Method for measuring the presence and / or the concentration of an analyte in a sample

Abstract

The present invention relates to a method (100) for measuring the presence and / or concentration of an analyte in a sample with a biosensor (1), said method comprising: - performing a measurement of the sample with the biosensor (1) and determining a time-resolved measurement curve (800) of the measurement; - determining a measurement result (822) and a validity parameter (824) from the time-resolved measurement curve (800) with a second artificial intelligence (820); - outputting the measurement result (822) if the validity parameter (824) exceeds a predetermined threshold value and discarding the measurement result (822) as invalid if the validity parameter (824) falls below the predetermined threshold value. (Fig. 8)

Description

[0001] Method for measuring the presence and / or concentration of an analyte in a

[0002] sample

[0003] Technical area

[0004] The present invention relates to an improved method for measuring the presence and / or concentration of a specific analyte in a sample using a biosensor.

[0005] State of the art

[0006] A highly sensitive method for detecting and analyzing analytes in a sample involves using an analyte-induced change in the surface tension of a miniaturized spring element, a so-called cantilever, to measure the presence and / or concentration of an analyte in a sample.

[0007] A sensor device for detecting an occurrence and / or a concentration and / or an amount of an analyte in a sample, comprising a sensor, connection electronics and a housing, wherein the sensor is configured to convert chemical and / or biochemical information of an analyte in a sample into an electrical signal, wherein the sensor comprises a test cantilever having a base and a deformable part, wherein a receptor layer for selectively absorbing the analyte is applied at least to the deformable part, wherein the sensor comprises a reference cantilever having a base and a deformable part, wherein a reference layer for selectively non-absorbing the analyte is applied to the deformable part, is known from WO 2022 / 200438 A1.

[0008] US 2022 / 0336042 A1 discloses a method for classifying monitoring results of an analytical sensor system for monitoring molecular interactions. Description of the invention

[0009] In order to improve the reliability and precision of a measurement while taking into account its intended application, a method for measuring the presence and / or concentration of a specific analyte in a sample using a biosensor having the features of claim 1 is proposed.

[0010] Accordingly, a method for measuring the presence and / or concentration of an analyte in a sample with a biosensor is proposed, comprising:

[0011] Carrying out a measurement of the sample with the biosensor and determining a time-resolved measurement curve of the measurement;

[0012] Determining a measurement result and a validity parameter from the time-resolved measurement curve using a second artificial intelligence;

[0013] Output the measurement result if the validity parameter exceeds a specified threshold and reject the measurement result as invalid if the validity parameter falls below the specified threshold.

[0014] In this way, all information in a time-resolved measurement curve can be utilized. Small and / or large irregularities in the time-resolved measurement curve can be evaluated accordingly by the second artificial intelligence through appropriate training with representative training data. The second artificial intelligence can usually produce a reliable measurement result based on the representative training data, despite minor irregularities.

[0015] During the evaluation, the correctness of the measurement result is determined by comparing a validity parameter created by the second artificial intelligence with a predefined threshold.

[0016] The validity parameter represents a parameter with which the second artificial intelligence assesses its measurement result based on its own training.

[0017] The predefined threshold serves as a parameter to ensure that the measurement result is highly likely to be correct according to the intended application of the measurement or the biosensor. Consequently, when outputting the measurement result, the second artificial intelligence's assessment of its own measurement result, represented by a validity parameter, is first compared with a predefined threshold. The predefined threshold is based on the intended application of the measurement or the biosensor. This ensures that the measurement is correct according to its application scenario, enabling the measurement method to provide an ideal measurement result.

[0018] During the production of biosensors, for example, during the production of MEMS biosensors by growing MEMS structures on a wafer, applying nanosensors, or immobilizing the biochemistry, statistical variations or fluctuations in the manufacturing process can lead to different properties of the biosensors. For example, some biosensors may be more suitable for a first application scenario, whereas others may be more suitable for a second application scenario. Using the method described above, these differences in the qualities of the sensors can also be addressed, ultimately resulting in measurement results with a high degree of accuracy and a high probability of the measurement result being correct.

[0019] Preferably, the second artificial intelligence comprises a classifier which determines an individual measurement result and a validity parameter from the time-resolved measurement curve, wherein the measurement result assumes a value from a discrete value range.

[0020] For example, the discrete value range can be "positive" or "negative" when the biosensor measures a specific analyte, but can also include finer gradations such as "not diseased," "mildly diseased," or "severely diseased." The classes to which a classifier assigns corresponding measurement results can be adjusted accordingly.

[0021] The classifier may comprise a method for calculating a distance measure between time-resolved measurement curves, wherein the time-resolved measurement curves may also be shifted in time or distorted relative to one another.

[0022] The classifier can be trained on the basis of training data obtained by the following steps: determining a time-resolved measurement curve (800) of the at least one specific analyte in a sample comprising a defined concentration for a plurality of biosensors;

[0023] Determining a classification for each time-resolved measurement curve (800) of the plurality of biosensors based on the defined concentration;

[0024] Summarizing time-resolved measurement curves (800) and the corresponding classification in training data, whereby the training data are preferably prepared.

[0025] In addition, the respective feature vector of the respective biosensors can be added to the training dataset.

[0026] In this way, the second artificial intelligence trained with this training data can then determine the correct measurement result with a high degree of reliability when an individual measurement is available.

[0027] The measurement method is highly flexible and can be applied to any specific analyte. The second artificial intelligence can be trained using training data for different specific analytes. If there are characteristics in the time-resolved measurement curves of two different analytes, the second artificial intelligence can also be used to assign time-resolved measurement curves to an analyte. Accordingly, for example, the classifier also assigns a specific analyte to a class when determining a measurement result.

[0028] The second artificial intelligence may also include a regression model that determines an individual measurement result and a validity parameter from the time-resolved measurement curve, whereby the measurement result assumes a value from a continuous range of values.

[0029] In this way, not only the presence of a specific analyte in the sample can be determined, but also, for example, the concentration of the analyte in the sample can be determined.

[0030] The regression model can be trained on the basis of training data obtained by the following steps: determining a time-resolved measurement curve of the at least one specific analyte in a sample comprising a defined concentration for a plurality of biosensors; summarizing the time-resolved measurement curves and the respective associated defined concentration in training data, wherein the training data is preferably processed.

[0031] In addition, the respective feature vector of the respective biosensors can be added to the training dataset.

[0032] Using this training data, the accuracy of determining the concentration of a specific analyte in the sample can be further improved.

[0033] Regression allows for quantitative descriptions of relationships between variables, usually divided into independent and dependent variables. For example, the measurement result can be used as the dependent variable and the time-resolved measurement curve as several independent variables. Combining regression with a decision rule can also lead to classification. In the simplest case, a decision rule can take a concentration determined by the regression model and assign it a class, such as "positive" or "negative." Furthermore, by determining concentration, the regression model enables a very detailed analysis of a measurement.

[0034] The measurement result and the validity parameter can also be determined by the second artificial intelligence based on the feature vector of the biosensor.

[0035] This ensures that the specific characteristics of the respective biosensor are also taken into account in the evaluation by the second artificial intelligence. As a simple example, the feature vector can describe a specific area of ​​a coating. Depending on this area, the strength of the sensor signal can vary, so taking the feature vector into account can lead to an improved evaluation of the measurement result.

[0036] The specified threshold can be determined by a trained first artificial intelligence. This allows the determination of whether a measurement is rejected as invalid or determined as reliable to be indirectly determined by the trained first artificial intelligence, as it determines the individually relevant threshold.

[0037] The predetermined threshold can be determined using the trained first artificial intelligence based on an application scenario of the biosensor.

[0038] This allows the threshold to be precisely tailored to the specific application scenario. For example, a different, typically lower, threshold will be determined for an analysis intended for home use than for an analysis that requires a very high probability of the measurement result being correct, such as an analysis in a pharmaceutical laboratory.

[0039] To achieve this, the application scenario of the biosensor can be defined and passed to the first artificial intelligence, whereby the application scenario is determined based on inventory and / or demand data.

[0040] The trained first artificial intelligence can determine the predetermined threshold value with at least one performance parameter of the biosensor on the basis of at least one quality parameter, wherein the at least one performance parameter is preferably selected according to the application scenario, wherein the selection preferably corresponds to an individualization of the biosensor.

[0041] The trained first artificial intelligence can determine the at least one performance parameter and the predetermined threshold based on a feature vector, wherein the feature vector is obtained from a data preparation of the at least one quality parameter.

[0042] The quality parameter can be determined based on a property of the biosensor, wherein at least one electrical resistance is determined as the property, preferably all electrical resistances of a resistance bridge of the biosensor. The biosensor can comprise at least one resistance bridge and at least one of the

[0043] Quality parameter can be a self-similarity of the electrical resistances of the resistance bridge.

[0044] At least one of the performance parameters of the biosensor may include sensitivity and / or specificity and / or yield.

[0045] If the biosensor comprises at least one resistive bridge, at least one of the quality parameters may be a self-similarity of the electrical resistances of the resistive bridge.

[0046] It has been shown that the self-similarity of the resistances of the resistance bridge is a good indicator of the performance of the biosensor(s) and can therefore be used as at least one of the quality parameters that can be used to individualize the respective biosensor.

[0047] It is of great importance for the user of a biosensor that the respective analysis results are consistent and reliable or that the user receives an indication of the probability or certainty of the respective analysis results.

[0048] In other words, the user wants to know whether the test result obtained is reliable or not. However, the expected level of reliability can vary depending on the application. For a virus test for humans, a very high level of reliability may be required, for example, to reliably order or lift quarantine measures. For a home virus test as a preliminary test to determine whether to see a doctor, or for testing an animal, such as a pet, the expected level of reliability may be lower.

[0049] To quantify the reliability of tests, the parameters of sensitivity and specificity, for example, are known, which can be used to classify a test. For example, in a test for the presence of a specific virus, these performance parameters can be specified to describe the test's reliability.

[0050] The sensitivity of a test indicates what proportion of tested individuals is reliably identified as sick ("positive") by the test. Sensitivity is defined as the number of individuals identified as sick by the test divided by the number of actually sick individuals in the group tested. With a high test sensitivity, hardly any sick individuals will be falsely classified as healthy, so with a test with high sensitivity, a sick individual will be identified as sick with a high probability.

[0051] The specificity of a test indicates the proportion of tested individuals that the test reliably identifies as healthy ("negative"). Specificity is defined as the number of individuals tested as healthy divided by the number of actually healthy individuals in the group tested. With a high test specificity, hardly any healthy individual will be falsely identified as ill, so with a test with high specificity, a healthy individual will also be identified as healthy with a high probability.

[0052] Accordingly, these performance parameters are well suited to determine the performance of the biosensor.

[0053] The first trained artificial intelligence can be trained based on training data obtained using the following steps:

[0054] Determining a time-resolved measurement curve of at least one specific analyte and at least one sample without the specific analyte, each using a plurality of biosensors;

[0055] Determining an individual measurement result and a validity parameter for each biosensor using a second artificial intelligence from the time-resolved measurement curve of the respective biosensor;

[0056] Determining at least one quality parameter for each biosensor;

[0057] Statistical evaluation of the individual measurement results based on the assigned validity parameters using threshold values, the assigned quality parameters and the previously known result for each biosensor;

[0058] Determining performance parameters from statistical evaluation;

[0059] Using the quality parameters, performance parameters, and thresholds as training data. The first artificial intelligence trained in this way can then determine thresholds based on the respective individual biosensor, taking into account both the properties of the individual biosensor and the respective quality parameters intended for the application scenario.

[0060] The training data is determined for any specific analytes, for example, for different groups of viruses or bacteria. Training data can also be generated for different interferences, such as interference due to temperature or interfering proteins, by, among other things, adapting the samples and / or measurement routine accordingly. This allows optimized training data to be obtained to provide a representative dataset for training a first artificial intelligence, so that the trained first artificial intelligence can, in turn, perform better individualization of a biosensor.

[0061] By training the trained first artificial intelligence, a particularly good prediction of the suitability of the individual biosensor for a specific application scenario can be made, so that individualization of the biosensor is reliably possible and the measurement of the analyte can be reliably achieved or the economically best application of the biosensor can be determined.

[0062] The time-resolved measurement curve can be recorded at at least one defined concentration of the analyte and / or the time-resolved measurement curve can additionally be recorded at a defined disturbance and / or the time-resolved measurement curve can be recorded at at least one defined measurement routine.

[0063] The trained first artificial intelligence can be trained on the basis of training data that includes as quality parameters the self-similarity of the electrical resistances of a resistance bridge of each biosensor.

[0064] The trained first artificial intelligence can be trained based on training data that includes the sensitivity and / or specificity and / or yield of each biosensor as performance parameters. Furthermore, a measuring device for measuring the presence and / or concentration of an analyte in a sample with a biosensor is proposed, which is configured to communicate with a biosensor to perform the measurement and is configured to perform the measurement method described above.

[0065] The biosensor and the corresponding measuring device envisaged here can be a sensor for converting chemical and / or biochemical information of an analyte into an electrical signal in a sample. The sensor can comprise a test cantilever having a base and a deformable part, with a receptor layer for selectively absorbing the analyte applied at least to the deformable part, and a reference cantilever having a base and a deformable part, with a reference layer for selectively preventing the analyte from being absorbed applied to the deformable part.

[0066] The base of the test cantilever and / or the base of the reference cantilever can be designed as a rigid base. A rigid base is understood to mean that the respective cantilever, i.e., the test cantilever and / or the reference cantilever, is not deformed or substantially deformed relative to the deformable part of the respective cantilever. The rigid base is, for example, connected to a substrate, supported by a substrate, or machined from the substrate. The deformable part of the test cantilever and / or the reference cantilever, however, is not supported by the substrate but rather protrudes beyond an edge of the substrate and is accordingly freely formed.

[0067] The deformable part of the test cantilever and / or the reference cantilever can, for example, be designed to be deflectable. Deflection of the respective cantilever can be achieved, for example, around a bending edge formed in a transition region between the base and the deflectable region. The bending edge is, for example, the edge of the substrate along which the cantilever is divided into the base and the deformable part.

[0068] However, the deformation of the respective cantilever in its deformable part is not limited to a lifting or lowering deformation; the cantilever itself can also be deformed, for example, by arching, undulating, or distorting. A sample refers to a limited amount of a substance taken from a larger amount of the substance, for example, from a reservoir. The composition of the sample is representative of the composition of the substance in the reservoir. Accordingly, the substance occurrence and composition of the sample can be used to determine the corresponding occurrence in the reservoir.

[0069] For example, a sample can be a saliva sample, a blood sample, lymph, urine, sweat, or intertissue fluid, or a swab, in particular a throat swab, a nasal swab, or a sinus swab, or even a sampled tissue. A sample includes, in particular, any type of biological sample, including, in particular, animal samples.

[0070] A sample can also be a non-biological sample, for example a sample of a chemical substance.

[0071] An analyte is the substance whose presence in the sample is to be qualitatively and / or quantitatively detected or detected with the sensor. The analyte can be present directly in the sample, dissolved in the sample, or adhere to the sample or a part of the sample, particularly a sample particle. The analyte can also interact chemically, biologically, and / or physically with the sample, so that the analyte can only be detected indirectly via a corresponding interaction.

[0072] In particular, one sample form can be converted into another, allowing the analyte, or rather its presence, to be detected in a simple and reliable manner. For example, a swab can be dissolved in a liquid, so that the swab dissolved in the liquid then becomes the actual sample, which is then tested for the analyte.

[0073] The analyte in the sample can also be chemically pretreated, for example, by disrupting the viral envelope—if the analyte is a virus—to access nucleocapsid antigens. Furthermore, the analyte can be "labeled" through such pretreatment to amplify the measurement signal. For this purpose, for example, conjugated antibodies can bind to analyte antigens to create the greatest possible deformation on the cantilever system.

[0074] The sample then contains the chemical information and / or biochemical information about the

[0075] Analytes. Chemical information can include, for example, the type of analyte, the concentration of the analyte, the occurrence of the analyte, the weight of the analyte, the reactivity of the analyte, the density of the analyte, etc. Biochemical information encompasses the same properties as chemical information, but these substances can arise, for example, through biological processes. In particular, biochemical information is referred to when the analyte has a particular influence on the biological cycle, for example, metabolism or the immune system.

[0076] The test cantilever includes a passive and an active test transducer and the reference cantilever includes a passive and active reference transducer.

[0077] The chemical and / or biochemical information is converted into an electrical signal. This can mean that the chemical composition of the analyte can change or create an electrical signal. This can, for example, affect the conductivity of a circuit. For example, a first piece of biochemical information can be present when the circuit is conducting, and a second piece of biochemical information can be present when the circuit is not conducting or has a reduced conductivity.

[0078] In addition to the direct accessibility of information, such as via conductivity, it is also possible to infer the biochemical information via a physical and / or chemical process and / or an interaction.

[0079] For this purpose, the proposed sensor comprises a reference cantilever and a test cantilever. A cantilever is a spring element comprising a base and a deformable part. The base is therefore a stationary part of the cantilever, which is arranged in a stationary manner on a substrate. The deformable part of the cantilever is arranged at the base and protrudes beyond the base.

[0080] In particular, the base and cantilever can be formed as a single piece. In other words, the deformable part of the cantilever is suspended from the base on one side. By extending beyond the substrate, the deformable part of the cantilever can be bent, deflected, and stretched. The spatial boundary from which the cantilever is bendable, or where the cantilever transitions from the base to the deformable part, is called the bending edge. The bending edge is usually an edge of the substrate when the cantilever extends beyond the base. If the cantilever is bent, material stresses and forces arise in or on the material of the cantilever, which can be measured. If such material stress and / or force can be measured, this can be used to determine whether the cantilever is bending.

[0081] The purpose of the transducers is to determine or measure the deformation of the cantilevers. Active transducers are mounted on the deformable parts of the cantilevers, whereas passive transducers are mounted on the bases of the cantilevers. In particular, the electrical properties of a circuit can be influenced via the transducers.

[0082] For example, a deformation of the cantilever can lead to an increase in the resistance of a transducer, such as an active transducer, while a lack of deformation of the cantilever also causes no change in the resistance of the transducer. This can be achieved, for example, by designing the transducer according to the principle of a strain gauge, whereby a deformation of the respective cantilever is expressed in a change in the length of the strain gauge of the transducer applied to it. Thus, a deformation of the cantilever can be detected directly by a change in the resistance of the strain gauge.

[0083] Thus, the chemical and / or biochemical information of the analyte becomes detectable via a deformation of the cantilever, a subsequent registration via a transducer, and finally via a change in an electrical property of a circuit.

[0084] The deformation of the cantilevers can be induced substance-specifically by a suitable coating. For this reason, the reference cantilever has a reference layer for selectively preventing the absorption of the analyte, while the test cantilever has a receptor layer for absorption of the analyte.

[0085] A receptor layer is a substance that can interact with the analyte. This means that the receptor layer is selected specifically for each analyte. Similarly, a reference layer is a substance that cannot interact with the analyte. The reference layer is therefore also selected specifically for the analyte.

[0086] In this case, interaction means that the analyte interacts chemically, biochemically, and / or physically with the receptor layer. In particular, the interaction can consist of binding of the analyte to the receptor layer. Interaction can also consist of absorption, adsorption, or nonspecific adhesion of the analyte to the receptor layer.

[0087] The receptor and reference layers are preferably chemically identical with respect to potential interference and differ only in their interaction with the analyte. A substance other than the analyte will therefore interact just as strongly or just as weakly with the receptor layer as with the reference layer.

[0088] The selective uptake of the analyte by the test cantilever causes a force to act on the test cantilever through the analyte, causing the test cantilever to react sensitively to the analyte. Accordingly, the other substances in the sample that are not the analyte only contribute to a background noise in the form of a basic deflection of the test cantilever. For example, the force acting on the test cantilever increases more rapidly, the higher the concentration of the analyte in the sample or the faster the surface of the cantilever is covered with the analyte. The maximum force possible for the respective configuration is reached when the cantilever is completely covered.

[0089] The selective non-uptake of the analyte at the reference cantilever, on the other hand, means that no force is exerted by the analyte on the reference cantilever, so that only the substances that are not the analyte contribute to a background noise in the form of a basic bending of the reference cantilever.

[0090] This acting force can cause deformation in the deformable part of the test cantilever, while the deformable part of the reference cantilever remains unchanged. The basis for the deflection of the cantilever is the change in surface tension due to the interaction with the analyte. The change in surface tension leads to a stretching or compression of the upper (or lower) surface of the cantilever. The different stretching or compression on the upper and lower surfaces creates an internal force or material stress in the material, which leads to deformation.

[0091] With the proposed sensor, the measurement process is drastically simplified by the selective non-uptake of the analyte by the reference cantilever, as the reference cantilever is not sensitive to the analyte, and therefore the analyte does not contribute to the background noise. Only substances other than the analyte contribute to the background noise of the reference cantilever. In a sense, the selective non-uptake of the analyte by the reference cantilever can cause the reference cantilever to be exposed to the same turbulence, the same thermal drift, and the same influence of all non-analyte substances as in a reference sample. However, the difference is that the reference signal is determined directly in the sample liquid.

[0092] In particular, a reference cantilever with a reference layer and a test cantilever with a receptor layer result in a significantly more specific analysis of the analyte than just a reference cantilever without a receptor layer, since both the reference layer and the receptor layer exhibit a specific interaction or non-interaction with the analyte.

[0093] The sensor design with a reference cantilever and a test cantilever has the advantage that two measurements can be taken simultaneously in the sample, with the reference cantilever measurement calibrating the test cantilever measurement. This reduces environmental influences, such as chemical, thermal, mechanical, electrical, and fluidic interference, on the respective measurement, allowing the presence of the analyte to be determined by comparing the measurement with the test cantilever and the reference cantilever.

[0094] These forces or material stresses, such as strains or compressions, acting on the cantilevers can ultimately be detected by the transducers, whereby different levels of strain or compression result in different levels of stress being detected by the transducers.

[0095] Short description of the characters

[0096] Preferred further embodiments of the invention are explained in more detail by the following description of the figures.

[0097] Showing:

[0098] Figure 1 shows a first schematic embodiment of an exemplary biosensor for converting chemical and / or biochemical information;

[0099] Figure 2 shows a further schematic embodiment of a biosensor; Figure 3 shows a schematic possibility for connecting the electrodes of a biosensor in the form of a resistance bridge;

[0100] Figure 4 shows a schematic flow diagram of a method for individualizing an individual, manufactured biosensor for measuring a specific analyte;

[0101] Figure 5A shows a schematic embodiment for determining voltages and / or electrical resistances at a resistance bridge of a biosensor using a measuring device, here in the form of a schematically shown multimeter;

[0102] Figure 5B shows an embodiment for determining the at least one property of the biosensor with a schematically shown camera system;

[0103] Figure 6A shows a schematically shown neural network as an embodiment of a trained first artificial intelligence for determining performance parameters and an associated threshold value;

[0104] Figure 6B shows a schematic flowchart comprising a second artificial intelligence for generating training data;

[0105] Figure 7 shows a schematic representation of a training data set comprising the performance parameters sensitivity, specificity and yield as a function of the self-similarity of a resistance bridge and a threshold value;

[0106] Figure 8 shows a schematic flow chart as an embodiment of an evaluation of a measurement of a biosensor based on its individualization by means of a second artificial intelligence; and

[0107] Figure 9 shows a schematic flow chart of an embodiment for passing through no or at least one further manufacturing step of a biosensor based on its individualization.

[0108] Detailed description of preferred embodiments

[0109] Preferred embodiments are described below with reference to the figures. Identical, similar, or equivalent elements in the different figures are provided with identical reference numerals, and a repeated description of these elements is partially omitted to avoid redundancies.

[0110] Figure 1 schematically shows a first embodiment of an exemplary biosensor 1 for converting chemical and / or biochemical information. The biosensor 1 comprises a test cantilever 2, which in turn has a base 20 and a deformable part 22. A passive test transducer 200 is arranged on the base 20, while an active test transducer 220 is arranged on the deformable part 22.

[0111] Analogous to the test cantilever 2, the biosensor 1 also has a reference cantilever 3, which in turn has a base 30 with a passive reference transducer 300, as well as a deformable part 32 which has an active reference transducer 320.

[0112] The purpose of the transducers is to determine or measure the deformation of the cantilevers. Active transducers are mounted on the deformable parts of the cantilevers, whereas passive transducers are mounted on the bases of the cantilevers. In particular, the electrical properties of a circuit can be influenced via the transducers.

[0113] For example, a deformation of the cantilever can lead to an increase in the resistance of a transducer, such as an active transducer, while a lack of deformation of the cantilever also causes no change in the resistance of the transducer. This can be achieved, for example, by designing the transducer according to the principle of a strain gauge, whereby a deformation of the respective cantilever is expressed in a change in the length of the strain gauge of the transducer applied to it. Thus, a deformation of the cantilever can be detected directly by a change in the resistance of the strain gauge.

[0114] Thus, the chemical and / or biochemical information of the analyte becomes detectable via a deformation of the cantilever, a subsequent registration via a transducer, and finally via a change in an electrical property of a circuit.

[0115] The transducer can also detect a contraction of the surface on which it is arranged. In the embodiments shown, however, the transducers are always arranged on surfaces where stretching is expected. The stretching and / or change in surface tension and / or force detected by the transducer can, however, also be a bending force or a shear force, or be caused by a bending force or shear force, or generally be based on the elastic modulus of the respective cantilever. In particular, the attachment of the deformable part 22, 32 to the base 20, 30 results in the deformable part 22, 32 aligning along a bending curve due to the application of a force caused by a change in the surface tension of the test cantilever.The resulting bending curve is determined by the geometry, in particular the area moment of inertia of the cantilever, as well as by the cantilever's mass and elastic modulus. The bending curve can be described, for example, according to beam theory.

[0116] The transducers 200, 220, 300, 320 are each connected to an electronics unit 4 which is capable of recording or forwarding a measurement signal from the transducers 200, 220, 300, 320, while the electronics unit 4 is also capable of supplying the transducers 200, 220, 300, 320 with current and / or voltage.

[0117] The transducers 300, 320, 200, 220 are preferably connected via electrodes 401, 402, 403, 404. In particular, the active test transducer 220 is connected to the active reference transducer 320 via electrode 401. Furthermore, the passive test transducer 200 is connected to the passive reference transducer 300 via electrode 403. The active test transducer 220 is also connected to the passive test transducer 200 via electrode 402, whereas the active reference transducer 320 is connected to the passive reference transducer 300 via electrode 404. This results in a total of four electrodes via which the transducers are electrically connected to one another.

[0118] Electrical contact can be achieved in particular by applying the transducers to existing electrodes, thus creating a conductive connection.

[0119] The biosensor 1 has the task of indicating the occurrence and / or concentration and / or amount of an analyte 90 in a sample 9.

[0120] In Figure 1, sample 9 is a liquid that was prepared, for example, by taking a swab, in particular a nasal swab or a throat swab, from a test subject. It is also conceivable that the sample comprises a liquid on an object, such as a rope or a cotton swab. However, sample 9 may also be saliva or blood or another bodily fluid. However, sample 9 may also be a gargle fluid with which the test subject gargled. Sample 9 may also have been obtained and / or synthesized from a tissue sample or from another substance taken from the test subject. The analyte 90 may be dissolved in the sample or be present in an undissolved manner as a suspension, dispersion, or emulsion.

[0121] However, sample 9 and the analyte of interest 90 can also be of non-biological origin.

[0122] In any case, the biosensor 1 is intended to examine the sample 9 with regard to the presence and / or concentration and / or amount of the analyte 90 in the sample 9. For this purpose, a receptor layer 24 with which an analyte 90 can interact is applied to the test cantilever 2. For example, the receptor layer 24 can adsorb or absorb the analyte 90. During adsorption, the analyte 90 would adhere to the surface of the receptor layer 24, whereas during absorption, the analyte 90 would penetrate into the interior of the receptor layer 24.

[0123] If the sample 9 contains a specific analyte 90, it can interact with the receptor layer 24. This can lead to a change in the surface tension of the section of the deformable part 22 of the test cantilever 2 covered with the receptor layer 24. This change in surface tension can be registered by the active test transducer 220, which in turn is interpreted as a measurement signal in the electronics 4.

[0124] The change in the surface tension of the section of the deformable part 22 of the test cantilever 2 covered with the receptor layer 24 can also lead to a deformation of the deformable part 22 of the test cantilever 2. The active test transducer 220 can therefore also register a deformation of the deformable part of the test cantilever 2, which in turn is interpreted as a measurement signal in the electronics 4.

[0125] However, due to the interaction with the sample liquid of sample 9, a force can be registered by the active test transducer 220, for example, in which only a surface tension of the liquid acts on the deformable part 22 of the test cantilever 2. Therefore, in this case, the presence of an analyte 90 is not responsible for a corresponding resulting deformation or change in the surface tension.

[0126] To determine the magnitude of this basic effect of sample 9 on test cantilever 2, reference cantilever 3 is brought into contact with sample 9 simultaneously with test cantilever 2. For this purpose, reference cantilever 3 has a reference layer 34 with which an analyte 90 cannot interact, or a reference layer 34 that cannot adsorb or absorb analyte 90. Interaction with analyte 90 is to be avoided in order to enable differentiation from the measurement signal of test cantilever 2.

[0127] Since both the test cantilever 2 and the reference cantilever 3 interact with the sample 9, both cantilevers 2, 3 interact with the sample 9 in a similar manner. However, the difference here is that the test cantilever 2 can also interact with a potentially present analyte 90 via its reference layer 24. Accordingly, the measurement signals of the active transducers 220, 320 differ if an analyte 90 is present in the sample 9. In the simplest case, the magnitude of the difference in the measurement signals can be used to determine the amount of analyte 90 present in the sample 9.

[0128] The deformation of the cantilevers can be induced substance-specifically by a suitable coating. For this reason, the reference cantilever has a reference layer for selectively preventing the absorption of the analyte, while the test cantilever has a receptor layer for absorption of the analyte.

[0129] A receptor layer is a substance that can interact with the analyte. This means that the receptor layer is selected specifically for each analyte. Similarly, a reference layer is a substance that cannot interact with the analyte. The reference layer is therefore also selected specifically for the analyte.

[0130] In this case, interaction means that the analyte is in chemical and / or biochemical and / or physical interaction with the receptor layer. In particular, the interaction can consist of binding of the analyte to the receptor layer. Interaction can also consist of absorption, adsorption, or nonspecific adhesion of the analyte to the receptor layer. The receptor and reference layers are preferably chemically identical with respect to potential interference and preferably differ only in their interaction with the analyte. Accordingly, a substance other than the analyte interacts just as strongly or just as weakly with the receptor layer as with the reference layer.

[0131] The selective uptake of the analyte by the test cantilever causes a force to act on the test cantilever through the analyte, causing the test cantilever to react sensitively to the analyte. Accordingly, the other substances in the sample that are not the analyte only contribute to a background noise in the form of a basic deflection of the test cantilever. For example, the force acting on the test cantilever increases more rapidly, the higher the concentration of the analyte in the sample or the faster the surface of the cantilever is covered with the analyte. The maximum force possible for the respective configuration is reached when the cantilever is completely covered.

[0132] The selective non-uptake of the analyte at the reference cantilever, on the other hand, means that no force is exerted by the analyte on the reference cantilever, so that only the substances that are not the analyte contribute to a background noise in the form of a basic bending of the reference cantilever.

[0133] This acting force can cause deformation in the deformable part of the test cantilever, while the deformable part of the reference cantilever remains unchanged. The basis for the deflection of the cantilever is the change in surface tension due to the interaction with the analyte. The change in surface tension leads to a stretching or compression of the upper (or lower) surface of the cantilever. The different stretching or compression on the upper and lower surfaces creates an internal force or material stress in the material, which leads to deformation.

[0134] State-of-the-art reference cantilevers simply lack a receptor layer that reacts sensitively to the analyte. This allows effects such as turbulence in the sample and the thermal drift of the sensor system to be determined. However, with such a reference cantilever, the analyte can bind, for example, through nonspecific binding to the reference layer of the reference cantilever. This causes the analyte itself to contribute to the background noise. Therefore, with a state-of-the-art sensor, reference measurements in a reference sample, i.e., a sample without analyte, are necessary. Only in this way can the effect of nonspecific binding of substances that are not the analyte be determined.

[0135] In the biosensor, the selective non-uptake of the analyte by the reference cantilever drastically simplifies the measurement process, as the reference cantilever is not sensitive to the analyte, and therefore the analyte does not contribute to the background noise. Only substances other than the analyte contribute to the background noise of the reference cantilever. In a sense, the selective non-uptake of the analyte by the reference cantilever can cause the reference cantilever to be exposed to the same turbulence, the same thermal drift, and the same influence of all non-analyte substances as in a reference sample. However, the difference is that the reference signal is determined directly in the sample liquid.

[0136] In particular, a reference cantilever with a reference layer and a test cantilever with a receptor layer result in a significantly more specific analysis of the analyte than just a reference cantilever without a receptor layer, since both the reference layer and the receptor layer exhibit a specific interaction or non-interaction with the analyte.

[0137] The sensor design with a reference cantilever and a test cantilever has the advantage that two measurements can be taken simultaneously in the sample, with the reference cantilever measurement calibrating the test cantilever measurement. This reduces environmental influences, such as chemical, thermal, mechanical, electrical, and fluidic interference, on the respective measurement, allowing the presence of the analyte to be determined by comparing the measurement with the test cantilever and the reference cantilever.

[0138] These forces or material stresses, such as strains or compressions, acting on the cantilevers can ultimately be detected by the transducers, whereby different levels of strain or compression result in different levels of stress being detected by the transducers.

[0139] Test cantilever 2 and reference cantilever 3 thus measure the presence of analyte 90 in sample 9 at different positions. Different sample properties, such as temperature fluctuations or concentration gradients, can occur at different positions within the sample. These different environmental conditions can be measured using passive transducers 200 and 300.

[0140] The passive transducers 200, 300 are arranged on the base and preferably do not detect a measurement signal in the event of a deformation or change in the surface tension of the deformable part 22, 32 of the reference or test cantilevers 2, 3. However, the base level of the measurement signal of the passive transducers 200, 300 can be influenced due to these different ambient conditions. By providing a comparison value for each measured value of the active transducers 220, 230 via the passive transducers 200, 300, which considers the ambient conditions in isolation, the influence of the ambient conditions on the measurement signals of the active transducers 220, 320 can be determined and reduced, or calculated out, or isolated.

[0141] Accordingly, the presence of an analyte 90 in a sample 9 can be isolatedly analyzed using the biosensor 1 by reducing and isolating the influence of interactions that cannot be attributed to the analyte 90 through a large number of measuring points on the reference and test cantilevers 3, 2. This enables a high degree of measurement accuracy for the presence of the analyte 90 in the sample 9.

[0142] Figure 2 shows a further schematic embodiment of a biosensor 1. The transducers 300, 320, 200, 220 are contacted via the electrodes 401, 402, 403, 404. In particular, the active test transducer 220 is connected to the active reference transducer 320 via the electrode 401. Furthermore, the passive test transducer 200 is connected to the passive reference transducer 300 via the electrode 403. The active test transducer 220 is also connected to the passive test transducer 200 via the electrode 402, whereas the active reference transducer 320 is connected to the passive reference transducer 300 via the electrode 404.

[0143] This results in a total of four electrodes through which the transducers 200, 220, 300, and 320 are electrically connected to each other. Electrical contact can be achieved in particular by applying the transducers to the electrodes, creating a conductive connection.

[0144] Figure 3 shows one possible way of connecting the electrodes. The electrodes that

[0145] Transducers 200, 220, 300, and 320 are generally constructed with mirror symmetry. Currents flow through the electrodes, or voltages are present, so that an asymmetrical design of these electrodes could lead to asymmetric crosstalk of electrical signals to the other electrodes. This mutual influence can lead to the generation of a stray signal between the electrodes, which can, however, be avoided by the symmetrical design. Consequently, voltages drop across the electrical resistors of transducers 200, 220, 300, and 320, such as a single-ended voltage at the passive test transducer Utest passive (200) and a single-ended voltage at the passive reference transducer Ureference passive (poo).

[0146] The transducers 200, 220, 300, 320 are electrically connected in a so-called resistance bridge. In the resistance bridge, an excitation voltage V0, for example, direct voltage or alternating voltage, is applied between the electrodes 403, 401. Between these electrodes, the passive and active transducers act as voltage dividers due to their electrical resistances. A resistance bridge in the form shown has the advantage that no voltage builds up between the electrodes 402, 404, provided the ratio of the electrical resistances of the passive transducer 200 to the active transducer 220 of the test cantilever 2 is equal to the ratio of the electrical resistances of the passive transducer 300 to the active transducer 320 of the reference cantilever 3. Thus, in particular, a deviation of one electrical resistance is sufficient to change the electrical resistance ratios and thus to build up a voltage between the electrodes 402, 404.

[0147] When the reference cantilever 3 and the test cantilever 2 interact with the sample 9 and the analyte 90, both deformable parts 22, 32 experience, for example, a change in the surface tension, which is, for example, greater for the deformable part 22 of the test cantilever 2 than for the deformable part 32 of the reference cantilever 3. Consequently, the electrical resistance of the active test transducer 220 of the deformable part 22 of the test cantilever 2 will vary to a greater extent than for the active reference transducer 320 of the deformable part 32 of the reference cantilever 3. If the electrical resistances of the passive transducers 200, 300 do not change or at least change equally, a change in the electrical resistance ratios results from the deformation of the deformable part 22 of the test cantilever 2 due to the interaction with the analyte 90 of the sample 9, which is specifically related to the reference layer 24 of the test cantilever 2.During such an interaction, a voltage is accordingly built up between the electrodes 402, 404, so that a change in the surface tension at the active test transducer 220 relative to the active reference transducer 320 can be displayed as a bridge transverse voltage VB. Preferably, the bridge transverse voltage VB scales with the presence of the analyte 90 in the sample 9, thus enabling a quantitative evaluation of the measurement signal.

[0148] The bridge transverse voltage VB corresponds to the difference between the single-ended voltage at the passive test transducer Utest passive (200) and the single-ended voltage at the passive reference transducer Ureference passive (3000).

[0149] A bridge transverse voltage detector 44 can externally display or transmit the bridge transverse voltage VB, so that the user of the biosensor 1 can see that a bridge transverse voltage VB is present. In particular, such a bridge transverse voltage detector 44 can also be provided by an AD converter 440, wherein the AD converter 440 converts the bridge transverse voltage VB into a digital signal that can be transmitted to the external measuring device.

[0150] In particular, the AD converter 440 can be operated in two different measurement modes.

[0151] The first measurement mode is the differential measurement mode, in which the bridge transverse voltage VB is measured, thus generating a relative measurement value for the deformation of the two reference and test cantilevers 3, 2. In this differential measurement mode, the measurement signal of all transducers 200, 220, 300, 320 is taken into account, so that the output signal of the AD converter 440 is a measurement signal cleansed of environmental influences, which allows conclusions to be drawn about the relative deformation of the deformable parts 32, 22 and thus about the presence of an analyte 90.

[0152] The second measurement mode is the so-called absolute measurement mode. In absolute measurement mode, the bridge transverse voltage VB is not detected, but rather the signals at electrodes 402 and 404 are tapped in isolation from each other, allowing a statement to be made about the respective deflections of the deformable parts 32, 22. This information is not available to the user in differential measurement mode, in which the bridge transverse voltage VB is measured.

[0153] The biosensors actually manufactured may exhibit a certain degree of scatter with regard to the respective applied structures and thus in particular also with regard to the properties of the transducers, in particular of the active and passive test transducers 220, 200 and the active and passive reference transducers 320, 300. These differences in the properties, for example in the electrical resistances of the transducers 200, 220, 300, 320, are due to manufacturing and therefore cannot be completely ruled out.

[0154] However, it is of great importance for the user of a biosensor 1 that the respective analysis results are consistent and reliable or that the user receives an indication of the probability or certainty of the respective analysis results.

[0155] In other words, the user wants to know whether the test result obtained is reliable or not. However, the expected level of reliability can vary depending on the application. For a virus test for humans, a very high level of reliability may be required, for example, to reliably order or lift quarantine measures. For a lactate test for a recreational athlete, the expected reliability may be lower.

[0156] To quantify the reliability of tests, the parameters of sensitivity and specificity, for example, are known, which can be used to classify a test. For example, in a test for the presence of a specific virus, these performance parameters can be specified to describe the test's reliability.

[0157] The sensitivity of a test indicates what proportion of tested individuals is reliably identified as sick ("positive") by the test. Sensitivity is defined as the number of individuals identified as sick by the test divided by the number of actually sick individuals in the group tested. With a high test sensitivity, hardly any sick individuals will be falsely classified as healthy, so with a test with high sensitivity, a sick individual will be identified as sick with a high probability.

[0158] The specificity of a test indicates the proportion of tested individuals that the test reliably identifies as healthy ("negative"). Specificity is defined as the number of individuals tested as healthy divided by the number of actually healthy individuals in the group tested. With a high test specificity, hardly any healthy individual will be falsely identified as ill, so with a test with high specificity, a healthy individual will also be identified as healthy with a high probability.

[0159] In the following, a method is described by means of which the biosensors described above can be individualized to measure a specific analyte and the measurement method is then designed in such a way that the test results always enable a measurement result with a high sensitivity and a high specificity, despite a possible fluctuation range in the production of the biosensors.

[0160] Figure 4 shows a schematic flowchart of an embodiment of a method 100 for individualizing an individually manufactured biosensor 1 for measuring a specific analyte 90. The individualization of the individually manufactured biosensor 1 is to be carried out such that, after successful individualization, the individual biosensor 1 can be used by the user for a specific application scenario. In the corresponding application scenario, it is then provided that the biosensor 1 performs the corresponding analysis in such a way that the requirements for test reliability expected by the user for the specific application scenario, for example, sensitivity and specificity, can always be met, or the test is discarded. In other words, a reliable test result can always be achieved in this way.

[0161] In the method 100, in a first step S1, at least one quality parameter of the individual biosensor 1 whose individualization is to be achieved is determined. The at least one quality parameter can be used as an indicator of the performance of the biosensor 1. At least the at least one quality parameter serves to individualize the biosensor in the further method 100.

[0162] The at least one quality parameter of the individual biosensor 1 results, for example, from the production data of the biosensor 1, which was recorded during the production of the biosensor 1, or from a measurement. The quality parameters can be determined either directly from the production data or the measurement data, or from the production data or the measurement data. An exemplary determination of measurement data or a determination of quality parameters from the measurement data or from production data is described below, for example, in Figures 5A and 5B. Reference is made to this at this point.

[0163] In a second step S2, at least one performance parameter and a corresponding threshold value are then determined for the individual biosensor 1 based on the provided quality parameters. The threshold value preferably corresponds to a probability by which the correctness of a measurement result from a measurement with the biosensor is assessed. The correctness can assume the values ​​to be correct or invalid. The corresponding threshold value depends on the performance parameters of the biosensor 1. As performance parameters, for example, the sensitivity, specificity and / or the yield of the respective biosensor 1 for the measurement of a specific analyte 90 can be determined. The sensitivity or specificity indicates how reliably a medical diagnostic method, such as the measurement of a specific analyte 90 in a user, detects whether the user is ill or not ill.The yield, in turn, indicates the extent to which a medical diagnostic procedure, such as the measurement of a specific analyte in a user, delivers a correct result.

[0164] The performance parameters are determined using a trained first artificial intelligence, whereby the trained first artificial intelligence determines the performance parameters and threshold values ​​of the respective individual biosensor 1 from the quality parameters. After input of at least one quality parameter, the trained first artificial intelligence outputs a list of performance parameters and corresponding threshold values.

[0165] For example, the determination in step S2 results in a list of tuples with performance parameters and corresponding thresholds, individual for the respective biosensor 1, based on the at least one quality parameter of the respective biosensor 1. Each tuple from the list of tuples includes a value and a corresponding threshold for each performance parameter. With a suitable selection of the performance parameters, the tuple allows an assessment of the correctness of a measurement of the biosensor 1 based on the corresponding threshold.

[0166] As shown in the exemplary embodiment in Figure 6A, a neural network 80 can be used as the trained first artificial intelligence for determining performance parameters. The training of the first artificial intelligence is described below following Figure 6A. Reference is made to this at this point.

[0167] By training the first artificial intelligence, this is specified for the task in step S2. Thus, the first artificial intelligence used in step S2 can determine lists for one or more performance parameters with the respective threshold values ​​for each, or a specific, analyte. For example, the sensitivity, specificity, and / or yield of the respective biosensor 1 for measuring a specific analyte 90 can be determined as performance parameters by the trained first artificial intelligence.In a third step S3, the individual biosensor 1 is then individualized based on the determined performance parameters and the associated threshold value in such a way that the performance parameters and their threshold values ​​are analyzed for different application scenarios and in particular analytes 90 to determine whether the individual biosensor 1 is suitable for a specific application scenario or rather for another application scenario.

[0168] For example, in a first application scenario, biosensor 1 is to be used to detect a virus to contain a pandemic. In this case, analyte 90 is clearly specified, as this is the specific virus present in the sample fluid of sample 9 to be tested. Furthermore, in order to be applicable in this case, the test must achieve high sensitivity and high specificity. For this first application scenario, the requirement profile accordingly arises in that analyte 90 in the form of the virus must be determined with high specificity and, at the same time, high sensitivity, while taking the yield into account. High sensitivity and high specificity are of great importance here, among other things, to be able to contain the pandemic on the one hand, but also to be able to reliably implement official measures to restrict individual freedom, such as quarantine measures, on the other.The test usually has both a specificity and a sensitivity of 100%. A high yield is important for resource conservation and user satisfaction, as it ensures sufficient tests are available whose accuracy in measuring the specific analyte is not invalidated, for example.

[0169] In a second example application scenario, for example, the determination of the lactate level in the blood of a recreational athlete may be required. Here, too, the analyte 90 is clearly specified: lactate in the athlete's blood. However, the requirements for the sensitivity and specificity of the corresponding biosensor are not as high in this case, since the recreational athlete needs the data for individual training control, but this does not entail any substantial restrictions on personal freedom, for example, due to quarantine measures. Accordingly, in this second application scenario, the analyte would be clear: lactate in the blood; however, the requirements for specificity and sensitivity are significantly lower.

[0170] Specifically, in step S3, for example, based on the data determined in step S2

[0171] Performance parameters and the associated threshold values ​​can be used to determine whether an individual biosensor 1 is suitable, for example, for a virus test to contain a pandemic, which requires high sensitivity and high specificity, or whether the individual biosensor 1 is more suitable for an application scenario in which high specificity and high sensitivity are not required.

[0172] If a list of tuples is available, a tuple can be selected from the list of tuples. The tuple can be selected based on the values ​​of the performance parameters in the list of tuples, taking the application scenario into account, in order to customize the biosensor.

[0173] The threshold value in the selected tuple can later be used to assess the accuracy of the measurement when the biosensor measures the specific analyte. The threshold value depends on the performance parameters. This is also discussed in the description of Figure 7 below. Reference is also made to this. Accordingly, the tuple, and in particular the threshold value for the respective performance parameter, can also advantageously be stored with biosensor 1.

[0174] After completion of the individualization, the process 100 ends and the individual, now individualized biosensor can be labeled and used according to the respective defined application scenario.

[0175] For this purpose, both the application scenario and the corresponding threshold value can be stored in the respective individual, now individualized biosensor.

[0176] Of course, with a corresponding evaluation of the individual biosensor, several different application scenarios with the corresponding threshold values ​​can be determined and saved, which can then be stored in the biosensor in a selectable manner.

[0177] The data, i.e., the corresponding application scenario and the associated performance parameters and thresholds, can be stored in a non-volatile memory within the biosensor, such as an EEPROM. Storing the data completes the customization of each individual biosensor.

[0178] The individualization of the biosensor for measuring a specific analyte can also take place in step S3 using the trained first artificial intelligence from step S2, taking into account a specific application scenario. The trained first artificial intelligence thus determines the performance parameter values ​​and the corresponding threshold value for the biosensor 1 based on the at least one quality parameter, taking into account the specific application scenario. The trained first artificial intelligence selects, for example, a tuple from a list of tuples based on the specific application scenario. The performance parameter values ​​and the associated threshold value in the selected tuple are based on the specific application scenario, and the trained first artificial intelligence individualizes the biosensor 1.The specific application scenario can, for example, be specified by a user, or determined based on current inventory levels and demand and provided to the trained first artificial intelligence.

[0179] If no suitable tuple can be selected by the trained first artificial intelligence, for example because no performance parameter values ​​exist for biosensor 1 for the specific application scenario, the first artificial intelligence can issue an error message. In this case, the trained artificial intelligence can also independently select another specific application scenario, for example, based on current inventory levels and / or demand. The first artificial intelligence incorporates the specific application scenario to determine a performance parameter with an associated threshold value for biosensor 1. Accordingly, the training of the first artificial intelligence takes the specific application scenario into account. The consideration of the specific application scenario during training of the first artificial intelligence is explained in more detail at the end of Figure 6B. Reference is made to this at this point.

[0180] The determination of at least one quality parameter by measuring measured values ​​or evaluating production data is shown below in Figures 5A and 5B.

[0181] Figure 5A schematically shows an embodiment for determining a property of the biosensor 1 based on an embodiment of a biosensor 1 comprising a test cantilever 2 and a reference cantilever 3 with deformable parts 22, 32. By means of a measuring device, shown here as an example in the form of a multimeter 50, the voltages at the electrical resistances of the transducers 300, 320, 200, 220, such as the single-ended voltage at the passive test transducer Utest passive (200) and the single-ended voltage at the passive reference transducer Ureference passive (300>), are measured. The transducers 300, 320, 200, 220 are contacted via the electrodes 401, 402, 403, 404. For this purpose, measuring tips 52 of the multimeter 50 are correspondingly connected to the electrodes of the biosensor 1. The measured value of the voltage across the electrical resistance is displayed on a display of the multimeter 50 in the exemplary embodiment.The multimeter 50 can also be used to measure other properties of the biosensor 1, such as electrical resistances, capacitances, or impedances. For example, the multimeter can be used to measure the electrical resistances of the transducers 300, 320, 200, 220. The multimeter 50 can also be part of a measuring apparatus, particularly during or after the biosensor manufacturing process, so that the measurement of at least one property can be automated.

[0182] Figure 5B shows a further embodiment for determining the at least one property of the subcomponents or all subcomponents of the biosensor 1 using a camera system 60. The camera system 60 can capture an image section of the biosensor 1 using an imaging method, create a spectrum of the image section, and evaluate a time-resolved analysis, spectrally filtered excitation, and spectrally filtered detection of signals using a camera and, for example, a computer 62. The evaluation can be performed in all production steps and may include the use of electrons, light, ions, and / or near-field analyses.

[0183] The evaluation of the image section can, for example, result in a determination of the electrical resistances of the transducers 300, 320, 200, 220 as a property of the biosensor 1. The transducers 300, 320, 200, 220 are contacted via the electrodes 401, 402, 403, 404. The evaluation of the image section can also result in the coverage density and homogeneity of a coating of a test cantilever 2 and a reference cantilever 3 as a property of the biosensor 1. The evaluation of the image section can also be the individual, finely resolved, geometric configuration of the cantilever, the electrodes, or the transducer and can also contain spectroscopic information.

[0184] At least one quality parameter can then be determined from the previously determined properties of the biosensor.

[0185] For example, a proportion and its distribution of the functionalized surface of biosensor 1 can be determined as a quality parameter. From the previously determined single-ended voltages at the electrical resistances of the passive test transducer Utest passive (200), the passive reference transducer Ureference passive (300), and the excitation voltage VO, the self-similarity of the electrical resistances in the resistance bridge of biosensor 1 can also be determined as a quality parameter.

[0186] The self-similarity of the biosensor 1 results here in a first consideration, for example, based on the following calculation rule, taking into account the excitation voltage VO at the resistance bridge, the single-ended voltage at the passive test transducer Utest passive (200) and the single-ended voltage at the passive reference transducer Ureference passive (300) as follows:

[0187] Self-similarity =min(1 - I Utest passive (200) / (VO / 2) - 11 , 1 - ( Ureference passive (300) / (VO / 2) - 11), where min( , ) outputs the smallest value of the arguments. The single-ended voltages at the electrical resistances of the passive test transducer Utest passive (200) and the passive reference transducer Ureference passive (300) can be determined from the electrical resistances Reference passive (2oo), Rreference active (220), Rtest passive (300), Rtest active (320) of the transducers 200, 220, 300, 320 in the resistance bridge and the excitation voltage VO at the resistance bridge as follows:

[0188] Utest passive (200) = VO * Rtest passive (200) / ( Rtest passive (200) + Rtest active (220)) ,

[0189] Ureference passive (300) = VO * Rreference passive (300) / ( Rreference passive (300) + Rreference active (320)).

[0190] This results in the self-similarity depending on the electrical resistances Rreference passive (2oo), Rreference active (220), Rtest passive (300), Rtest active (320) of the transducers 200, 220, 300, 320 as follows:

[0191] Self-similarity = min(1 - I (Rtest passive <200) - Rtest active (220)) / (Rtest passive (200) + Rtest active (220)) | , 1 - | (Rreference passive (300) - Rreference active (320)) / (Rreference passive (300) + Rreference active (320)) |) ,

[0192] The self-similarity can possibly also be determined by including the bridge transverse stress VB.

[0193] As already described above, the trained first artificial intelligence used in step S2 can be a trained neural network 80. Figure 6A shows the trained neural network 80 from step S2 as an exemplary embodiment as a possible first artificial intelligence. The trained first artificial intelligence, for example the neural network 80 from Figure 6A, is trained with specific training data in order to enable the determination of the performance parameters from the quality parameters for the respective biosensor 1. The following additionally discusses the generation and application of the training data on the basis of which the first artificial intelligence can be trained for use in step S2.

[0194] In step S2, the neural network 80 shown in Figure 6A determines the performance parameters of the biosensor 1 and associated threshold values ​​for an analyte 90 using a feature vector. The feature vector results from the at least one determined quality parameter of the biosensor 1.

[0195] The feature vector can be obtained, for example, from data preparation of the at least one quality parameter. The data preparation can, for example, include rescaling the at least one quality parameter. The data preparation can also include an error analysis of the at least one quality parameter, wherein the error analysis ends with the generation of the feature vector. The data preparation can include the removal of unnecessary quality parameters. A principal component analysis or another method for data reduction or data selection can also be applied during data preparation in order to obtain the feature vector that contains as much information as possible about the underlying at least one quality parameter.The data processing may also include storing the at least one quality parameter and / or the feature vector in a database or in a memory, such as an EEPROM, of the biosensor 1. The feature vector may also correspond to the at least one quality parameter.

[0196] The exemplary neural network 80 shown in the embodiment in Figure 6A has four layers. A neural network 80 can also have a topology with, for example, more or fewer layers, as well as more or fewer neurons in each layer.

[0197] The feature vector based on the quality parameters is passed as input to the trained neural network 80. For example, the feature vector can have n components x = (xi,... ,xn), whereby the neural network 80 accordingly has n neurons 82 in a first layer 84. The neural network 80 in the embodiment in Figure 6A has three neurons 82 in its first layer 84. Thus, feature vectors with three components are passed to the neural network 80. A neuron 82 at the i-th position in the second layer 85 of the neural network 80 outputs a value as follows: Oi (wj + bi), where w = (wi,... ,w n ) is a vector of weights, and bi is a bias value. Oi is an activation function. The activation function can be, for example, a ReLU or sigmoid function.

[0198] The neural network 80 outputs performance parameters and their corresponding thresholds as output values ​​at its last layer 86. In the embodiment in Figure 6A, the neural network 80 has five neurons 82 in its last layer 86, with the five neurons 82 outputting a performance parameter list 70. A performance parameter list can, for example, be a list of tuples, where each tuple from the list of tuples includes a value and an associated threshold for each performance parameter.

[0199] For example, the five neurons 82 can output five values ​​for the performance parameter specificity in the form of a performance parameter list, each with its corresponding threshold. For example, the specificity of biosensor 1 is selected from the performance parameter list with the five specificity values ​​and their corresponding thresholds.

[0200] The trained neural network 80 in Figure 6A is trained by training data 88 and is suitable to fulfill the function described in S2.

[0201] Figure 6B shows schematically how the training data 88 can be obtained.

[0202] A measurement is performed under controlled conditions using a plurality of pre-manufactured biosensors 1. In other words, a biosensor 1 is used to measure a known analyte concentration of the analyte of interest 90 under regular measurement conditions, i.e., the measurement conditions for which the respective biosensor 1 is intended for the user, and under regular environmental influences that can be expected during a measurement. Similarly, a plurality of measurements can also be performed under controlled disturbances in order to create a more global topography. The course of the resulting time-resolved measurement is stored for each biosensor 1 of the manufactured biosensors in combination with the information about the measured analyte 90—in particular, the known analyte concentration and / or the presence or absence of the analyte 90 present in the sample fluid of the sample 9 to be analyzed.

[0203] For each individual biosensor 1 from the multitude of biosensors already manufactured, a time-resolved measurement curve 800 is obtained, as shown in Figure 6B as an example for a biosensor. The measurement accordingly provides a measurement curve 800, wherein the measurement curve is obtained on the basis of a voltage signal at the resistance bridge of the biosensor 1 that varies over time.

[0204] It is also known which analyte 90 was measured, at which concentration, and under which disturbance, so that both the individual measurement curve 800 for each biosensor 1 and the expected result are known. In this way, training data can be provided for training a second artificial intelligence 820.

[0205] In the second artificial intelligence 820, for example a classifier, the individual measurement result 822 is determined from the time-resolved measurement curve 800 of an individual measurement and at the same time a validity parameter 824 is output.

[0206] For example, the second artificial intelligence 820 can be a classifier that classifies the measurement result into a positive or negative individual measurement result. For this purpose, the second artificial intelligence 820 can, for example, comprise dynamic time normalization (DTW for short, "dynamic time warping"). The second artificial intelligence 820 can also comprise a regression model. The regression model can output an analyte concentration as an individual measurement result.

[0207] The validity parameter 824 is compared with a predefined threshold to indicate the correctness of the measurement result. The threshold stored together with the application scenario during biosensor customization may be used as the predefined threshold for evaluating the validity parameter when evaluating the measurement. The correctness can assume the values ​​"correct" or "invalid."

[0208] The present measurement result may be invalid, for example, if a time-resolved measurement curve 800 ends abruptly due to a premature termination of the associated measurement, resulting in an unknown course of the measurement curve. In this case, the second artificial intelligence 820 can determine the individual measurement result for the measurement curve, but only with very low validity. Due to the comparison of the associated validity parameter with the specified threshold, the associated measurement result may then be classified as invalid.

[0209] At the same time, before each measurement of a specific analyte with a biosensor 1, its quality parameter is also determined, for example, the self-similarity of the electrical resistances in the resistance bridge. In a sorting step 840, the determined data, consisting of the individual measurement result 822, the associated validity parameter 824, the associated quality parameter, for example, the self-similarity 826, and the known result for each biosensor from the multitude of previously manufactured biosensors, are statistically evaluated.

[0210] The statistical evaluation may include the following substeps. Sorting step 840 may initially include filtering the determined data. When filtering the determined data, each assigned validity parameter is compared with a specified threshold value to indicate the correctness of each individual measurement result. All individual measurement results whose correctness is, for example, correct are summarized with the assigned validity parameters, as well as their assigned quality parameters and the expected results, to form a filtered data set. The filtered data set is in turn divided into groups, with each group including biosensors with the same quality parameters. A group may also possibly include all associated data from the filtered data set for which one or more quality parameters are above one or more predetermined limit values.For each of these groups, the performance parameters, such as sensitivity, specificity, and / or yield, can now be determined. The filtering and subsequent determination of the performance parameters is repeated for a variety of specified thresholds to generate the training data 88.

[0211] In Figure 6B, the training data 88 are shown as an example in a three-dimensional representation, for example, for the sensitivity, with the sensitivity values ​​being displayed based on a grayscale coding 72. The three-dimensional representation has self-similarity plotted on the y-axis as a quality parameter and the threshold value plotted on the x-axis.

[0212] The resulting training data 88, which, when applied as training data to the trained first artificial intelligence, such as the neural network 80 in Figure 6A, result in a list of performance parameters 70, for example comprising sensitivity, specificity and / or yield, with the associated threshold values ​​for the biosensor for the specific analyte 90, being able to be determined upon input of a quality parameter for a biosensor 1, for example self-similarity.

[0213] The training data can also be marked according to specific application scenarios. For example, it can be stored in the training data that performance parameters within a range are suitable for a specific application, such as lactate measurement or the measurement of a specific virus. Once the training data are marked according to the specific application scenarios, the corresponding training data can be used to train a first artificial intelligence, which includes customizing the biosensor to measure a specific analyte in step S3, as shown, for example, in Figure 1, incorporating a specific application scenario for the biosensor 1.

[0214] The second artificial intelligence 820 can also be used to evaluate a measurement by a user (see Figure 8).

[0215] The second artificial intelligence 820 is trained to output the individual measurement result and validity parameter. For training, stored measurement curves from the multitude of previously manufactured biosensors can be used in combination with information about the measured analyte—in particular, the known analyte concentration and / or the presence or absence of the analyte in the sample fluid to be analyzed. Furthermore, the respective feature vector of the respective biosensors can be added to the training data. This data is stored in a training dataset.

[0216] If the second artificial intelligence 820 is a classifier, for example, the classifier can be based on a nearest-neighbor classification method. The classifier determines the measurement result, for example, for an unknown time-resolved measurement curve 800 of a biosensor based on a comparison of the unknown measurement curve with the measurement curves in the training data set.

[0217] In the case of measurement curves of equal length and not distorted, the comparison can be carried out, for example, by calculating a norm between the still unknown measurement curve of the biosensor and all measurement curves in the training data set, optionally also taking the respective feature vector into account. The magnitude values ​​are then ordered in ascending order. The measurement result of the unknown measurement curve of the biosensor can be obtained using a calculation rule, e.g. averaging, of a predefined number of measurement results for measurement curves from the training data set with the smallest magnitude values. The validity parameter is calculated, for example, based on the highest magnitude value for the measurement curve in the training data set, the measurement result of which is used to determine the measurement result of the still unknown measurement curve.The second artificial intelligence 820 can be adapted to include dynamic time warping (DTW for short). DTW is based on a method that compares two time series, such as two time-resolved measurement curves 800. The two time series do not have to match perfectly, but can, for example, be temporally shifted or distorted. DTW enables, for example, two time series of different lengths to be compared. Consequently, DTW can also be used to compare two time-resolved measurement curves 800 that do not cover the same time period.

[0218] For example, if the second artificial intelligence 820 includes a regression model, the regression model is trained by minimizing a cost function. The validity parameter can result from a calculation involving the measurement result and the training data set.

[0219] Figure 7 shows the training data 88 again in three representations comprising sensitivity, specificity and yield.

[0220] The values ​​for the performance parameters sensitivity, specificity and yield are represented by a grayscale bar 72. The self-similarity in the three representations lies between 0 and 1, and the threshold value between 0.5 and 0.9.

[0221] The three diagrams show that there is a systematic relationship between sensitivity, specificity, and yield depending on self-similarity and the threshold, as well as between the performance parameters sensitivity, specificity, and yield for a given self-similarity and a given threshold. The threshold thus depends on the performance parameters. The threshold also depends on self-similarity.

[0222] The systematic relationship is evident in the fact that at a certain self-similarity and with increasing threshold, there is a tendency for greater sensitivity and specificity, although the yield tends to decrease.

[0223] By including the specified threshold value, the sensitivity, specificity, and yield for biosensor 1 can then be determined during the measurement based on the respective performance parameter lists 70. For the determined self-similarity of biosensor 1, a corresponding adjustment between the sensitivity and specificity, as well as the yield of biosensor 1, can thus be made by setting the threshold value.

[0224] Figure 8 shows, using a flow chart, an embodiment for an evaluation of a measurement of a biosensor 1 based on the individualization of the biosensor 1.

[0225] For this purpose, in method 100, as already described above, the individualized biosensor is used to measure the corresponding specific analyte for the application scenario for which it was individualized.

[0226] In step S4, the measurement is then performed with the correspondingly customized biosensor under the specified measurement conditions. The measurement results in the time-resolved measurement curve 800, which shows the corresponding time-resolved signal voltage curve at the resistance bridge for the reference cantilever 3 and the test cantilever 2.

[0227] The measurement of the specific analyte 90 can be carried out using an apparatus. The apparatus also comprises, among other things, the sample 9 to be measured with the specific analyte 90. An apparatus can possibly also comprise several technical components. The technical components can, for example, be one or more mobile devices. The apparatus can also include one or more programs. The one or more programs can, for example, be stored and / or run on the technical components. The programs can serve to evaluate the measurement of the specific analyte with the inclusion of the individualized biosensor. The evaluation can, for example, be triggered by an electrical signal from the biosensor 1 to the apparatus. The measurement can also be evaluated on a server based on data from the measurement of the analyte.The measurement data, as well as the data of the biosensors themselves, such as at least one of their quality parameters, application scenarios, performance parameters, and / or threshold values, can also be stored and processed in a cloud.

[0228] The resulting measurement curve 800 is fed in step S5 to the second artificial intelligence 820, which outputs an individual measurement result as well as a validity parameter that the measurement result is correct.

[0229] In addition to the resulting measurement curve 800, the feature vector stored in the biosensor 1 used for the measurement can also be fed to the second artificial intelligence 820 for evaluating the measurement curve 800. The feature vector can be read by the device from the non-volatile memory of the biosensor 1. The readout can be performed before the measurement, during the measurement, and / or after the measurement, so that the feature vector can then be fed to the second artificial intelligence and taken into account in the evaluation of the resulting measurement curve.

[0230] Depending on the validity parameter, the final measurement result is then output to the user in step S6. If the validity parameter falls below a predefined threshold, the measurement result is classified as invalid. However, if the validity parameter is above the predefined threshold, a measurement result can be output that is positive or negative with a corresponding probability that at least corresponds to the validity parameter. The threshold stored during the individualization of the biosensor 1 together with the application scenario may be used as the predefined threshold for evaluating the validity parameter during the measurement evaluation. The threshold from the individualization of the biosensor 1 preferably results, among other things, from the application scenario of the biosensor 1.

[0231] The comparison between the validity parameter and the specified threshold can also be performed by the second artificial intelligence in step S5. Step S6 therefore includes an output of the classification of the measurement result, the measurement result itself, and / or the corresponding probability that at least corresponds to the validity parameter.

[0232] This makes it possible to ensure that the measurement result can always be produced with absolute reliability, depending on the given application scenario, by customizing the biosensor on the one hand and evaluating the measurement result based on its validity parameter for the corresponding performance parameters on the other. In an extreme case, this can achieve both a specificity and a sensitivity of 100% for a virus test, for example.

[0233] If, for example, during the individualization of the biosensor for a specific application scenario, it was specified that a specificity of 98% and a validity of 59% were required with a threshold of 0.60, this threshold must be used to evaluate the measurement for this individual biosensor in order to achieve the required performance parameters. In other words, if the measurement performed results in a validity parameter below 0.95 during the evaluation of the measurement curve in the artificial intelligence 820 in step S5, the corresponding measurement is rejected as invalid. Therefore, it is always ensured that the parameters specified for the specified application scenario are strictly adhered to by the measurement, or the measurement is rejected as invalid.

[0234] Irregularities in a measurement can lead to an unknown or irregular course of the measurement curve. By training the second artificial intelligence 820, a precise measurement result can still be determined for weak irregularities. A weak irregularity occurs, for example, if the measurement is aborted shortly before completion, or if weak disturbances, such as minor temperature fluctuations, occur during the measurement. Such weak irregularities in the measurement can be compensated for by repeated and adapted training of the second artificial intelligence 820. Strong irregularities can arise, for example, from a significantly premature termination of the measurement, whereby the termination results in the biosensor 1 being separated from the specific analyte 90 well before the measurement is completed.With such an unknown or irregular course of the measurement curve, the second artificial intelligence 820 will also arrive at a result, but the validity parameter associated with the result will be very low. In other words, an irregular measurement will always result in the evaluation of the validity parameter relative to the threshold in step S6 leading to the respective measurement being rejected as invalid. Consequently, repeated and adapted training of the second artificial intelligence 820 can reduce the number of measurements rejected as invalid.

[0235] Since the individualization of the respective biosensor is merely advantageous but not essential for the method shown in Figure 8 for determining the measurement result, the exemplary embodiment can also be considered to begin with the method 100 for individualizing a biosensor 1. However, the individualization of the biosensor is not absolutely necessary.

[0236] Figure 9 shows, using a flowchart, an exemplary embodiment for running through no or at least one further manufacturing step S7 of a biosensor 1 based on a method 100 for individualizing the biosensor. As already described in Figure 4, successful individualization leads to a determination of an application scenario of the biosensor 1. In this case, both the application scenario and the performance parameters assigned to the application scenario with the respective threshold values ​​can be stored in the biosensor 1. Based on the stored data, comprising the application scenario and the assigned performance parameters with the respective threshold values, biosensors, for example in stock as inventory, can run through at least one further manufacturing step S7. Manufacturing steps can include, for example, functionalization.During functionalization, a biosensor is adapted to its intended purpose based on the stored data. Functionalization can include, among other things, the application of a receptor layer 24 and / or reference layer 34. The production of a biosensor can also be aborted based on its individualization, so that the biosensor does not undergo any further production steps. These production steps can occur during production, during repair, and / or during testing of the biosensor.

[0237] For example, biosensors can be flexibly adapted to their respective application scenarios, even after extended storage periods. Biosensors can also potentially undergo a process 100 to customize the biosensor at any time and then be reworked or their production can be discontinued.

[0238] Where applicable, all individual features presented in the embodiments may be combined and / or exchanged without departing from the scope of the invention.

[0239] List of reference symbols

[0240] 100 procedures

[0241] 51 Determine at least one quality parameter

[0242] 52 Determine at least one performance parameter

[0243] 53 Customizing a biosensor

[0244] 54 Carrying out a measurement

[0245] 55 Classifying the measurement

[0246] 56 Evaluation of a measurement

[0247] 1 biosensor

[0248] 2 test cantilevers

[0249] 3 reference cantilevers

[0250] 4 Electronics

[0251] 9 Sample

[0252] 90 analytes

[0253] 200 passive test transducers

[0254] 220 active test transducers

[0255] 300 passive reference transducer

[0256] 320 active reference transducer

[0257] 400, 401, 402, 403 electrodes

[0258] 20 Base

[0259] 22 Deformable part

[0260] 24 Receptor layer

[0261] 30 Base

[0262] 32 Deformable part

[0263] 34 Reference layer

[0264] 44 Bridge transverse voltage detector

[0265] 50 multimeters

[0266] 52 measuring probes

[0267] 60 camera system

[0268] 62 computers

[0269] 70 Performance Parameter List

[0270] 72 Grayscale 80 Neural Network

[0271] 82 neurons

[0272] 84 First Shift

[0273] 85 Second shift 86 Last shift

[0274] 88 training data

[0275] 800 measurement curve

[0276] 820 Second artificial intelligence

[0277] 822 Measurement result 824 Validity parameters

[0278] 826 quality parameters

[0279] VO excitation voltage

[0280] VB bridge transverse voltage

Claims

Claims 1 . A method (100) for measuring the presence and / or concentration of an analyte in a sample with a biosensor (1), comprising: Carrying out a measurement of the sample with the biosensor (1) and determining a time-resolved measurement curve (800) of the measurement; Determining a measurement result (822) and a validity parameter (824) from the time-resolved measurement curve (800) with a second artificial intelligence (820); Outputting the measurement result (822) if the validity parameter (824) exceeds a predetermined threshold and rejecting the measurement result (822) as invalid if the validity parameter (824) falls below the predetermined threshold.

2. Method according to claim 1, characterized in that the second artificial intelligence (820) comprises a classifier which determines an individual measurement result and a validity parameter from the time-resolved measurement curve (800), wherein the measurement result assumes a value from a discrete value range.

3. Method according to claim 2, characterized in that the classifier comprises a method for calculating a distance measure between time-resolved measurement curves, wherein the time-resolved measurement curves can also be shifted in time or distorted relative to one another.

4. Method according to claim 2 or 3, characterized in that the second artificial intelligence is trained on the basis of training data obtained by the following steps: Determining a time-resolved measurement curve (800) of the at least one specific analyte in a sample comprising a defined concentration for a plurality of biosensors; determining a classification for each time-resolved measurement curve (800) of the plurality of biosensors based on the defined concentration; Summarizing time-resolved measurement curves (800) and the corresponding classification in training data, whereby the training data are preferably prepared.

5. The method according to claim 4, characterized in that the respective feature vector of the respective biosensors is additionally added to the training data set.

6. Method according to one of the preceding claims, characterized in that the second artificial intelligence (820) comprises a regression model which determines an individual measurement result and a validity parameter from the time-resolved measurement curve (800), wherein the measurement result assumes a value from a continuous range of values.

7. The method according to claim 5, characterized in that the regression model is trained on the basis of training data obtained by the following steps: Determining a time-resolved measurement curve (800) of the at least one specific analyte in a sample comprising a defined concentration for a plurality of biosensors; combining the time-resolved measurement curves (800) and the respectively associated defined concentration into training data, wherein the training data is preferably processed.

8. The method according to claim 7, characterized in that the respective feature vector of the respective biosensors is additionally added to the training data set.

9. Method according to one of the preceding claims, characterized in that the measurement result (822) and the validity parameter (824) are additionally determined by the second artificial intelligence (820) on the basis of the feature vector of the biosensor (1).

10. Method according to one of the preceding claims, characterized in that the predetermined threshold value is determined by a trained first artificial intelligence (S2).

11. The method according to claim 10, characterized in that the predetermined threshold value is determined using the trained first artificial intelligence on the basis of an application scenario of the biosensor (1).

12. The method according to claim 1 1, characterized in that the application scenario of the biosensor (1) is defined and passed to the first artificial intelligence, wherein the application scenario is determined on the basis of inventory and / or demand data.

13. Method according to one of claims 10 to 12, characterized in that the trained first artificial intelligence compares the predetermined threshold value with at least one Performance parameters of the biosensor (1) are determined on the basis of at least one quality parameter, wherein the at least one performance parameter is preferably selected according to the application scenario, wherein the selection preferably corresponds to an individualization of the biosensor (1).

14. The method according to any one of claims 10 to 13, characterized in that the trained first artificial intelligence determines the at least one performance parameter and the predetermined threshold value on the basis of a feature vector, wherein the feature vector is obtained from a data processing of the at least one quality parameter.

15. The method according to claim 13 or 14, characterized in that the quality parameter is determined on the basis of a property of the biosensor (1), wherein at least one electrical resistance is determined as a property, preferably all electrical resistances of a resistance bridge of the biosensor (1).

16. Method according to one of claims 13 to 15, characterized in that the biosensor (1) comprises at least one resistance bridge and at least one of the quality parameters is a self-similarity of the electrical resistances of the resistance bridge.

17. Method according to one of claims 13 to 16, characterized in that at least one of the performance parameters of the biosensor (1) comprises a sensitivity and / or a specificity and / or a yield.

18. Method according to one of the preceding claims, characterized in that the trained first artificial intelligence is trained on the basis of training data obtained by the following steps: Determining a time-resolved measurement curve (800) of at least one specific analyte, as well as at least one sample without the specific analyte, each with a plurality of biosensors; Determining an individual measurement result (822) and a validity parameter (824) for each biosensor with a second artificial intelligence (820) from the time-resolved measurement curve (800) of the respective biosensor; Determining at least one quality parameter (826) for each biosensor; Statistically evaluating the individual measurement results (822) on the basis of the assigned validity parameters (824) using threshold values, the assigned quality parameters (826) and the previously known result for each biosensor; Determining performance parameters from statistical evaluation; Use the quality parameters, performance parameters and thresholds as training data.

19. The method according to claim 18, characterized in that the time-resolved measurement curve (800) is recorded at at least one defined concentration of the analyte and / or that the time-resolved measurement curve (800) is additionally recorded at a defined disturbance and / or that the time-resolved measurement curve (800) is recorded at at least one defined measurement routine.

20. Method according to one of claims 10 to 19, characterized in that the trained first artificial intelligence is trained on the basis of training data which include, as quality parameters, the self-similarity of the electrical resistances of a resistance bridge of each biosensor.

21. Method according to one of claims 10 to 20, characterized in that the trained first artificial intelligence is trained on the basis of training data which include, as performance parameters, the sensitivity and / or the specificity and / or the yield of each biosensor.

22. Measuring device for measuring the presence and / or concentration of an analyte in a sample with a biosensor (1), arranged to communicate with a biosensor (1) for carrying out the measurement, and arranged to carry out the measuring method according to one of the preceding claims.

Images