inventor can also clearly see that with the increase of the stage of chronic kidney disease, the measured breath ammonia of the tested subjects increases according to the stage of chronic kidney disease of the tested subjects. The concentrations were significantly increased. From a statistical point of view, the measured expiratory ammonia concentration of each period is compared with the measured exhaled ammonia concentration of the previous period, and there is a statistically significant increase, among which, the meaning of the symbols in the sixth figure is: * means p<0.05, ** means p<0.01, *** means p<0.001, **** means p<0.0001.

Next, please refer to Figure 1, Figure 2, Figure 7 and Figure 8 together, where Figure 7 shows the ROC curve of the first phase and the second to fifth phases by showing the default threshold at 974ppb And, the eighth figure is a ROC curve graph showing a preset threshold value of 1187ppb to distinguish eGFR<60mL/min.

The inventors used the receiver operating characteristic curve (Receiver operating characteristic; ROC) to find out the value that can distinguish the stage of chronic kidney disease, and found that the preset threshold value is 974ppb to distinguish the first stage of chronic kidney disease from the second to fifth stage. The area under the curve (AUC) was the largest in patients with stage 1 disease, where AUC=0.835, p<0.0001. At this time, the sensitivity was 69%, the specificity was 95%, the positive predictive rate was 0.99, and the negative predictive rate was 0.36.

With the increase of age, renal function will gradually decline, so the clinical application will define chronic kidney disease as eGFR<60mL/min. Therefore, the inventor also uses the receiver operating characteristic curve (Receiver operating characteristic; ROC) to find The value that can distinguish eGFR<60mL/min, and found that the preset critical value is 1187ppb to distinguish whether the patient eGFR<60mL/min, the area under the curve (Area Under Curve; AUC) is the largest, where, AUC=0.831, p <0.0001. At this time, the sensitivity was 71%, the specificity was 78%, the positive predictive rate was 0.84, and the negative predictive rate was 0.61.

Therefore, it can be confirmed again from the seventh figure and the eighth figure that the measured exhaled ammonia concentration of the subject has a significant correlation with the renal function of the subject.

The setting unit 112 is used for setting and adjusting a preset threshold value, that is, the setting unit 112 continuously adjusts the preset threshold value. The inventor of the present application adjusted the preset threshold value from 680ppb to 1246ppb.

The first comparing unit 113 is electrically connected to the receiving unit 111 and the setting unit 112, and compares the measured exhaled ammonia concentration with a preset threshold to generate a plurality of kidney disease prediction results.

The second comparing unit 114 is electrically connected to the receiving unit 111 and the setting unit 112 for comparing the kidney disease prediction result with the kidney disease diagnosis result.

The statistics unit 115 is electrically connected to the second comparison unit 114 , so as to calculate a sensitivity and a specificity based on the predetermined threshold value.

The defining unit 116 is electrically connected to the statistics unit 115, and is used to define the current preset threshold as the threshold value of exhaled ammonia concentration in the prediction rule when the sensitivity and specificity reach an acceptable condition. When the sensitivity and specificity of a plurality of preset thresholds reach acceptable conditions, the defining unit 116 defines a first threshold and a second threshold respectively among the thresholds of the breath ammonia concentration. In this embodiment, the acceptable condition is that the AUC value of the ROC curve formed by sensitivity and specificity is the largest, that is, the maximum value of the sum of sensitivity and specificity, but it is not limited to this, it can also be the AUC value Greater than a certain value, or the sensitivity is greater than a certain percentage, the specificity is greater than a certain percentage, the percentage of sensitivity plus specificity is greater than a certain percentage and other conditions.

Please refer to Table 1. Table 1 shows the sensitivity and specificity of eGFR<60 mL/min calculated by the statistical unit 115 after the setting unit 112 sets and adjusts different preset thresholds. Preset Threshold (ppb) Sensitivity Specificity 680 0.868 0.489 690 0.855 0.489 701 0.842 0.489 710 0.842 0.511 720 0.842 0.533 744 0.829 0.533 765 0.816 0.556 770 0.816 0.556 775 0.816 0.578 782 0.816 0.600 812 0.816 0.622 849 0.803 0.622 870 0.803 0.644 881 0.803 0.667 886 0.803 0.689 888 0.789 0.689 907 0.776 0.689 944 0.776 0.711 974 0.776 0.733 984 0.763 0.733 993 0.750 0.733 1056 0.737 0.733 1134 0.737 0.756 1188 0.737 0.778 1246 0.724 0.778 Table I

Because different preset cutoff values have sensitivity and specificity. As sensitivity increases, specificity decreases. In groups with high prevalence, false positives will be lower. Therefore, in screening for chronic kidney disease without immediate risk, sensitivity can be decreased to increase specificity, thereby reducing false positives. Therefore, according to the present invention, after the statistical result of adjusting the preset threshold value, the defining unit 116 defines a first threshold value among the threshold values of exhaled ammonia concentration to be 886ppb, and at this time, the sensitivity is greater than 80%. In the common knowledge in the art, screening for non-fatal diseases with a sensitivity of 80% is considered an acceptable screening method or screening tool.

When the measured exhaled ammonia concentration of the screener is greater than the first critical value in the expiratory ammonia concentration critical values, it is judged that the prediction rule is met. Therefore, the early warning module 15 will generate early warning information. In this embodiment, the display module 16 will display the warning information for the screening person or the relevant person to view, but not limited to this. In other embodiments of the present invention, the early warning information may also be transmitted to the mobile phone of the screener or a related person by means of a message for viewing.

Preferably, the defining unit 116 defines different thresholds among the thresholds of exhaled ammonia concentration for different groups. For example, because renal function gradually declines with increasing age, the elderly population should undergo further testing and treatment when eGFR < 60 mL/min, while the younger population should have an eGFR < 90 mL/min. , requires further testing and treatment. Therefore, the defining unit 116 can define a first threshold value and a second threshold value among the threshold values of breath ammonia concentration, wherein the first threshold value is for the elderly group, and the second threshold value is for the young group . In this embodiment, the defining unit 116 defines the first critical value as 886ppb (sensitivity is 80%, specificity is 69%), and defines the second critical value as 974ppb (specificity is 95%), wherein , the first critical value corresponds to a first age interval of the older group, the second critical value corresponds to a second age interval of the young group, and a first age lower limit of the first age interval will be greater than the second age A second upper age limit value of the interval. Therefore, the present invention has high sensitivity and high specificity for the screening prediction of chronic kidney disease that is not immediately life-threatening.

The storage unit 117 is electrically connected to the defining unit 116 for storing prediction rules. The comparison module 14 compares the measured exhaled ammonia concentration with the threshold value corresponding to the age of the screener according to the age of the screener (the older group corresponds to the first threshold value, and the younger group corresponds to the second threshold value). .

Finally, please refer to the first figure, the second figure and the ninth figure, wherein the ninth figure is a graph showing the actual screening prediction result of the present invention. The inventors used the present invention to perform screening prediction for 34 willing screeners, wherein all the screeners belonged to the elderly group. According to statistical analysis, the number of samples greater than 30 is representative.

The present invention defines the threshold value of exhaled ammonia concentration in the prediction rule according to the aforementioned method, obtains the exhaled air of each of 34 screeners, and senses the measured exhaled ammonia concentration in the exhaled air of the 34 screeners. When the measured exhaled ammonia concentration is greater than the first critical value (886ppb) of the expiratory ammonia concentration threshold, an early warning message is generated for the screener, and the early warning message indicates that the screening result of the screener is suspected of having chronic kidney disease sick.

After the screening test of the present invention predicts, there are six screeners whose expiratory ammonia concentration is greater than 886ppb, indicating that the screening test of the present invention predicts that there are six screeners who are suspected of suffering from chronic kidney disease. In fact, the eGFRs of the above six screeners were 21, 49, 49, 54, 79, and 82 mL/min, respectively. Among them, there were four screeners with eGFR < 60 mL/min, indicating that the above six were affected by the present invention. Of the six screeners whose screening predicted suspected CKD, four did have CKD. Among all the screeners, there are only the above four screeners with eGFR <60mL/min, and their measured exhaled ammonia concentrations are indeed greater than 886ppb. It means that the above four screeners who need immediate further examination and treatment are all screened out by the present invention.

It can be calculated from the ninth figure that the present invention has a sensitivity of 100% (4/4) and a specificity of 94% (29/31) for eGFR<60mL/min and the measured exhaled ammonia concentration greater than 886ppb, with a positive predictive rate of 94% (29/31). was 67% (4/6), and the negative predictive rate was 100% (29/29). Therefore, through the above screening prediction, it can be further confirmed that the present invention can indeed achieve the effect of early prevention and treatment of chronic kidney disease. In addition, based on common knowledge in the technical field, Figure 9 also uses thick black lines to indicate six screeners whose measured breath ammonia concentration is greater than 886ppb and twenty-nine screeners whose measured breath ammonia concentration is less than 886ppb the mean of the eGFR of the participants.

To sum up, the present invention uses the acquired exhaled gas of the screener for prediction, and when the measured exhaled ammonia concentration is greater than the threshold value of exhaled ammonia concentration, it is determined that the screener is suspected of suffering from chronic kidney disease. Compared with the existing and derived problems of the prior art requiring the use of invasive medical behaviors such as blood drawing, the present invention utilizes the exhaled gas of the screener for sensing and non-invasive rapid kidney function screening prediction, which can achieve Quickly, conveniently and inexpensively screen out those who need to pay attention to renal function, so as to prevent and treat early chronic kidney disease. In addition, the present invention can also define a first threshold value and a second threshold value in the threshold value of exhaled ammonia concentration for groups of different ages, so as to achieve the same prediction effect for groups of different ages.

Through the detailed description of the preferred embodiments above, it is hoped that the features and spirit of the present invention can be described more clearly, and the scope of the present invention is not limited by the preferred embodiments disclosed above. On the contrary, the intention is to cover various modifications and equivalent arrangements within the scope of the claimed scope of the present invention.

1: Chronic Kidney Disease Prediction System 11:Database 111: Receiver unit 112: Setting unit 113: The first comparison unit 114: Second comparison unit 115: Statistics Unit 116: Define Unit 117: Storage unit 12: Get mods 13: Ammonia sensing module 14: Compare Mods 15: Early warning module 16: Display module 17: Information generation module S101~S113: Steps

The first figure is a block diagram showing the chronic kidney disease prediction system provided by the preferred embodiment of the present invention; The second A and the second B are flowcharts showing the method for predicting chronic kidney disease provided by the preferred embodiment of the present invention; The third figure is a graph showing the measured breath ammonia concentration and blood urea ammonia concentration; The fourth panel is a graph showing the measured breath ammonia concentration and serum creatinine concentration; The fifth figure is a graph showing measured exhaled ammonia concentration and estimated glomerular filtration rate; The sixth figure is a graph showing the comparison of measured breath ammonia concentration and chronic kidney disease in different stages; Figure 7 shows the ROC curves of the first phase and the second to fifth phases with a preset threshold of 974ppb; The eighth figure is a ROC curve graph showing the preset threshold at 1187ppb to distinguish eGFR<60mL/min; and The ninth figure is a graph showing the actual screening prediction results of the present invention.

S101~S113: Steps

Claims (10)

A method for predicting chronic kidney disease, comprising the following steps: (a) establishing a database, wherein the database stores a prediction rule, and at least one threshold value of exhaled ammonia concentration is defined in the prediction rule; (b) using an acquisition module to acquire an exhaled breath of a screening subject; (c) using an ammonia sensing module to sense an actual measured exhaled ammonia concentration of the exhaled gas; (d) using a comparison module to detect the measured exhaled breath The gas ammonia concentration is compared with the at least one breath ammonia concentration threshold, and when the measured breath ammonia concentration is greater than the at least one breath ammonia concentration threshold, it is determined that the prediction rule is met, and an early warning module is used to generate An early warning information, and the early warning information represents that one of the screening results is suspected of having chronic kidney disease. The method for predicting chronic kidney disease according to claim 1, wherein the step (a) further comprises the following steps: (a1) using a receiving unit to receive a plurality of measured breath ammonia concentrations and a plurality of measured subjects For each kidney disease diagnosis result, a preset threshold value is set by a setting unit, and a first comparison unit is used to compare the measured breath ammonia concentrations with the preset threshold value to generate a plurality of kidney diseases Predicting results; (a2) using a second comparison unit to compare the kidney disease prediction results with the kidney disease diagnosis results, and use a statistical unit to calculate the predetermined threshold value under the judgment criterion a sensitive (a3) Use a definition unit to adjust the preset threshold value, and repeat the steps (a1) and (a2) until the sensitivity and the specificity are determined based on the preset threshold value. When the property reaches an acceptable condition, the predetermined threshold is defined as a first threshold of the at least one exhaled ammonia concentration threshold. The method for predicting chronic kidney disease according to claim 1, wherein the step (a) further comprises the following steps: (a1) using a receiving unit to receive a plurality of measured breath ammonia concentrations and a plurality of measured subjects For each kidney disease diagnosis result, a preset threshold value is set by a setting unit, and a first comparison unit is used to compare the measured breath ammonia concentrations with the preset threshold value to generate a plurality of kidney diseases Predicting results; (a2) using a second comparison unit to compare the kidney disease prediction results with the kidney disease diagnosis results, and use a statistical unit to calculate the predetermined threshold value under the judgment criterion a sensitivity and a specificity; (a3) use a definition unit to adjust the preset threshold value, and repeat the steps (a1) and (a2) until a plurality of the preset threshold values are used to determine the above-mentioned threshold value. When the sensitivity and the specificity reach an acceptable condition, the preset thresholds are defined as a first threshold and a second threshold in the at least one breath ammonia concentration threshold, the first threshold corresponds to a first age range, the second threshold is smaller than the first threshold and corresponds to a second age interval, and a first age lower limit value of the first age interval is greater than a second age upper limit value of the second age interval. The method for predicting chronic kidney disease as claimed in claim 1, wherein the step (b) further comprises the following steps: (b1) using a first pipeline and a pump to deliver the exhaled gas to a drying cylinder; (b2) Use the drying cylinder to dry the exhaled gas; (b3) use a second pipeline and the pump to transport the exhaled gas to a container; (b4) use the container to hold the dried exhaled gas. The method for predicting chronic kidney disease as claimed in claim 4, wherein the step (c) further comprises the following step: (e) using a third pipeline and the pump to deliver the exhaled gas from the container. The method for predicting chronic kidney disease as claimed in claim 1, wherein the step (c) further comprises the following step: (c1) using an ammonia sensing module to sense the measured exhaled ammonia concentration in the exhaled air. The method for predicting chronic kidney disease according to claim 1, further comprising the following steps: (e) displaying the warning information by using a display module. A chronic kidney disease prediction system, comprising: a database storing a prediction rule, and at least one threshold value of exhaled ammonia concentration is defined in the prediction rule; an acquisition module for acquiring an exhaled breath of a screened person gas; an ammonia sensing module for sensing an actual measured exhaled ammonia concentration of the exhaled gas; a comparison module for electrically connecting the database and the ammonia sensing module for comparing the actual measurement exhaled ammonia concentration and the at least one expiratory ammonia concentration threshold, and when the measured exhaled ammonia concentration is greater than the at least one expiratory ammonia concentration threshold, it is determined that the prediction rule is met; and an early warning module is electrical The comparison module is connected to generate an early warning information when the prediction rule is met, and the early warning information represents that a preliminary screening result of the screening person is suspected of suffering from chronic kidney disease. The chronic kidney disease prediction system as claimed in claim 8, further comprising a display module electrically connected to the early warning module for displaying the early warning information. The chronic kidney disease prediction system according to claim 8, wherein the database comprises: a receiving unit for receiving a plurality of measured breath ammonia concentrations and a plurality of kidney disease diagnoses of a plurality of subjects. As a result, a setting unit is used to set and adjust a preset threshold value; a first comparison unit is electrically connected to the receiving unit and the setting unit an element to compare the measured breath ammonia concentrations with the preset threshold to generate a plurality of kidney disease prediction results; a second comparison unit that is electrically connected to the receiving unit for comparison with the first a unit for comparing the kidney disease prediction results with the kidney disease diagnosis results; a statistic unit is electrically connected to the second comparison unit, so as to count the predetermined threshold value under the judgment criterion a sensitivity and a specificity; a defining unit, which is electrically connected to the statistical unit, for defining the preset threshold as the prediction rule when the sensitivity and the specificity reach an acceptable condition the at least one threshold value of exhaled ammonia concentration; and a storage unit electrically connected to the definition unit for storing the prediction rule.

Images