Vacuum monitoring

Abstract

Errors in an analyzer fluidics system may be detected using systems and methods which involve obtaining a plurality of pressure measurements while a vacuum is being applied to a tube used to remove fluid from a container. These measurements may then be provided to a classification module, and the classification module may determine a status output as either a normal status output, or one of a set of error status outputs.

Description

VACUUM MONITORINGCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to and benefit of U.S. Provisional Application Serial No. 63 / 524,435, filed June 30, 2023, the contents of which are incorporated herein by reference in their entirety.BACKGROUND

[0002] Clinical analyzers and / or immunoassays are well known in the art and are generally used for automated or semi- automated analysis of patient samples, such as blood, urine, spinal fluid, and the like. For testing and analyzing a patient sample, a specific component (for example, an antigen) is measured in the patient sample. Analysis of the patient sample involves general procedures, such as aspirating the patient sample from a sample vessel, dispensing the patient sample into a reaction vessel, aspirating a reagent from a reagent pack, dispensing the reagent into the reaction vessel, and so on. Such procedures are typically conducted by using one or more probes, such as a pipetting device (also referred to as a pipettor).

[0003] For many aspirating and dispensing procedures, it is important that the pipettor is periodically cleaned, such as to avoid cross contamination between different patient samples or different reagents. For example, in some instances, a portion of a patient sample may contact the pipettor as the pipettor dispenses the reagent into the reaction vessel, and may then be carried from the reaction vessel by the pipettor. Additionally or alternatively, a reagent pipettor comes into contact with different reagents (within a test pack and between test packs) which, if not properly cleaned off a pipettor may result in contamination between reaction vessels, from a reaction vessel to a reagent pack, or between different portions of a reagent pack. Thus, it may be important to cleanse the pipettor before the pipettor aspirates a sample or reagent and / or before the pipettor dispenses a sample or reagent into a reaction vessel. Any remnant of a prior fluid (reagentor patient sample) may lead to an erroneous result of the analyzer. Tn one exemplary example, for cleaning the pipettor, the tip of the pipettor is moved into a wash tower, where the pipettor is sprayed by an orifice in the side of the wash tower with wash fluid (also referred to as cleaning fluid); the wash fluid is then removed from the wash tower as waste fluid via a vacuum pump and associated tubing. In some cases, there may be a failure such as an obstruction or leak in such a fluidics system that may lead to an inadequate cleaning operation, fluid spills, wasted samples, reagents, or other supplies, and / or inaccurate test results. It would be desirable to detect such errors in order to prompt an appropriate remedial action.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] While the specification concludes with claims which particularly point out and distinctly claim the invention, it is believed the present invention will be better understood from the following description of certain examples taken in conjunction with the accompanying drawings, in which like reference numerals identify the same elements and in which:

[0005] FIG. 1A is a schematic illustration of an example of an analyzer having a wash tower for cleaning a pipettor and a vacuum pump for removing waste fluid from the wash tower, showing the analyzer during a cleaning operation;

[0006] FIG. IB is a schematic illustration of the analyzer of FIG. 1 A, showing an obstruction in a tubing extending between the wash tower and the vacuum pump;

[0007] FIG. 1C is a schematic illustration of the analyzer of FIG. 1A, showing a leak in the tubing extending between the wash tower and the vacuum pump;

[0008] FIG. ID is a schematic illustration of the analyzer of FIG. 1A, showing an absence of fluid in the wash tower;

[0009] FIG. 2 depicts a method for detecting errors in an analyzer fluidics system; and

[0010] FIG. 3 illustrates a method for determining a status output.

[0011] The drawings are not intended to be limiting in any way, and it is contemplated that various embodiments of the invention may be carried out in a variety of other ways, including those not necessarily depicted in the drawings. The accompanying drawings incorporated in and forming a part of the specification illustrate several aspects of the present invention, and together with the description serve to explain the principles of the invention; it being understood, however, that this invention is not limited to the precise arrangements shown.DETAILED DESCRIPTION

[0012] Turning now to the drawings, FIGS. 1A-1D schematically show an example of a portion of an analyzer (10) for automated or semi-automated analysis of patient samples, such as blood, urine, spinal fluid, and the like. In the example shown, analyzer (10) includes a pipettor (12) configured to aspirate and / or dispense a fluid, such as a reagent. To that end, pipettor (12) includes a distal tip (14) configured to be moved into a first vessel, such as a reagent pack, to allow pipettor (12) to aspirate a fluid, such as a reagent, from the first vessel; and further configured to be moved into a second vessel, such as a reaction vessel, to allow pipettor (12) to dispense the fluid into the second vessel. Pipettor (12) of the present example includes a generally cylindrical outside surface (16) and a generally cylindrical inside surface ( 18) that defines an inner lumen for receiving the fluid. While pipettor (12) of the present example is described for aspirating and / or dispensing a reagent, it will be appreciated that pipettor (12) may alternatively be used for aspirating and / or dispensing any other suitable fluid, such as a patient sample.

[0013] Analyzer (10) further includes a wash tower (20) for periodically cleaning at least a portion of pipettor (12), such as distal tip (14), as shown in FIG. 1A. Wash tower (20) of the present example includes a container (22) defining an interior (24) that is configured to selectively receive at least a portion of pipettor (12), and that is further configured to collect waste fluid (W) from a cleaning procedure. In this regard, container (22) has an open top (26) for enabling at least a distal portion of pipettor (12), such as distal tip (14), to be selectively inserted into interior (24) through open top (26). Due to top (26) beingopen, it will be appreciated that interior (24) and any waste fluid (W) contained therein may be exposed to the surrounding environmental (c.g., atmospheric) pressure. Container (22) of the present example also has a bottom drain (28) for allowing the waste fluid (W) collected within interior (24) to gravitate toward bottom drain (28) and thereby exit interior (24).

[0014] In the example shown, wash tower (20) also includes at least one orifice (30) configured to spray or otherwise apply wash fluid (F) to at least the distal portion of pipettor (12), such as distal tip (14), when the distal portion of pipettor (12) is inserted into interior (24) of container (22). Orifice (30) of the present example extends through a sidewall of container (22) to generally face at least the distal portion of pipettor (12), such as distal tip (14), when the distal portion of pipettor (12) is inserted into interior (24) of container (22). Orifice (30) may be in fluid communication with a wash fluid reservoir and / or a wash fluid pump (not shown) for directing wash fluid (F) received therefrom onto pipettor (12). More particularly, orifice (30) may be configured to spray wash fluid (F) onto outside surface (16) of pipettor (12) along at least the distal portion of pipettor (12). In some versions, orifice (30) may be defined by a nozzle (not shown) that protrudes into interior (24) of container (22). In addition, or alternatively, wash fluid (F) may be pumped through a proximal (e.g., top) portion of pipettor (12) onto inside surface (18) of pipettor (12) along at least the distal portion of pipettor (12). In this manner, the wash fluid (F) may cleanse any remnant of a prior fluid to which pipettor (12) was exposed, such as a prior patient sample, from pipettor (12) before pipettor (12) is used for a subsequent aspirating and / or dispensing procedure. For example, the wash fluid (F) may effectively remove any remnant of a prior patient sample or reagent from pipettor (12), and the mixture of wash fluid (F) and sample and / or reagent removed from pipettor (12) may be collected within interior (24) of container (22) and directed toward bottom drain (28) as waste fluid (W) for removal from wash tower (20).

[0015] In this regard, analyzer (10) further includes a waste fluid pump in the form of a vacuum pump (40) and a tube (also referred to as tubing) (42) operatively coupled to bottom drain (28) and vacuum pump (40). Vacuum pump (40) may be configured to applya vacuum to tube (42) to thereby remove the waste fluid (W) from interior (24) of container (22) and / or convey the waste fluid (W) to a waste receptacle (not shown) via tube (42), such that tube (42) at least partially defines a discharge passageway extending from bottom drain (28) toward vacuum pump (40). In the example shown, at least one pressure sensor (e.g., transducer) (44) is positioned within the discharge passageway defined by tube (42) for obtaining measurements of the fluid pressure within the discharge passageway defined by tube (42), such as while vacuum pump (40) is applying a vacuum to tube (42). Pressure sensor (44) of the present example is positioned within the discharge passageway defined by tube (42) at a location proximate the vacuum pump (40) for obtaining measurements of the fluid pressure within tube (42) at or near an interface between tube (42) and vacuum pump (40). For example, pressure sensor (44) may be positioned at or near an inlet port of vacuum pump (40) for obtaining measurements of the fluid pressure at or near the inlet port of vacuum pump (40). While tube (42) may be included in some examples, tube (42) may alternatively be omitted such that vacuum pump (40) may be directly coupled to bottom drain (28). In such cases, the pressure sensor (44) may be positioned within a discharge passageway defined only by the inlet port of vacuum pump (40), for example.

[0016] Analyzer (10) of the present example further includes a processor (50) in operative communication with pressure sensor (44) for receiving the pressure measurements from pressure sensor (44). As discussed in greater detail below, processor (50) may be configured to utilize the pressure measurements received from pressure sensor (44) in order to accurately determine a status output (e.g., an error status output) for the fluidics system that is at least partially defined by container (22), orifice (30), vacuum pump (40), and tube (42). For example, the pressure measurements received from pressure sensor (44) may be indicative of an obstruction within tube (42) upstream of pressure sensor (44) that is preventing some or all of the waste fluid (W) from reaching pressure sensor (44), which may be referred to as an “obstructed condition” error status output, as shown in FIG. IB. In addition, or alternatively, the pressure measurements received from pressure sensor (44) may be indicative of a leak in tube (42) upstream of pressure sensor (44) that is preventing some or all of the waste fluid (W) from reaching pressure sensor (44), and / or an absenceof any wash fluid (F) within interior (24) of container (22) such that there is likewise an absence of any waste fluid (W) within tube (42), cither of which may be referred to as a “no fluid” error status output, as shown in FIGS. 1C and ID, respectively. In some versions, processor (50) may be configured to take remedial action in response to an error status output.

[0017] As an illustration of how a processor may be used in determining a status output for the fluidics system, consider FIG. 2, which depicts a method for detecting errors in an analyzer fluidics system. In that method, a pipettor tip would be moved (201) into a container (e.g., the container (22) of wash tower (20)) and a cleaning fluid would be applied to the inside and / or outside of the pipettor. After the cleaning fluid is applied, the fluid would be collected (202) in the container, and a vacuum would be applied (203) to the tube to remove the fluid from the container. While this vacuum was being applied (203), a plurality of pressure measurements may be obtained (204), such as by using a sensor (44) as described in the context of FIG. 1A. These measurements can be provided (204) to a classification module, which would determine (205) a status output based on the measurements.

[0018] To illustrate how a classification module may determine (205) a status output, consider FIG. 3 which illustrates a method for determining a status output using a plurality of convolution kernels, a plurality of pooling operators, and a classifier. Initially, in the method of FIG. 3, a plurality of convolution outputs would be obtained (301) based on convolving the plurality of pressure measurements with a plurality of convolution kernels. This step may be done in procedure which begins by representing measurements of pressure within the tube (42) as a one-dimensional vector of values Pi to Pn. This onedimensional vector may then be convolved with a set of one-dimensional convolution vectors (the convolution kernels), which may be randomly generated (e.g., kernels whose values are random in terms of their lengths, weights, bias, dilation, and / or padding), or may be fixed (e.g., having predefined length, weight, dilation, bias, and / or padding). Each of the vectors obtained by convolving the pressure vector with one of the convolution vectorswould then be a convolution output, resulting in a plurality of convolution outputs being obtained that could then be subjected to further processing to determine the status output.

[0019] An example of the type of processing which may be applied to the plurality of convolution outputs is to obtain features (302) by application of one or more pooling operators. These pooling operators may, for each of the convolution outputs, derive a feature which combines one or more values from that convolution output into a single value. For example, the proportion of positive values pooling operator may provide a feature in the form of a single value equal to the number of values in a convolution output which are above 0 divided by the total number of values in the convolution output which are above zero. Other examples of pooling operators which may be applied include means of positive values, mean of indices of positive values, and longest stretch of positive values, all of which would take a multi-element convolution output as input, and use it to derive a single valued feature. Of course, it should be understood that other types of features may also be obtained (302) through the application of pooling operators. For example, an every m max pooling operator could transform a n value convolution output into an n / m value convolution output by taking the maximum of every m values from the convolution output and using those maxima to construct a new vector. Other types of pooling operators could also be used, and so the example pooling operators described above should be understood as being illustrative only, and should not be treated as limiting.

[0020] Continuing with the discussion of FIG. 3, once the plurality of features had been obtained (302), those features may be provided (303) as input to a classifier, and the output of the classifier may be treated as the status output for the fluidics system. This classifier may be, for example, a neural network which has been trained on a set of training data comprising groups of features derived from pressure measurements using the classification module’s convolution kernels and pooling operators, were each group was annotated with a verified status for the fluidics system (e.g., if the fluidics system was discovered to be obstructed, then a group of features derived from a set of pressure measurements taken while the fluidics system was obstructed could be annotated with the “obstructed” class). Other types of classifiers, such as support vector machines, decision tree classifiers, orvarious types of linear or nonlinear classifiers may also be used as alternatives to the neural network classifier described above.

[0021] Of course, other variations beyond simply the use of different types of convolution kernels, pooling operators or classifiers are also possible, and may be used to implement classification modules in some embodiments of the disclosed technology. For example, in some cases, determining a status output for an analyzer fluidics system may include steps other than those shown in FIG. 3. For example, in some cases determining the status output for an analyzer fluidics system may include generating a derived sequence of pressure measurement changes by taking first order differences from the plurality of pressure measurements. Where such a derived sequence is generated, obtaining (301) the plurality of convolution outputs may comprise convolving the derived sequence of pressure measurements with its own plurality of convolution kernels, thereby providing a richer dataset for use in obtaining (302) features and potentially allowing for more accurate classifications. Other types of classification, such as described in Middlehurst M, et. al., HIVE-COTE 2.0: a new meta ensemble for time series classification, Machine Learning 110, 3211-3243 (2021) or C.W. Tan, et. al., MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification, Data Mining and Knowledge Discovery 36, 1623-1646 (2022), each of which is incorporated herein in its entirety could also be used, as could tree / forest models, shapelet / wavelet-based models, recurrent neural network and long short-term memory based models, and K-nearest neighbor and K-means based models.

[0022] Variations are also possible in terms of the physical components which could be used in systems or methods implemented based on this disclosure. For example, while the above discussion explained that methods such as shown in FIG. 2 could be performed locally on an analyzer, it is also possible that measurements collected on an analyzer may be sent to a remote location (e.g., a cloud based server) for analysis, rather than (or in addition to) the analyzer analyzing the measurements using its own processor.

[0023] As another example, while the above discussion is provided in the context of cleaning a pipettor (12), it will be appreciated that the above discussion applies to the cleaning of any other suitable types of vessels that may come into contact with patient samples, such as cuvettes, sample cups, tubes, reaction vessels, etc., and further applies to the cleaning of any other suitable objects, such as grippers, collets, camera lenses, etc. Accordingly, both the methods described above, and the components used in their practice should be understood as being illustrative only, and should not be treated as limiting.

[0024] To further illustrate potential ways in which the technology described herein may be applied, the following examples are provided as showing systems and methods which may be implemented based on this disclosure.

[0025] Example 1

[0026] A method for detecting errors in an analyzer fluidics system, the method comprising: (a) moving a tip of a pipettor into a container and, while the tip of the pipettor is in the container, applying a fluid, wherein the fluid is a cleaning fluid, to at least one of an inside surface or an outside surface of the pipettor; (b) collecting the fluid in the container after it is applied to the at least one of the inside surface or the outside surface of the pipettor; (c) applying a vacuum to a tube in order to remove the fluid from the container, wherein the tube is operatively connected to the container and to a vacuum pump; (d) while the vacuum is being applied to the tube, obtaining a plurality of pressure measurements, wherein each measurement from the plurality of pressure measurements is a measurement of pressure inside the tube at a location proximate the vacuum pump; (e) providing the plurality of pressure measurements as input to a classification module; and (f) the classification module determining a status output for the analyzer fluidics system based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the status output for the analytics system is a normal status output, or one of a set of error status outputs.

[0027] Example 2

[0028] The method of example 1 , wherein the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises: (a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels; (b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and (c) providing the plurality of features to a classifier comprised by the classification module.

[0029] Example 3

[0030] The method of example 2, wherein the classifier is a linear classifier.

[0031] Example 4

[0032] The method of any of examples 2-3, wherein (a) the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and (b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

[0033] Example 5

[0034] The method of any of examples 2-4, wherein the one or more pooling operators comprises: (a) proportion of positive values; (b) mean of positive values; (c) mean of indices of positive values; and (d) longest stretch of positive values.

[0035] Example 6

[0036] The method of any of examples 1-5, wherein the set of error status outputs comprises: (a) no fluid; and (b) obstructed condition.

[0037] Example 7

[0038] The method of any of examples 1 -6, wherein the tube is attached to the container at a bottom of the container.

[0039] Example 8

[0040] The method of any of examples 1-7, wherein the container is open such that the fluid connected in the container is exposed to atmospheric pressure.

[0041] Example 9

[0042] An analyzer comprising: (a) a pipettor; (b) a container; (c) a vacuum pump; (d) a tube, wherein the tube is operatively connected to the vacuum pump and the container; (e) one or more processors; and (f) a non-transitory computer readable medium storing instructions for, when executed by the one or more processors, performing a fluidics system reliability improvement method with the pipettor as subject pipettor, the container as subject container, and the tube as subject tube, the fluidics system reliability improvement method comprising: (i) moving a tip of the subject pipettor into the subject container; (ii) applying fluid to at least one of an inside surface or an outside surface of the subject pipettor while the tip of the subject pipettor is in the subject container; (iii) applying a vacuum to the subject tube in order to remove the fluid from the subject container; (iv) obtaining a plurality of pressure measurements, wherein each measurement form the plurality of pressure measurements is a measurement of pressure inside the subject tube at a location proximate the vacuum pump; (v) providing the plurality of pressure measurements as input to a classification module; and (vi) the classification module determining an analyzer fluidics system status output based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the analyzer fluidics system status output is a normal status output, or one of a set of error status outputs.

[0043] Example 10

[0044] The analyzer of example 9, wherein the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises: (a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels; (b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and (c) providing the plurality of features to a classifier comprised by the classification module.

[0045] Example 11

[0046] The analyzer of example 10, wherein the classifier is a linear classifier.

[0047] Example 12

[0048] The analyzer of any of examples 10-11, wherein: (a) the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and (b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

[0049] Example 13

[0050] The analyzer of any of examples 10-12, wherein the one or more pooling operators comprises: (a) proportion of positive values; (b) mean of positive values; (c) mean of indices of positive values; and (d) longest stretch of positive values.

[0051] Example 14

[0052] The analyzer of any of examples 9-13, wherein the set of error status outputs comprises: (a) no fluid; and (b) obstructed condition.

[0053] Example 15

[0054] The analyzer of any of examples 9-14, wherein the tube is attached to a bottom of the container.

[0055] Example 16

[0056] The analyzer of any of examples 9-15, wherein: (a) the analyzer comprises a plurality of pipettors, wherein the pipettor is comprised by the plurality of pipettors; (b) the analyzer comprises a plurality of containers, wherein the container is comprised by the plurality of containers; (c) the analyzer comprises a plurality of tubes, wherein the tube is comprised by the plurality of tubes; (d) each pipettor from the plurality of pipettors has a corresponding container from the plurality of containers and a corresponding tube from the plurality of tubes; and (e) the non-transitory computer readable medium stores instructions for, for each pipettor from the plurality of pipettors, performing the fluidics system reliability improvement method with that pipettor as the subject pipettor, the container corresponding to that pipettor as the subject container, and the tube corresponding to that pipettor as the subject tube.

[0057] Example 17

[0058] The analyzer of any of examples 9-16, wherein the container is open such that the fluid within the container is exposed to atmospheric pressure.

[0059] Example 18

[0060] A method for detecting errors in an analyzer fluidics system, the method comprising: (a) applying a cleaning fluid to at least one of an inside surface or an outside surface of an object; (b) collecting the fluid in a container after it is applied to the at least one of the inside surface or the outside surface of the object; (c) applying, via a vacuum pump, a vacuum to a discharge passageway in fluid communication with the container in order to remove the fluid from the container; (d) while the vacuum is being applied to the discharge passageway, obtaining a plurality of pressure measurements, wherein each measurement from the plurality of pressure measurements is a measurement of pressureinside the discharge passageway at a location proximate the vacuum pump; (e) providing the plurality of pressure measurements as input to a classification module; and (f) the classification module determining a status output for the analyzer fluidics system based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the status output for the analytics system is a normal status output, or one of a set of error status outputs.

[0061] Example 19

[0062] The method of example 18, wherein the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises: (a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels; (b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and (c) providing the plurality of features to a classifier comprised by the classification module.

[0063] Example 20

[0064] The method of example 19, wherein the classifier is a linear classifier.

[0065] Example 21

[0066] The method of any of examples 19-20, wherein: (a) the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and (b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

[0067] Example 22

[0068] The method of any of examples 19-21 , wherein the one or more pooling operators comprises: (a) proportion of positive values; (b) mean of positive values; (c) mean of indices of positive values; and (d) longest stretch of positive values.

[0069] Example 23

[0070] The method of any of examples 18-22, wherein the set of error status outputs comprises: (a) no fluid; and (b) obstructed condition.

[0071] Example 24

[0072] The method of any of examples 18-23, wherein the discharge passageway is at least partially defined by a tube attached to the container.

[0073] Example 25

[0074] The method of any of examples 18-24, wherein the container is open such that the fluid collected in the container is exposed to atmospheric pressure.

[0075] Example 26

[0076] The method of any of examples 18-25, wherein the object includes patient samplecontacting vessel.

[0077] Example 27

[0078] The method of example 26, wherein the patient sample-contacting vessel includes at least one of a pipettor, a cuvette, a sample cup, a tube, or a reaction vessel.

[0079] Example 28

[0080] The method of any of examples 18-25, wherein the object includes at least one of a gripper, a collet, or a camera lens.

[0081] Example 29

[0082] An analyzer comprising: (a) an object; (b) a container; (c) a vacuum pump; (d) a discharge passageway, wherein the discharge passageway is operatively connected to the vacuum pump and the container; (e) one or more processors; and (f) a non-transitory computer readable medium storing instructions for, when executed by the one or more processors, performing a fluidics system reliability improvement method with the object as subject object, the container as subject container, and the discharge passageway as subject discharge passageway, the fluidics system reliability improvement method comprising: (i) applying fluid to at least one of an inside surface or an outside surface of the subject object; (ii) applying a vacuum to the subject discharge passageway in order to remove the fluid from the subject container; (iii) obtaining a plurality of pressure measurements, wherein each measurement form the plurality of pressure measurements is a measurement of pressure inside the subject discharge passageway at a location proximate the vacuum pump; (iv) providing the plurality of pressure measurements as input to a classification module; and (v) the classification module determining an analyzer fluidics system status output based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the analyzer fluidics system status output is a normal status output, or one of a set of error status outputs.

[0083] Example 30

[0084] The analyzer of example 29, wherein the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises: (a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels; (b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and (c) providing the plurality of features to a classifier comprised by the classification module.

[0085] Example 31

[0086] The analyzer of example 30, wherein the classifier is a linear classifier.

[0087] Example 32

[0088] The analyzer of any of examples 30-31, wherein: (a) the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and (b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

[0089] Example 33

[0090] The analyzer of any of examples 30-32, wherein the one or more pooling operators comprises: (a) proportion of positive values; (b) mean of positive values; (c) mean of indices of positive values; and (d) longest stretch of positive values.

[0091] Example 34

[0092] The analyzer of any of examples 29-33, wherein the set of error status outputs comprises: (a) no fluid; and (b) obstructed condition.

[0093] Example 35

[0094] The analyzer of any of examples 29-34, wherein the discharge passageway is at least partially defined by a tube attached to the container.

[0095] Example 36

[0096] The analyzer of any of examples 29-35, wherein: (a) the analyzer comprises a plurality of objects, wherein the object is comprised by the plurality of objects; (b) the analyzer comprises a plurality of containers, wherein the container is comprised by the plurality of containers; (c) the analyzer comprises a plurality of discharge passageways, wherein the discharge passageway is comprised by the plurality of discharge passageways; (d) each object from the plurality of objects has a corresponding container from theplurality of containers and a corresponding discharge passageway from the plurality of discharge passageways; and (c) the non-transitory computer readable medium stores instructions for, for each object from the plurality of objects, performing the fluidics system reliability improvement method with that object as the subject object, the container corresponding to that object as the subject container, and the discharge passageway corresponding to that object as the subject discharge passageway.

[0097] Example 37

[0098] The analyzer of any of examples 29-36, wherein the container is open such that the fluid within the container is exposed to atmospheric pressure.

[0099] Example 38[000100] The analyzer of any of examples 29-37, wherein the object includes patient samplecontacting vessel.[000101] Example 39[000102] The analyzer of example 38, wherein the patient sample-contacting vessel includes at least one of a pipettor, a cuvette, a sample cup, a tube, or a reaction vessel.[000103] Example 40[000104] The analyzer of any of examples 29-37, wherein the object includes at least one of a gripper, a collet, or a camera lens.[000105] Having shown and described various embodiments of the present invention, further adaptations of the methods and systems described herein may be accomplished by appropriate modifications by one of ordinary skill in the ail without departing from the scope of the present invention. Several of such potential modifications have been mentioned, and others will be apparent to those skilled in the art. For instance, the examples, embodiments, geometries, materials, dimensions, ratios, steps, and the like discussed above are illustrative and are not required. Accordingly, the scope of the presentinvention should be considered in terms of the following claims and is understood not to be limited to the details of structure and operation shown and described in the specification and drawings.

Claims

I / We claim:

1. A method for detecting errors in an analyzer fluidics system, the method comprising:(a) moving a tip of a pipettor into a container and, while the tip of the pipettor is in the container, applying a fluid, wherein the fluid is a cleaning fluid, to at least one of an inside surface or an outside surface of the pipettor;(b) collecting the fluid in the container after it is applied to the at least one of the inside surface or the outside surface of the pipettor;(c) applying a vacuum to a tube in order to remove the fluid from the container, wherein the tube is operatively connected to the container and to a vacuum pump;(d) while the vacuum is being applied to the tube, obtaining a plurality of pressure measurements, wherein each measurement from the plurality of pressure measurements is a measurement of pressure inside the tube at a location proximate the vacuum pump;(e) providing the plurality of pressure measurements as input to a classification module; and(f) the classification module determining a status output for the analyzer fluidics system based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the status output for the analytics system is a normal status output, or one of a set of error status outputs.

2. The method of claim 1, wherein the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises:(a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels;(b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and(c) providing the plurality of features to a classifier comprised by the classification module.

3. The method of claim 2, wherein the classifier is a linear classifier.

4. The method of claim 2 or claim 3, wherein:(a) the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and(b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

5. The method of any one of claims 2 to 4, wherein the one or more pooling operators comprises:(a) proportion of positive values;(b) mean of positive values;(c) mean of indices of positive values; and(d) longest stretch of positive values.

6. The method of any preceding claim, wherein the set of error status outputs comprises:(a) no fluid; and(b) obstructed condition.

7. The method of any preceding claim, wherein the tube is attached to the container at a bottom of the container.

8. The method of any preceding claim, wherein the container is open such that the fluid collected in the container is exposed to atmospheric pressure.

9. An analyzer comprising:(a) a pipettor;(b) a container;(c) a vacuum pump;(d) a tube, wherein the tube is operatively connected to the vacuum pump and the container;(e) one or more processors; and(f) a non-transitory computer readable medium storing instructions for, when executed by the one or more processors, performing a fluidics system reliability improvement method with the pipettor as subject pipettor, the container as subject container, and the tube as subject tube, the fluidics system reliability improvement method comprising:(i) moving a tip of the subject pipettor into the subject container;(ii) applying fluid to at least one of an inside surface or an outside surface of the subject pipettor while the tip of the subject pipettor is in the subject container;(iii) applying a vacuum to the subject tube in order to remove the fluid from the subject container;(iv) obtaining a plurality of pressure measurements, wherein each measurement form the plurality of pressure measurements is a measurement of pressure inside the subject tube at a location proximate the vacuum pump;(v) providing the plurality of pressure measurements as input to a classification module; and(vi) the classification module determining an analyzer fluidics system status output based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the analyzer fluidics system status output is a normal status output, or one of a set of error status outputs.

10. The analyzer of claim 9, wherein the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises:(a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels;(b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and(c) providing the plurality of features to a classifier comprised by the classification module.

11. The analyzer of claim 10, wherein the classifier is a linear' classifier.

12. The analyzer of claim 10 or claim 11, wherein:(a) the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and(b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

13. The analyzer of any one of claims 10 to 12, wherein the one or more pooling operators comprises:(a) proportion of positive values;(b) mean of positive values;(c) mean of indices of positive values; and(d) longest stretch of positive values.

14. The analyzer of any one of claims 9 to 13, wherein the set of error status outputs comprises:(a) no fluid; and(b) obstructed condition.

15. The analyzer of any one of claims 9 to 14, wherein the tube is attached to the container at a bottom of the container.

16. The analyzer of any one of claims 9 to 15, wherein:(a) the analyzer comprises a plurality of pipettors, wherein the pipettor is comprised by the plurality of pipettors;(b) the analyzer comprises a plurality of containers, wherein the container is comprised by the plurality of containers;(c) the analyzer comprises a plurality of tubes, wherein the tube is comprised by the plurality of tubes;(d) each pipettor from the plurality of pipettors has a corresponding container from the plurality of containers and a corresponding tube from the plurality of tubes; and(e) the non-transitory computer readable medium stores instructions for, for each pipettor from the plurality of pipettors, performing the fluidics system reliability improvement method with that pipettor as the subject pipettor, the container corresponding to that pipettor as the subject container, and the tube corresponding to that pipettor as the subject tube.

17. The analyzer of any one of claims 9 to 16, wherein the container is open such that the fluid within the container is exposed to atmospheric pressure.

18. A method for detecting errors in an analyzer fluidics system, the method comprising:(a) applying a cleaning fluid to at least one of an inside surface or an outside surface of an object;(b) collecting the fluid in a container after it is applied to the at least one of the inside surface or the outside surface of the object;(c) applying, via a vacuum pump, a vacuum to a discharge passageway in fluid communication with the container in order to remove the fluid from the container;(d) while the vacuum is being applied to the discharge passageway, obtaining a plurality of pressure measurements, wherein each measurement from the pluralityof pressure measurements is a measurement of pressure inside the discharge passageway at a location proximate the vacuum pump;(e) providing the plurality of pressure measurements as input to a classification module; and(f) the classification module determining a status output for the analyzer fluidics system based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the status output for the analytics system is a normal status output, or one of a set of error status outputs.

19. The method of claim 18, wherein the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises:(a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels;(b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and(c) providing the plurality of features to a classifier comprised by the classification module.

20. The method of claim 19, wherein the classifier is a linear classifier.

21. The method of any one of claims 19 to 20, wherein:(a) the classification module determining the status output for the analyzer fluidics system based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and(b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

22. The method of any one of claims 19 to 21 , wherein the one or more pooling operators comprises:(a) proportion of positive values;(b) mean of positive values;(c) mean of indices of positive values; and(d) longest stretch of positive values.

23. The method of any one of claims 18 to 22, wherein the set of error status outputs comprises:(a) no fluid; and(b) obstructed condition.

24. The method of any one of claims 18 to 23, wherein the discharge passageway is at least partially defined by a tube attached to the container.

25. The method of any one of claims 18 to 24, wherein the container is open such that the fluid collected in the container is exposed to atmospheric pressure.

26. The method of any one of claims 18 to 25, wherein the object includes patient samplecontacting vessel.

27. The method of claim 26, wherein the patient sample-contacting vessel includes at least one of a pipettor, a cuvette, a sample cup, a tube, or a reaction vessel.

28. The method of any one of claims 18 to 25, wherein the object includes at least one of a gripper, a collet, or a camera lens.

29. An analyzer comprising:(a) an object;(b) a container;(c) a vacuum pump;(d) a discharge passageway, wherein the discharge passageway is operatively connected to the vacuum pump and the container;(e) one or more processors; and(f) a non-transitory computer readable medium storing instructions for, when executed by the one or more processors, performing a fluidics system reliability improvement method with the object as subject object, the container as subject container, and the discharge passageway as subject discharge passageway, the fluidics system reliability improvement method comprising:(i) applying fluid to at least one of an inside surface or an outside surface of the subject object;(ii) applying a vacuum to the subject discharge passageway in order to remove the fluid from the subject container;(iii) obtaining a plurality of pressure measurements, wherein each measurement form the plurality of pressure measurements is a measurement of pressure inside the subject discharge passageway at a location proximate the vacuum pump;(iv) providing the plurality of pressure measurements as input to a classification module; and(v) the classification module determining an analyzer fluidics system status output based on the plurality of pressure measurements, wherein the classification module is configured to determine, based on its input, if the analyzer fluidics system status output is a normal status output, or one of a set of error status outputs.

30. The analyzer of claim 29, wherein the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises:(a) obtaining a plurality of convolution outputs based on convolving the plurality of pressure measurements with a first plurality of convolution kernels;(b) obtaining a plurality of features based on applying one or more pooling operators to the plurality of convolution outputs; and(c) providing the plurality of features to a classifier comprised by the classification module.

31. The analyzer of claim 30, wherein the classifier is a linear classifier.

32. The analyzer of any one of claims 30 to 31, wherein:(a) the classification module determining the analyzer fluidics system status output based on the plurality of pressure measurements comprises generating a derived sequence of pressure measurement changes by taking first order differences of the measurements from the plurality of pressure measurements; and(b) obtaining the plurality of convolution outputs is further based on convolving the derived sequence of pressure measurement changes with a second plurality of convolution kernels.

33. The analyzer of any one of claims 30 to 32, wherein the one or more pooling operators comprises:(a) proportion of positive values;(b) mean of positive values;(c) mean of indices of positive values; and(d) longest stretch of positive values.

34. The analyzer of any one of claims 29 to 33, wherein the set of error status outputs comprises:(a) no fluid; and(b) obstructed condition.

35. The analyzer of any one of claims 29 to 34, wherein the discharge passageway is at least partially defined by a tube attached to the container.

36. The analyzer of any one of claims 29 to 35, wherein:(a) the analyzer comprises a plurality of objects, wherein the object is comprised by the plurality of objects;(b) the analyzer comprises a plurality of containers, wherein the container is comprised by the plurality of containers;(c) the analyzer comprises a plurality of discharge passageways, wherein the discharge passageway is comprised by the plurality of discharge passageways;(d) each object from the plurality of objects has a corresponding container from the plurality of containers and a corresponding discharge passageway from the plurality of discharge passageways; and(e) the non-transitory computer readable medium stores instructions for, for each object from the plurality of objects, performing the fluidics system reliability improvement method with that object as the subject object, the container corresponding to that object as the subject container, and the discharge passageway corresponding to that object as the subject discharge passageway.

37. The analyzer of any one of claims 29 to 36, wherein the container is open such that the fluid within the container is exposed to atmospheric pressure.

38. The analyzer of any one of claims 29 to 37, wherein the object includes patient samplecontacting vessel.

39. The analyzer of claim 38, wherein the patient sample-contacting vessel includes at least one of a pipettor, a cuvette, a sample cup, a tube, or a reaction vessel.

40. The analyzer of any one of claims 29 to 37, wherein the object includes at least one of a gripper, a collet, or a camera lens.

Images