Automated analyzer

Abstract

Provided is an automatic analysis device capable of calculating stable measurement values even when temperature fluctuations occur in a light source or a photometer. An automatic analysis device is provided with: a light source (104) that has a first temperature measurement unit (209) and that irradiates light onto a container (203) that accommodates a mixed solution of a sample and a reagent; a photometer (208) that has a second temperature measurement unit (210) and that measures the amount of light from the light source that has passed through the liquid mixture; a light amount correction value calculation unit (211) that calculates a light amount correction value on the basis of the light source temperature measured by the first temperature measurement unit and the photometer temperature measured by the second temperature measurement unit; and an absorbance calculation unit (205) that calculates the absorbance of the liquid mixture on the basis of the light amount measured by the photometer and the light amount correction value.

Description

Automatic analysis device Technical Field

[0001] This invention relates to an automated analysis device. Background Technology

[0002] In automated analytical devices for analyzing samples such as blood, the light source is one of the most important components affecting analytical performance. Light emitted from the light source passes through a reaction solution containing reagents and the sample, is split into specific wavelengths by a spectrometer, and then detected by a detector. Due to this detection process, ensuring the stability of the amount of light emitted from the light source and the stability of the amount of light received in the detector becomes crucial. It is known that in the optical system of an automated analytical device, the amount of emitted light and the amount of light received are affected by the ambient temperature, or by the temperature of the light source and detector. Therefore, techniques for stabilizing the temperature of the light source and detector, or techniques for correcting temperature variations, are needed.

[0003] As a method for light quantity correction related to the optical system of an automatic analysis device, Patent Document 1 discloses a method for correcting absorbance by using the ambient temperature around the light source and a correction rate calculated before analysis.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2022-164188 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] In the method disclosed in Patent Document 1, only the temperature on the light source side is used for correction. Therefore, there is a problem that the temperature change on the detector side is not reflected. For example, if the temperature on both the light source and detector sides increases by 1°C, the light intensity on the light source side decreases while the light intensity on the detector side increases. When performing correction that only corresponds to the temperature change on the light source side is performed under such conditions, the correction will be performed in the direction that causes an excessive increase in light intensity, and the correct measurement value may not be obtained.

[0009] Furthermore, in the method of Patent Document 1, the absorbance is corrected not for the amount of light. Generally, absorbance is calculated using the amount of incident light before passing through the reaction liquid and the amount of transmitted light after passing through the reaction liquid; therefore, it is appropriate to correct the amount of light rather than the absorbance.

[0010] Furthermore, light sources and photometers exhibit individual differences depending on the device. Therefore, it is desirable to have a structure that can perform light quantity correction based on their individual differences, or that can adjust for varying temperature values.

[0011] The purpose of this invention is to provide an automatic analysis device capable of offsetting or reducing the temperature effects on both the light source and the detector side to calculate stable measurement values.

[0012] Methods for solving problems

[0013] An automatic analysis apparatus according to one embodiment of the present invention includes: a light source having a first temperature measuring unit that irradiates light onto a container holding a mixture of a sample and a reagent; a photometer having a second temperature measuring unit that measures the amount of light from the light source that passes through the mixture; a light quantity correction value calculation unit that calculates a light quantity correction value based on the light source temperature measured by the first temperature measuring unit and the photometer temperature measured by the second temperature measuring unit; and an absorbance calculation unit that calculates the absorbance of the mixture based on the light quantity measured by the photometer and the light quantity correction value.

[0014] Invention Effects

[0015] This automated analytical device is capable of calculating stable measurements even when there are temperature variations in the light source or photometer (detector). Further details and new features will become clear from the description and accompanying drawings in this specification. Attached Figure Description

[0016] Figure 1 is a schematic structural diagram showing the overall structure of the automatic analysis device.

[0017] Figure 2 is a diagram illustrating the optical system and surrounding devices of the automatic analysis apparatus of Embodiment 1.

[0018] Figure 3 is a functional block diagram illustrating the light quantity correction function of Example 1.

[0019] Figure 4 shows the calculation process for the measured values ​​in Example 1.

[0020] Figure 5 is a graph showing the relationship between temperature and light intensity for each wavelength.

[0021] Figure 6 is a diagram illustrating the optical system and surrounding devices of the automatic analysis apparatus of Embodiment 2.

[0022] Figure 7 is a functional block diagram illustrating the temperature adjustment function of Example 2.

[0023] Figure 8 shows the calculation process for the measured values ​​in Example 2.

[0024] Figure 9 is a graph showing the relationship between the light source temperature and the photometer adjustment temperature for each wavelength.

[0025] Figure 10A shows an example of the hardware structure of a learning device.

[0026] Figure 10B is a functional block diagram illustrating the training of the learning model in Example 3.

[0027] Figure 11 shows an example of a learning model.

[0028] Figure 12 is a functional block diagram illustrating the light quantity correction function of Example 3.

[0029] Figure 13 is a functional block diagram illustrating the temperature adjustment function of Example 3. Detailed Implementation

[0030] Figure 1 is a schematic structural diagram of the automatic analysis device. The display unit 101 displays operation and measurement information performed by the automatic analysis device. The input unit 102 inputs requirements for the analysis actions performed by the automatic analysis device. The analysis unit 103 has various operating mechanisms for performing the analysis actions. The light source 104 is one of the elements constituting the analysis unit 103, projecting light onto the object being measured. The control unit 105 controls the various operating mechanisms constituting the analysis unit 103 based on operation instructions input from the input unit 102, etc., and calculates the measurement data.

[0031] Example 1

[0032] Figure 2 illustrates the optical system used in the automated analysis apparatus of Example 1 and the surrounding devices. The light source 104 is composed of LED elements. There is no limitation on the number of LED elements constituting the light source 104; using multiple elements is not a problem. When the light source 104 has multiple LED elements, the current supplied to each LED element is individually set. During operation of the analysis unit 103, light from the light source 104 illuminates the reaction vessel 203 at the photometric position between the light source 104 and the diffraction grating 207. In the mixture within the reaction vessel 203, the analyte component of the test sample reacts with reagents, generating or consuming the photometric substance proportional to the concentration of the analyte component. Furthermore, reaction tank water (a temperature-controlled medium) is present between the reaction tank 204 and the reaction vessel 203.

[0033] The light illuminating the mixture, specifically the wavelength of light corresponding to the absorption region of the substance being measured, is absorbed by the substance. The light passing through the mixture is incident on a concave diffraction grating 207 provided in the photometer 208. The diffraction grating 207 disperses the incident light according to wavelength and outputs the dispersed light to the photodetector 206. The photodetector 206 converts the light intensity into an electrical signal and outputs this electrical signal to the absorbance calculation unit 205. The absorbance calculation unit 205 calculates the absorbance and outputs it to the device control unit 212. As described later, the absorbance calculation unit 205 calculates the absorbance based on the light intensity correction value calculated by the light intensity correction value calculation unit 211 based on the electrical signal output from the photodetector 206 and the temperature data obtained from the temperature measuring units 209 and 210.

[0034] The device control unit 212 performs colorimetric analysis based on the absorbance output from the absorbance calculation unit 205. During colorimetric analysis, cell blank water is dispensed into all reaction cells, and the absorbance at each wavelength from 340 to 800 nm is measured (cell blank measurement). The device control unit 212 stores this measurement result as a cell blank value (also called baseline absorbance). The device control unit 212 compares the cell blank value with the absorbance of the mixture being analyzed to correct the absorbance, and outputs the corrected absorbance as measurement data to the user interface (such as the screen displayed on the display unit 101).

[0035] The current detection unit 201 monitors (measures) the current flowing through the light source 104. The current adjustment unit 202 has a circuit that reduces the amount of current supplied to the light source 104 or disconnects the power supply to the light source 104 at a timing that does not affect the analysis.

[0036] Furthermore, the hardware of the control unit 105 shown in Figure 1 is a computer, which performs its functions as a functional unit by executing programs. The device control unit 212, the light quantity correction value calculation unit 211, the absorbance calculation unit 205 shown in Figure 2, and the measurement value calculation unit 301 shown in Figure 3 are all examples of functional units. Hereinafter, the main hardware component of these functional units is the computer (control unit 105). The computer executes processing according to the program read from memory while appropriately utilizing resources such as memory and communication interfaces via a processor. Furthermore, the processing used to implement the functions is not limited to software program processing; it can also be implemented using dedicated circuits. Dedicated circuits can utilize FPGAs (Field Programmable Gate Arrays), ASICs (Application Specific Integrated Circuits), etc.

[0037] Using Figure 3, the light quantity correction function of Embodiment 1 will be described. The light source 104 emits light by being supplied with current from the current adjustment unit 202. The light emitted from the light source 104 is measured as light quantity in the photometer 208, and the light quantity data is sent to the absorbance calculation unit 205. The light source 104 has a temperature measuring unit 209 for measuring the light source temperature, and the photometer 208 has a temperature measuring unit 210 for measuring the photometer temperature. The temperature data measured by the temperature measuring units 209 and 210 is sent to the light quantity correction value calculation unit 211. The light quantity correction value calculation unit 211 calculates the light quantity correction value according to a pre-calculated and maintained light quantity correction rate and the temperature data sent from the temperature measuring units 209 and 210. Thus, by using both the temperature information of the light source 104 and the temperature information of the photometer 208, it is possible to obtain light quantity information that eliminates the influence of temperature changes on both the light source side and the detector side.

[0038] The calculated light intensity correction value is sent to the absorbance calculation unit 205. The absorbance calculation unit 205 calculates the absorbance based on the light intensity data and the light intensity correction value. The calculated absorbance is sent to the measurement value calculation unit 301. The measurement value calculation unit 301 calculates the measurement value set according to the measurement item based on the sent absorbance data. The calculated measurement value is displayed to the user through the display unit 101.

[0039] Here, the light quantity correction value calculation unit 211 calculates the light quantity correction value based on the temperature data and light quantity correction rate received from the temperature measurement units 209 and 210. The light quantity correction value calculation unit 211 can also maintain both the light quantity correction rate for light source temperature correction and the light quantity correction rate for photometer temperature correction. The light quantity correction rate for light source temperature correction can be obtained by measuring the light quantity from the light source using a photometer with a constant photometer temperature while changing the ambient temperature of the light source. Conversely, the light quantity correction rate for photometer temperature correction can be obtained by measuring the light quantity from a light source with a constant light source temperature using a photometer while changing the photometer temperature. In this case, the light quantity correction value is calculated as the sum of the light quantity correction value based on the light source temperature change of the light source 104 and the light quantity correction value based on the photometer temperature change of the photometer 208.

[0040] Furthermore, the light intensity correction rate can be a value inherent to each device. Therefore, the light intensity correction rate can be calculated using the actual device. In particular, when using an LED light source as the light source 104, since the LED light source is a consumable, the device itself can calculate the light intensity correction rate for light source temperature correction. For example, when starting the device after disconnecting the power supply, the light intensity correction rate for light source temperature correction can be calculated based on the light intensity change from illuminating the light source 104 until the light intensity stabilizes, and the temperature measurement unit 209 measuring the temperature data during this period.

[0041] Thus, by using the method for calculating the light quantity correction value shown in Figure 3, it is possible to calculate the light quantity correction value corresponding to temperature variations at both the light source and the photometer. Furthermore, by setting the light quantity correction rate to an inherent value for the device, it is possible to calculate the light quantity correction value reflecting the individual differences of each device.

[0042] Next, the calculation flow of the measured value in Example 1 will be described using Figure 4. This flow is executed by the control unit 105. When the measurement of the automatic analysis device begins, firstly, the measurement preparation operation S401 is started. During the measurement preparation operation S401, the reference temperature measurement S402 is performed. In the reference temperature measurement S402, the measured value of the temperature at that time point measured by the temperature measurement units 209 and 210 is stored. Next, the process moves to the measurement operation S403. In the measurement operation S403, the temperature information acquisition S405 of the temperature measurement units 209 and 210 is performed in parallel with the light intensity measurement S404, and the light intensity correction value calculation S406 is performed using the acquired temperature data. In the light intensity correction value calculation S406, the difference between the reference temperature measured in the reference temperature measurement S402 and the temperature at the time of light intensity measurement obtained in the temperature information acquisition S405 is calculated, and the light intensity correction value is calculated based on the difference and the light intensity correction rate. The absorbance calculation S407 is performed using the light intensity data measured in the light intensity measurement S404 and the light intensity correction value calculated in the light intensity correction value calculation S406. Then, the absorbance data calculated in the absorbance calculation S407 is used to calculate the measured value in the measured value calculation S408.

[0043] Figure 5 is a graph showing the relationship between temperature and light intensity for each wavelength. The horizontal axis represents temperature, and the vertical axis represents light intensity. The solid line represents the change in light intensity relative to the temperature change of wavelength A, and the dashed line represents the change in light intensity relative to the temperature change of wavelength B. The slope of this graph corresponds to the light intensity correction rate. Let the light intensity at the reference temperature t0 be 100%, and the light intensity at any temperature t1 be a% for wavelength A and b% for wavelength B. Figure 5 shows an example where the relationship is b < 100 < a. Thus, the temperature dependence of light intensity generally varies with the wavelength of light. Furthermore, the difference in temperature dependence based on this wavelength is the same for both the light source temperature and the photometer temperature. Therefore, it is expected that the light intensity correction value calculation unit 211 maintains the light intensity correction rate for light source temperature correction and the light intensity correction rate for photometer temperature correction according to the wavelength used for measurement.

[0044] For example, the light intensity correction rate is pre-determined according to wavelength. The temperature of the blank water before measurement is set as the reference temperature t0, and the light intensity at the start of the measurement is set to 100%. The baseline light intensity used for absorbance calculation is corrected for temperature variations from the reference temperature t0. For instance, if the temperature rises by +0.1°C from the reference temperature t0, and the light intensity correction rate at a certain wavelength is +1% / 1°C, the corrected baseline light intensity becomes 100.1%. By using the light intensity correction rate for each wavelength in this way, appropriate light intensity correction can be applied to variations from the reference temperature according to wavelength.

[0045] Example 2

[0046] The optical system and surrounding devices used in the automated analysis apparatus of Example 2 will be described using Figure 6. Structures common to Example 1 will be labeled with the same symbols, and repeated descriptions will be omitted. The description will focus on the points that differ from Example 1.

[0047] The photometer 208 has a temperature adjustment unit 602 for adjusting its ambient temperature. Temperature data measured by temperature measuring units 209 and 210 is sent to a temperature adjustment value calculation unit 601. The temperature adjustment value calculation unit 601 calculates a temperature adjustment value based on the sent temperature data and adjusts the output of the temperature adjustment unit 602 set in the photometer 208 according to this value. The device control unit 212, temperature adjustment value calculation unit 601, absorbance calculation unit 205 shown in FIG. 6, and measurement value calculation unit 301 shown in FIG. 7 are all functional units, and the main hardware component is a computer (control unit 105).

[0048] The temperature adjustment function of Example 2 will be described using Figure 7. Temperature data measured by temperature measuring units 209 and 210 is sent to temperature adjustment value calculation unit 601. Temperature adjustment value calculation unit 601 calculates the temperature adjustment value based on a pre-calculated and maintained temperature adjustment rate, and the difference between the light source temperature and photometer temperature provided by temperature measuring units 209 and 210 and their respective reference temperatures. The calculated temperature adjustment value is sent to temperature adjustment unit 602. In temperature adjustment unit 602, the output is changed according to the provided temperature adjustment value, adjusting the temperature of photometer 208. Light emitted from light source 104 is measured as light intensity in photometer 208, and the light intensity data is sent to absorbance calculation unit 205 to calculate absorbance. The calculated absorbance is sent to measurement value calculation unit 301. Measurement value calculation unit 301 calculates the measurement value set according to the measurement item based on the received absorbance data.

[0049] Here, the temperature adjustment rate is set to compensate for the change in light quantity accompanying temperature variations in the light source 104 by adjusting the temperature of the photometer 208. Alternatively, the temperature adjustment rate can be a value inherent to each device. As explained in Embodiment 1, the light source correction rate for light source temperature correction can be calculated using an actual device, and the temperature dependence of the light quantity accompanying temperature variations in the light source can be obtained. On the other hand, the temperature dependence of the light quantity accompanying temperature variations in the photometer (which is not a consumable) is provided to the device in advance, and the temperature dependence of the light quantity accompanying temperature variations in the photometer is known. If information on both temperature dependencies exists, the temperature adjustment rate of the photometer 208 that compensates for the change in light quantity accompanying temperature variations in the light source 104 can be determined according to the device.

[0050] Thus, by using the calculation method of the temperature adjustment value shown in Figure 7, the change in light intensity caused by temperature variation on the light source side can be offset or reduced by the change in light intensity caused by temperature variation on the photometer side.

[0051] Next, the calculation process for the measured value in Example 2 will be described using Figure 8. This process is executed by the control unit 105. Steps common to those in Figure 3 are labeled with the same symbols, and repeated explanations are omitted. In measurement action S403, temperature information acquisition S405 is performed, and temperature adjustment value calculation S801 is performed using the acquired temperature data. Temperature adjustment of the photometer S802 is performed based on the temperature adjustment value calculated in temperature adjustment value calculation S801.

[0052] Figure 9 shows the relationship between the light source temperature and the photometer adjustment temperature for each wavelength. The photometer adjustment temperature is the amount of adjustment used to compensate for changes in light intensity caused by variations in the light source temperature. The horizontal axis represents the light source temperature, and the vertical axis represents the photometer adjustment temperature. A solid line represents the relationship between the photometer adjustment temperature and the light source temperature at wavelength A, and a dashed line represents the relationship between the photometer adjustment temperature and the light source temperature at wavelength B. Let the photometer adjustment temperature at the reference temperature t0 be 0℃, the photometer adjustment temperature at any temperature t1 for wavelength A be c℃, and the photometer adjustment temperature for wavelength B be d℃. Thus, the temperature adjustment rate generally varies according to the wavelength of light.

[0053] Therefore, it is preferable to pre-set a temperature adjustment rate corresponding to the wavelength of light, and select a temperature adjustment rate for any wavelength. For example, the temperature adjustment rate of the wavelength that is most affected by changes in light intensity due to temperature variations is selected. For example, when the selected wavelength increases by +0.01°C, with a temperature adjustment rate of +5°C / 1°C, the adjustment temperature value is calculated to be 0.05°C, and the output of the temperature adjustment unit 602 is adjusted to generate a temperature change of this value in the photometer. In this way, control is performed in a manner that offsets the changes in light intensity caused by temperature variations on the light source side by generating temperature variations on the photometer side.

[0054] Furthermore, while it's theoretically possible to equip the light source with a temperature adjustment unit to offset the light intensity variation caused by temperature fluctuations on the photometer side, since the light source is a replaceable component, including a temperature adjustment unit would increase operating costs. Embodiment 2 avoids this increase by equipping the non-replaceable photometer 208 with a temperature adjustment unit 602. Additionally, the light intensity variation relative to temperature fluctuations on the photometer side is smaller than that on the light source side, thus requiring less precise control compared to controlling the light source side.

[0055] Example 3

[0056] In Example 3, a machine learning model that has been learned is applied. Specifically, the learned machine learning model can be used to correct the light quantity correction value calculated by the light quantity correction value calculation unit 211 in Example 1, or the temperature adjustment value calculated by the temperature adjustment value calculation unit 601 in Example 2. It is assumed that the light quantity correction value calculation unit 211 and the temperature adjustment value calculation unit 601 calculate the light quantity correction value and the temperature adjustment value based on a model with the light source temperature and photometer temperature as variables. However, due to the influence of individual differences in the light source and photometer, device structure, etc., the effect of offsetting the influence of temperature changes on the light quantity correction value and the temperature adjustment value may become insufficient. Therefore, a learned model that has been learned can be used to correct the light quantity correction value and the temperature adjustment value using additional explanatory variables.

[0057] The following description uses a learning model for calculating the light quantity correction value in Example 1 as an example. Figure 10A shows an example of the hardware structure of the learning device 1000 used to train the learning model. The learning device 1000 is configured to transmit and receive signals with the control unit 105.

[0058] The learning device 1000 is implemented as an information processing device with a main structure including a processor (CPU) 1001, a memory 1002, a recording device 1003, an input interface (I / F) 1004, an output I / F 1005, a communication I / F 1006, and a bus 1007. The processor 1001 functions as a functional unit (functional block) providing specified functions by executing a program loaded into the memory 1002. The recording device 1003 stores the data and programs used by the functional unit. The recording device 1003 uses, for example, a non-volatile storage medium such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The input I / F 1004 is an interface for connecting input devices 1008 such as keyboards and indicator devices, and the output I / F 1005 is an interface for connecting a display device 1009. The communication I / F 1006 enables communication with the control unit 105 and other information processing devices. They are interconnected communicatively via the bus 1007.

[0059] In addition, all or part of the functions of the software-based system can be implemented using hardware such as FPGAs and ASICs. Furthermore, all or part of the functions can be implemented using multiple information processing devices, or it can be implemented as a cloud application. Also, in Figure 10A, the processor 106, recording device 107, and communication I / F 108 of the control unit 105, which has the same hardware structure as the learning device 1000, are extracted and shown.

[0060] Figure 10B shows a functional block diagram for training (learning) the learning model of Example 3. The recording device 107 of the control unit 105 stores the learning model 1014 learned by the learning device 1000. Learning data 1010 for generating supervision data is input to the learning device 1000.

[0061] The learning data 1010 includes, for example, experimental data 1011 collected by repeatedly measuring multiple samples with absorbance at a specified relationship using the pre-shipment apparatus, individual optical system data 1012 for the optical system of the apparatus used in the experiment, and a formula 1013 for calculating the light quantity correction value used in light quantity correction. The experimental data 1011 collected at this time includes temperature data from temperature measuring units 209 and 210, light quantity data from photometer 208, and room temperature data. Furthermore, the individual optical system data 1012 includes the measurement wavelength, photometer wavelength adjustment value, initial light quantity, and light source usage time. The measurement wavelength is the wavelength measured by photometer 208, the photometer wavelength adjustment value is an adjustment value used to correct deviations in the wavelength measured by photometer 208, the initial light quantity is the light quantity at the start of using light source 104, and the usage time is the cumulative illumination time of light source 104. The formula 1013 for calculating the light quantity correction value is a correction formula used by the light quantity correction value calculation unit 211 to calculate the light quantity correction value.

[0062] Figure 11 is a diagram illustrating an example of a neural network-based learning model 1100. The learning model 1100 has an input layer 1101, an intermediate layer 1102, and an output layer 1103. Description variables input to the input layer 1101 are propagated to the intermediate layer 1102, and then sequentially to the output layer 1103. The output layer 1103 outputs the inference result (target variable) based on the description variables input to the input layer 1101. Furthermore, in general, the intermediate layers of a neural network consist of multiple layers, but this is simplified here. The input layer 1101, intermediate layer 1102, and output layer 1103 each have multiple input units, intermediate units, and output units, represented by circles. The input data (description variables) input to each input unit of the input layer 1101 are weighted by the coupling coefficient between the input unit and the intermediate unit and then input to each intermediate unit. The value of the intermediate unit in the intermediate layer 1102 is calculated by summing the values ​​from the input units. Furthermore, the outputs from each intermediate unit in intermediate layer 1102 are weighted by the coupling coefficient between the intermediate unit and the output unit and then input to each output unit. The values ​​from the intermediate units are summed to calculate the value of the output unit in output layer 1103. Thus, the processing in intermediate layer 1102 is equivalent to performing a nonlinear transformation on the input data values ​​input to input layer 1101 and outputting them as output data in output layer 1103.

[0063] For example, the input data 1104, which is used as an explanatory variable, is the data obtained from the learning data 1010. The output data 1105, which is used as the target variable, is labeled as "Maintaining Light Adjustment Value", "Correcting Light Adjustment Value", and "Unable to Calculate Light Adjustment Value (Abnormal)".

[0064] The supervision data generation unit 1022 shown in Figure 10B generates supervision data, which is a combination of input data 1104 for the learning model 1100 and labels that become its correct solutions, based on the learning data 1010. The input data 1104 that becomes supervision data extracts the values ​​of the parameters that become input data 1104 from the learning data 1010. The correct solution labels are calculated based on the learning data 1010. For example, the light intensity assumed according to the sample is compared with the light intensity calculated using the light intensity correction value calculation formula 1013. If the two are considered to be approximately equivalent, it is set to "light intensity adjustment value maintenance". If they are not equivalent but the difference is within a specified value, it is set to "light intensity adjustment value correction". If the difference exceeds a specified value, it is set to "light intensity adjustment value cannot be calculated (abnormal)". Furthermore, in the case of "light intensity adjustment value correction", it is preferable to also learn the correction amount of the light intensity adjustment value.

[0065] Using the supervisory data generated by the supervisory data generation unit 1022, the learning model update unit 1023 trains the learning model 1100. The completed learning model 1014 is sent from the output unit 1025 to the control unit 105 and stored in the recording device 107 for determining and correcting light intensity correction values. Furthermore, a prototype of the learning model 1100 is stored in the algorithm database 1024. Here, an example of a neural network-based learning model is shown, but it is not limited to this.

[0066] Using Figure 12, the light intensity correction function of Embodiment 3 will be described. Unlike Figure 3 (Embodiment 1), the light intensity correction value correction determination unit 1201 is a functional unit that uses the learned model 1014 to determine whether the light intensity correction value needs correction. The light intensity correction value correction determination unit 1201 uses the learned model 1014 to determine whether the light intensity correction value calculated by the light intensity correction value calculation unit 211 needs correction, and outputs the determination result to the light intensity correction value calculation unit 211. If the determination result is "light intensity adjustment value maintained," the light intensity correction value calculated by the light intensity correction value calculation unit 211 is output to the absorbance calculation unit 205. If the determination result is "light intensity adjustment value corrected," the light intensity correction value calculation unit 211 corrects the calculated light intensity correction value according to the correction amount output by the learned model 1014, and then outputs it to the absorbance calculation unit 205. If the determination result is "unable to calculate light quantity adjustment value (abnormal)", the light quantity correction value calculation unit 211 stops the subsequent processing and requests an alarm notification to the device control unit 212.

[0067] The above describes an example of using the learned model 1014 to determine whether the light intensity correction value needs to be corrected, as described in Embodiment 3. However, it is also possible to determine whether the temperature correction value of Embodiment 2 needs to be corrected in the same way. The learned model used to determine whether the temperature adjustment value needs to be corrected can also be generated in the same way as described above. The learning data uses experimental data, optical system individual data for the optical system related to the device for which the experimental data was obtained, and the temperature adjustment value calculation formula used by the temperature adjustment value calculation unit 601 in calculating the temperature adjustment value.

[0068] The temperature adjustment function of Embodiment 3 will be described using Figure 13. Unlike Figure 7 (Embodiment 2), the temperature adjustment value correction determination unit 1301 uses a learned model to determine whether the temperature adjustment value needs correction. The temperature adjustment value correction determination unit 1301 uses the learned model to determine whether the temperature adjustment value calculated by the temperature adjustment value calculation unit 601 needs correction, and outputs the determination result to the temperature adjustment value calculation unit 601. If the determination result is "temperature adjustment value maintained," the temperature adjustment value calculated by the temperature adjustment value calculation unit 601 is output to the temperature adjustment unit 602. If the determination result is "temperature adjustment value corrected," the temperature adjustment value calculation unit 601 corrects the calculated temperature adjustment value according to the correction amount output by the learned model, and then outputs it to the temperature adjustment unit 602. If the determination result is "unable to calculate light intensity adjustment value (abnormal)," the temperature adjustment value calculation unit 601 stops subsequent processing and requests an alarm notification to the device control unit 212.

[0069] This invention is not limited to the embodiments described above, and includes various modifications. For example, the embodiments described above are examples provided for ease of understanding and illustration of the invention, and are not necessarily limited to having all the described structures. A portion of the structure of one embodiment can be replaced with the structure of another embodiment, and structures of other embodiments can be added to the structure of one embodiment. Regarding a portion of the structure of each embodiment, other structures can be added, deleted, or replaced.

[0070] Symbol Explanation

[0071] 101: Display unit; 102: Input unit; 103: Analysis unit; 104: Light source; 105: Control unit; 106: Processor; 107: Recording device; 108: Communication interface; 201: Current detection unit; 202: Current adjustment unit; 203: Reaction vessel; 204: Reaction tank; 205: Absorbance calculation unit; 206: Photodetector; 207: Diffraction grating; 208: Photometer; 209: Temperature measurement unit; 210: Temperature measurement unit; 211: Light quantity correction value calculation unit; 212: Device control unit; 301: Measured value calculation unit; 601: Temperature adjustment value calculation unit; 602: Temperature adjustment unit; 1000: Learning device; 1001: Processor (CPU); 1002: Memory; 1003: Recording device. Device, 1004: Input interface, 1005: Output interface, 1006: Communication interface, 1008: Input device, 1009: Display device, 1010: Learning data, 1011: Experimental data, 1012: Individual data of optical system, 1013: Light correction value calculation formula, 1014: Learning model, 1021: Input unit, 1022: Supervision data generation unit, 1023: Learning model update unit, 1024: Algorithm database, 1025: Output unit, 1100: Learning model, 1101: Input layer, 1102: Intermediate layer, 1103: Output layer, 1104: Input data, 1105: Output data, 1201: Light correction value correction determination unit, 1301: Temperature adjustment value correction determination unit.

Claims

1. An automatic analysis device, characterized in that, It comprises: a light source having a first temperature measuring unit that irradiates light onto a container holding a mixture of a sample and a reagent; a photometer having a second temperature measuring unit that measures the amount of light from the light source that passes through the mixture; and a light quantity correction value calculation unit that calculates a light quantity correction value based on the light source temperature measured by the first temperature measuring unit and the photometer temperature measured by the second temperature measuring unit. And an absorbance calculation unit, which calculates the absorbance of the mixture based on the light intensity measured by the photometer and the light intensity correction value.

2. The automatic analysis device according to claim 1, characterized in that, The light quantity correction calculation unit maintains the light quantity change relative to the temperature change of the light source, i.e., the first light quantity change rate, and the light quantity change relative to the temperature change of the photometer, i.e., the second light quantity change rate, and calculates the light quantity correction value as the sum of the light quantity correction value based on the temperature change of the light source and the light quantity correction value based on the temperature change of the photometer. The temperature change of the light source is based on the difference between the light source temperature measured by the first temperature measuring unit and the reference temperature, and the change of the first light quantity change rate. The temperature change of the photometer is based on the difference between the photometer temperature measured by the second temperature measuring unit and the reference temperature, and the change of the second light quantity change rate.

3. The automatic analysis device according to claim 2, characterized in that, The photometer includes: a diffraction grating that splits incident light according to wavelength; and a photodetector that detects the split light, wherein the light quantity correction calculation unit maintains the first light quantity change rate and the second light quantity change rate for each wavelength.

4. The automatic analysis device according to claim 1, characterized in that, The automatic analysis device includes a light quantity correction determination unit that evaluates and corrects the light quantity correction value calculated by the light quantity correction value calculation unit using a learned model. The learned model is a learning model learned using at least experimental data, individual optical system data of an optical system including the light source and the photometer related to the device that obtained the experimental data, and supervision data generated according to the light quantity correction value calculation formula used by the light quantity correction value calculation unit in the calculation of the light quantity correction value.

5. An automatic analysis device, characterized in that, The device comprises: a light source having a first temperature measuring unit that irradiates light onto a container holding a mixture of a sample and a reagent; a photometer having a second temperature measuring unit that measures the amount of light from the light source that passes through the mixture; a temperature adjustment value calculation unit that calculates a temperature adjustment value based on the light source temperature measured by the first temperature measuring unit and the photometer temperature measured by the second temperature measuring unit; and a temperature adjustment unit that adjusts the temperature of the photometer based on the temperature adjustment value. And an absorbance calculation unit, which calculates the absorbance of the mixture based on the amount of light measured by the photometer.

6. The automatic analysis device according to claim 5, characterized in that, The temperature adjustment calculation unit maintains a temperature adjustment rate set to offset the change in light intensity relative to the change in the temperature of the light source by the temperature change of the photometer, and calculates the temperature adjustment value based on the difference between the light source temperature and the reference temperature measured by the first temperature measuring unit, the difference between the photometer temperature and the reference temperature measured by the second temperature measuring unit, and the temperature adjustment rate.

7. The automatic analysis device according to claim 6, characterized in that, The photometer includes: a diffraction grating that splits incident light according to wavelength; and a photodetector that detects the split light, wherein the temperature adjustment calculation unit maintains the temperature adjustment rate for each wavelength.

8. The automatic analysis device according to claim 5, characterized in that, The automatic analysis device includes a temperature adjustment value correction determination unit, which evaluates and corrects the temperature adjustment value calculated by the temperature adjustment value calculation unit using a learned model. The learned model is a learning model learned using experimental data, individual optical system data related to the device that obtained the experimental data, including the light source and the photometer, and supervision data generated based on the temperature adjustment value calculation formula used by the temperature adjustment value calculation unit in calculating the temperature adjustment value.

Images