Automated chromatogram analysis method for blood test evaluation

Abstract

To provide a computer-supported blood test evaluation method and program related to analysis of diagnostic inspection data of an abnormal hemoglobin disease.SOLUTION: A chromatogram analysis tool 240 receives blood test data for a sample and divides the data into regions and determines a best-fit match template for each region. The chromatogram analysis tool determines a best-fit match for each region by comparing the blood test data to a set of templates associated with archetypical shapes of the region. The template with the highest r-squared value for the blood test data is the best-fit template. The chromatogram analysis tool generates a report on the basis of the best-fit match templates for each region. The report can indicate medical conditions or recommendations for additional testing.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] 1. Technical Field The subject matter of this description relates generally to the analysis of diagnostic test data, and specifically to computer-assisted blood test evaluation. [Background technology]

[0002] 2. Background information Hemoglobinopathies are genetic disorders that cause the hemoglobin molecules in an individual's blood to have an abnormal structure. For example, sickle cell disease is caused by a hemoglobinopathy in which red blood cells can assume a rigid, sickle shape under certain circumstances. These abnormally shaped red blood cells can block capillaries and restrict blood flow, leading to various health problems. In contrast, thalassemia is a genetic condition that results in reduced hemoglobin production. Some hemoglobinopathies also affect hemoglobin production and are therefore also thalassemias.

[0003] Various medical conditions are characterized by the presence of specific hemoglobin variants in the blood and the ratio of different variants. Blood tests provide information about the ratio of different hemoglobin variants in a blood sample. However, interpreting this information can be difficult. Different conditions may have similar effects on the presence of a particular variant. Analysis is further complicated because other environmental and health factors may affect the ratio of variants present. For example, an unusually high amount of hemoglobin F may indicate a genetic disorder or indicate that an individual was pregnant or an infant at the time of sample collection. Furthermore, a relatively low amount of a variant (or a change in the amount of a variant present) may be clinically significant but may be masked by a variant present in much higher amounts.

[0004] Computer technology offers new opportunities to analyze blood test data and more reliably distinguish between different reaction patterns produced by samples containing variants, which may reduce reliance on human analysts, who are prone to error and may require more time and training to arrive at a diagnosis than can be achieved using technology. [Brief explanation of the drawings]

[0005] [Figure 1] 1 is a high-level block diagram illustrating a networked computing environment in which diagnostic data is generated and analyzed, according to one embodiment. [Figure 2] 2 is a high-level block diagram illustrating a laboratory terminal suitable for use in the networked computing environment of FIG. 1 according to one embodiment. [Figure 3] FIG. 1 is a high-level block diagram illustrating a chromatogram analysis tool at a laboratory terminal, according to one embodiment. [Figure 4] FIG. 1 is a high-level block diagram illustrating an example of a computer suitable for use as a laboratory terminal, according to one embodiment. [Figure 5] 1 illustrates an exemplary chromatogram according to one embodiment. [Figure 6] 1 is a table illustrating an example of dividing a chromatogram into regions according to one embodiment. [Figure 7A] 1 shows an exemplary visual representation of a region of chromatogram data overlaid with a best-fit match template. [Figure 7B] 1 shows examples of chromatogram data and reports that may be generated by the present chromatogram analysis tool according to one embodiment. [Figure 8] 1 shows an example report of multiple results generated by the present chromatogram analysis tool according to one embodiment. [Figure 9]1 is a flowchart illustrating a method for generating a report on blood chromatography data according to one embodiment. Summary of the Invention

[0006] Detailed Description The drawings (figures) and the following description illustrate particular embodiments by way of example only. Those skilled in the art will readily recognize from the following description that alternative embodiments of the described structures and methods may be utilized without departing from the principles of the present description. Reference will be made below to several embodiments, examples of which are illustrated in the accompanying drawings. It is noted that, where practical, like or similar reference numerals are used in the drawings to indicate like or similar functionality.

[0007] Overview and Benefits The chromatogram analysis tool is used as part of a laboratory blood testing system to identify genetic conditions based on the relative proportions of various hemoglobin types in a sample. The blood testing system generates chromatographic data from the sample. The chromatogram analysis tool identifies regions of the chromatographic data and, for each region, determines a match between the chromatographic data in that region and one of a set of potential templates. The regions may have a predetermined size. A template represents the archetypical shape of the hemoglobin data in the corresponding region and may be a constructed example chromatogram; an individual or a portion of a pool of real example chromatograms; or a combination of real and / or constructed example chromatograms.

[0008] The chromatogram analysis tool generates a report based on the best-fit match. The report may indicate one or more possible medical conditions. The report may also include additional comments and notes, such as suggestions for additional tests to be performed, common diagnostic pitfalls, additional information about the corresponding condition (e.g., demographic factors that correlate with the diagnosis), and possible reproductive risks.

[0009] Analyzing chromatogram regions using templates has several advantages. First, it may aid in the interpretation of results, allowing laboratories to deliver more standardized results without the need for additional training. It may even reduce the amount of training required for laboratory technicians to work efficiently. Second, it may allow results to be compared virtually in real time with a large database of reference cases available online, potentially resulting in more accurate preliminary identification of potential conditions. Third, by applying templates to regions, scaling variations are inherently built into the template corresponding to each region. Therefore, region matching can provide greater accuracy than approaches that match templates to the entire chromatogram. Fourth, this method does not rely on peaks not found in normal samples to be integrated and assigned to unique windows. Fifth, the report may generate suggestions for next steps in arriving at a diagnosis, which may reduce reliance on manual connection between test results and possible causes. In some cases, the next step may be triggered automatically or semi-automatically (e.g., if the data required for the next step is already available in the database), which reduces the time to complete the inspection process. [The present invention 1001] 1. A method for generating a report from blood test data, the method comprising: receiving blood test chromatography data for a patient's blood sample, the data including a plurality of peaks, each peak corresponding to one or more types of hemoglobin and having a value indicative of the amount of the corresponding type of hemoglobin present in the blood sample; identifying a plurality of regions of the chromatographic data, each region containing chromatographic data from a different retention time range; For each area, retrieving a plurality of region templates corresponding to the region; and identifying a best-fit matching region template by comparing each region template with the chromatographic data contained within the region; and Generating a report indicating one or more medical conditions based on the best-fit match region template for each region. [The present invention 1002] The method of claim 1001, wherein the report includes at least one comment providing advice regarding the interpretation of the report. [The present invention 1003] The method of the present invention 1002, wherein the advice regarding interpretation of the report includes at least one of common pitfalls associated with the one or more medical conditions, recommendations for additional testing, or additional information about the medical condition. [The present invention 1004] Providing reports for display on the device The method of the present invention 1001 further comprising: [The present invention 1005] 1001. The method of claim 1001, wherein each region of said plurality of regions has a corresponding predetermined range, each range being defined by a start feature and an end feature within the chromatogram. [The present invention 1006] 1001. The method of claim 1001, wherein at least two of said predetermined ranges are of different lengths. [The present invention 1007] determining an indicator of the quality of the chromatographic data; and generating a notification if the quality indicator falls below a predetermined threshold. The method of the present invention 1001 further comprising: [The present invention 1008] identifying a best-fit matching region template for each region, For each region template, determining a maximum correlation coefficient R value between the chromatographic data of the region and the region template; and determining the best-fit match region template based on the maximum correlation coefficient R value; The method of the present invention 1001, comprising: [The present invention 1009] Determining the maximum correlation coefficient R value for a given region template sliding the given region template across the region of the chromatography data; calculating R values for different positions of the given region template within the region of the chromatographic data; and selecting the largest of the R values as the maximum R value for the given region template. The method of the present invention 1008, comprising: [The present invention 1010] 1001. The method of claim 1001, wherein each template represents an archetypical shape of a chromatogram in said region, including one or more peaks. [The present invention 1011] below: receiving blood test chromatography data for a patient blood sample, the data including a plurality of peaks, each peak corresponding to one or more types of hemoglobin and indicating an amount of the corresponding one or more types of hemoglobin present in the blood sample; identifying a plurality of regions of the chromatographic data, each region containing chromatographic data from a different retention time range; For each area, retrieving a plurality of region templates corresponding to the region; and identifying a best-fit matching region template by comparing each region template with the chromatographic data contained within the region; and generating a report indicating one or more medical conditions based on the best-fit match region template for each region; A non-transitory computer-readable medium storing computer program instructions executable by a processor to perform operations including: [The present invention 1012] The non-transitory computer readable medium of the present invention 1011, wherein the report includes at least one comment providing advice regarding the interpretation of the report. [The present invention 1013] A non-transitory computer-readable medium of the present invention 1012, wherein the advice regarding interpretation of the report includes at least one of common pitfalls associated with the one or more medical conditions, recommendations for additional testing, or additional information about the medical condition. [The present invention 1014] Providing reports for display on the device The non-transitory computer readable medium of the present invention 1011 having stored thereon instructions further comprising: [The present invention 1015] The non-transitory computer readable medium of the present invention 1011, wherein each region of the plurality of regions has a corresponding predetermined range, each range being defined by a start feature and an end feature in the chromatogram. [The present invention 1016] The non-transitory computer-readable medium of the present invention 1011, wherein at least two of the predetermined ranges have different lengths. [The present invention 1017] determining indicators of the quality of the chromatographic data to determine; and generating a notification if the quality indicator falls below a predetermined threshold; The non-transitory computer-readable medium of the present invention 1011 further comprises: [The present invention 1018] identifying a best-fit matching region template for each region; For each region template, determining an R value between the chromatographic data of the region and the region template; and Determine the best-fit match area based on the highest R value The non-transitory computer-readable medium of the present invention 1011 further comprises: [The present invention 1019] A non-transitory computer readable medium of the present invention 1011, wherein each template represents the hemoglobin composition of a prototypical shape of a chromatogram within said region, including one or more peaks. [The present invention 1020] a port for injecting a blood sample extracted from the patient; one or more processors; When executed, receiving blood test chromatography data for a patient's blood sample, the data including a plurality of peaks, each peak corresponding to one or more types of hemoglobin and having a value indicative of the amount of the corresponding type of hemoglobin present in the blood sample; identifying a plurality of regions of the chromatographic data, each region containing chromatographic data from a different retention time range; For each area, retrieving a plurality of region templates corresponding to the region; and identifying a best-fit matching region template by comparing each region template with the chromatographic data contained within the region; and generating a report based on the best-fit match region template for each region; a computer-readable medium having stored thereon computer program code that causes the one or more processors to perform operations including: 1. A chromatography device for generating a report from blood test data, comprising: DETAILED DESCRIPTION OF THE INVENTION

[0010] Exemplary System FIG. 1 illustrates one embodiment of a networked computing environment 100 in which diagnostic data is generated and analyzed. In the embodiment shown in FIG. 1, the networked computing environment includes a laboratory information system (LIS) 110, laboratory equipment 120, and laboratory terminals 130, all connected via a network 170. While two items of laboratory equipment 120 and two laboratory terminals 130 are illustrated, a given deployment may include any amount of equipment and any number of terminals (including only a single terminal). In other embodiments, the networked computing environment 100 contains different or additional elements. Additionally, functions may be distributed among the elements in a manner different from that described herein. For example, each item of laboratory equipment 120 may include a computer system that provides the functionality of the laboratory terminal 130.

[0011] The LIS 110 is a computerized system that supports laboratory operations. In various embodiments, the LIS 110 provides tools to help technicians and other users function efficiently within the laboratory. For example, the LIS 110 may provide data tracking, automated backup, data exchange, workflow management, sample management, data analysis, data mining, instrument management, report generation, data auditing, and the like. In the embodiment shown in FIG. 1 , the LIS 110 stores medical data 112. The medical data 112 is stored on one or more computer-readable media, such as a hard drive. The medical data 112 may include patient records, test results, medical literature, and the like. Those skilled in the art will recognize other functionality that the LIS 110 may provide and other types of data that may be stored as part of the medical data 112.

[0012] Laboratory equipment 120 is one or more devices that perform medical tests. In one embodiment, laboratory equipment 120 includes a chromatography system that produces a chromatogram showing the relative proportions of different variants of hemoglobin present in a sample. An example of such a system is the D-100™ produced by Bio-Rad™. Laboratory equipment 120 may also include devices that perform other tests, such as DNA tests and urinalysis. Chromatogram analysis tools may identify possible medical conditions, thereby triggering a series of tests to aid in the differential diagnosis of the sample, such as sickling tests, stability tests (isopropanol tests), electrophoresis tests, MS / MS, and molecular tests.

[0013] The laboratory terminal 130 is a computing device through which a user interacts with the LIS 110 and the laboratory equipment 120. In various embodiments, a technician initiates tests on samples using the terminal 130, which includes a chromatogram analysis tool. The terminal 130 presents a report generated by the chromatogram analysis tool, including result analysis and recommendations. In one embodiment, the technician approves the report, which is sent to the LIS 110 for storage. In another embodiment, a laboratory supervisor must also approve the report (e.g., using a second terminal 130). The terminal 130 may also send instructions (e.g., to the LIS 110) to initiate additional tests or to provide results of previously performed tests based on recommendations generated by the chromatogram analysis tool. Aspects of the terminal 130, and in particular the operation of the chromatogram analysis tool, are described in more detail below with reference to FIGS. 2 and 3.

[0014] Network 170 provides a communication channel through which other elements of networked computing environment 100 communicate. Network 170 may include any combination of local area networks or wide area networks, using both wired and wireless communication systems. In one embodiment, network 170 uses standard communication technologies or protocols. For example, network 170 may include communication links using technologies such as Ethernet, 802.11, Worldwide Interoperability for Microwave Access (WiMAX), 3G, 4G, Code Division Multiple Access (CDMA), Digital Subscriber Line (DSL), etc. Examples of networking protocols used for communication over network 170 include Multiprotocol Label Switching (MPLS), Transmission Control Protocol / Internet Protocol (TCP / IP), Hypertext Transport Protocol (HTTP), Simple Mail Transfer Protocol (SMTP), and File Transfer Protocol (FTP). Data exchanged over network 170 may be represented using any suitable format, such as Hypertext Markup Language (HTML) or Extensible Markup Language (XML). In one embodiment, some or all of the components are connected using RS-232 serial connections. In some embodiments, all or part of the communication links of network 170 may be encrypted using any suitable technique.

[0015] Figure 2 illustrates one embodiment of a lab terminal 130 suitable for use in the networked computing environment 100 of Figure 1. In the embodiment illustrated in Figure 2, the lab terminal 130 includes a results provider 210, a display subsystem 220, a user input subsystem 230, a chromatogram analysis tool 240, and local storage 260. In other embodiments, the lab terminal 130 contains different or additional elements. Additionally, functions may be distributed among the elements in a manner different from that described herein.

[0016] The results provider module 210 interfaces with the laboratory equipment 120 to obtain medical data. In one embodiment, the medical data is blood chromatography data, which the results provider module 210 uses to generate a chromatogram. Alternatively, the chromatogram may be generated by the laboratory equipment 120 (or elsewhere in the networked computing environment 100) and provided as input to the results provider module 210. FIG. 5 shows an example chromatogram 500 according to one embodiment. The chromatogram 500 includes a visual representation 510 of the data and a data table 520. The visual representation 510 includes a plot of detector response over time, including multiple peaks 512 (only two of which are labeled for clarity). The data table 520 identifies retention times (i.e., the times at which the strongest detector response was observed for the peaks 512) in various windows predicted to correspond to different variants of hemoglobin (e.g., A1a, A1b, F, etc.). The data table 520 also includes the area of each peak 512 (which corresponds to the total amount of a given variant present in the sample) and the results reported for each peak.

[0017] Returning to Figure 2, the display subsystem 220 presents information and controls to a user (e.g., a laboratory scientist). In one embodiment, the display subsystem 220 provides controls for a technician to initiate a test with the lab equipment 120. The display subsystem 220 then provides controls that allow an operator to view and analyze the results of the test (e.g., using the chromatogram analysis tool 240). The display subsystem 220 may also provide other functionality, such as viewing patient records, configuring the lab equipment 120, and viewing status / maintenance data.

[0018] The user input subsystem 230 receives input from a user (e.g., a laboratory scientist or supervisor) and provides it to other elements of the terminal 130. In one embodiment, the user input subsystem 230 includes a touchscreen. Controls are presented on the touchscreen to allow the user to control the laboratory equipment 120 or interact with the chromatogram analysis tool 240. Aspects of the user interface provided by the user input subsystem 230 are described in more detail below with reference to Figures 7 and 8.

[0019] The chromatogram analysis tool 240 analyzes the data provided by the result provider module 210 to generate a report. In various embodiments, the chromatogram analysis tool 240 subdivides the chromatogram into regions and matches each region to a set of templates corresponding to possible region shapes to find a best-fit match. The chromatogram analysis tool 240 then generates a report based on the best-fit match for each region and includes comments regarding the interpretation of the results. The report may additionally include the likelihood that each best-fit match is correct or recommendations for further testing to enable a definitive diagnosis. For example, if the results suggest that the subject may be a carrier of a genetic blood disorder, the chromatogram analysis tool 240 could recommend confirmatory DNA testing if the subject is considering having children. In one embodiment, the chromatogram analysis tool 240 may automatically trigger further analysis if the necessary data or equipment is available and update the report accordingly. Details of various embodiments of the chromatogram analysis tool 240 are described in more detail below with reference to FIG. 3.

[0020] Figure 3 illustrates one embodiment of the chromatogram analysis tool 240 of the laboratory terminal 120 shown in Figure 2. In the embodiment shown in Figure 3, the chromatogram analysis tool 240 includes a pre-processing module 310, a region identification module 320, a template store 325, a template matching module 330, and a result evaluation module 340. In other embodiments, the chromatogram analysis tool 240 contains different or additional elements. Additionally, functions may be distributed among the elements in a manner different from that described herein.

[0021] The preprocessing module 310 performs various baseline calculations and quality checks before further analysis of the data. In some embodiments, the preprocessing module 310 performs baseline subtraction on the chromatogram before subsequent analysis. In some embodiments, the preprocessing module 310 may perform an initial analysis of the chromatogram. For example, the preprocessing module 310 may calculate height and area and generate calibrated and uncalibrated results. The preprocessing module 310 may also calculate special sums from these calibrated and uncalibrated results that combine data from one or more peaks to aid in efficient analysis.

[0022] In some embodiments, the preprocessing module 310 analyzes the quality of the data. In one such embodiment, the quality analysis checks for features in the data that may indicate a high likelihood of inaccurate results. For example, the quality analysis module 310 may compare the total area for a chromatogram to a minimum area threshold and flag the test data as low quality if the total area is below the threshold. In this example, the preprocessing module 310 may use a special sum calculated as described above. If the test data is flagged as low quality data, the preprocessing module 310 may terminate the analysis and indicate that a new test should be performed. This can prevent time and resources from being wasted on further analysis of unreliable data. In such cases, the preprocessing module 310 may automatically trigger a retest of the sample. In another example, the preprocessing module 310 may look at the width of a known peak (e.g., the A1c or A2 peak), the sigma and tau values of an exponentially modified Gaussian fit, or an index derived from the sigma and tau values of the exponentially modified Gaussian fit, and add a warning comment if a threshold is exceeded. As another example, the quality analysis module 310 may use the tau / sigma ratio of the exponentially modified Gaussian or another index to check for uneven baselines and highly asymmetric peaks (e.g., peak tailing).

[0023] The region identification module 320 divides the chromatogram into regions. The region identification module 320 determines the start and end times of each region using chromatogram features and / or absolute or normalized time. In one embodiment, the region identification module 320 determines the boundaries of the region by searching for predicted features within a predicted range. For example, the region determination module 320 may determine the start or end boundaries of a region by searching for one or more of the following within the predicted range: the first peak start or valley, the last peak start or valley, the lowest intensity peak start or valley, the first valley or peak end, the last valley or peak end, the lowest intensity valley or peak end, the first peak start or valley or peak end, the last peak start or valley or peak end, the lowest intensity peak start or valley or peak end, or the last peak end. For example, the region identification module 320 determines the retention time boundary between region 1 (e.g., region 1 610) and region 2 (e.g., region 2 620) as the local minimum within the retention time range corresponding to where peaks F and LA1c elute; the determination is made such that, if peaks F and LA1c are both present, peak F is entirely within region 1 and peak LA1c is entirely within region 2. If a predicted peak feature is found within the predicted range, it is used as the corresponding region boundary. Otherwise, a default value (e.g., absolute time or normalized time) may be used for the boundary. This may accommodate unusual cases where the predicted peak does not appear but an unusual peak does. Because the region identification module 320 determines the regions based on selected features, the regions may vary in size (i.e., retention time length).

[0024] FIG. 6 is a table 600 illustrating an example of dividing a chromatogram into regions according to one embodiment. Table 600 divides the chromatogram into five regions and lists start and end features for each region. In the example shown in FIG. 6, Region 1 610 begins at the beginning of the chromatogram (i.e., retention time 0.0) and ends at the retention time corresponding to the end of peak F, if present. That is, Region 1 610 constitutes the retention time range in which peaks A1a, A1b, and F, if present, are eluted. Region 2 620 begins at the retention time corresponding to the start of peak LA1c, if present, and ends at the retention time corresponding to the end of peak P3, if present, so that Region 2 620 constitutes the retention time range in which peaks LA1c, HbA1c, and P3, if present, are eluted. Region 3 630, Region 4 640, and Region 5 650 are similarly defined by corresponding start and stop features or times. Table 600 describes the boundaries of regions 610, 620, 630, 640, 650 in terms of windowed components commonly found in chromatograms, however, in some embodiments, the boundaries are independent of the identity of these windowed components.

[0025] Returning to FIG. 3 , template store 325 stores one or more sets of templates, or the parameters necessary to generate templates as needed. Each template corresponds to a prototypical shape of a region of a chromatogram, where each prototypical shape represents a particular prototypical shape for that chromatogram region. Prototypical shapes may be constructed, real, or a combination of real and constructed, where each prototypical shape mimics one or more of the peaks and troughs found in that particular region of the chromatogram. Real prototypical shapes are derived from real data sets of chromatographic data, either individual or combined chromatograms. Constructed prototypical shapes are artificially created to represent the prototypical shapes, such as by experts who construct predicted curves. Each region is associated with a set of templates, where each template has a different prototypical shape. For example, templates for region 1 may include the prototypical shapes of normal A1a, A1b, and F peaks, with each template differing in the height, width, or symmetry of one or more of those peaks, and some templates may lack some peaks entirely. In other examples, expected prototypical shapes for abnormal reactions may be included. Each set of templates in template store 325 associated with a region may be indexed and searchable by various factors, such as the height of a particular peak, the absence of a particular peak, or a subset of templates known to represent chromatogram data associated with a certain medical condition.

[0026] The template matching module 330 compares a set of templates to individual regions of the chromatogram to determine the template that is the best match for each region. The template matching module compares regions of the chromatogram to templates in a template set associated with that region stored in the template store 325. In one embodiment, the template matching module 330 slides a first template from the template store 325 across the data for that region. The template matching module 330 determines the position of the first template on the region that has the best fit between the first template and the data for the region. The template matching module 330 may determine the position of the first template that provides the best fit on the data for the region by determining the correlation coefficient R value between the first template and the data at different alignments of the first template and the data. The alignment may occur in one or two dimensions. For example, the alignment may include an offset in one dimension.

[0027] In some embodiments, the alignment is parameterized by a jitter range; the jitter range may be calibrated for different features based on predicted retention times. The alignment of the first template with the data that results in the highest correlation coefficient R value is the best-fit position for the first template, and that R value is associated with the first template for that data. The template matching module repeats the method of determining the best-fit correlation coefficient R value for other templates in the template store 325. The template determined to have the highest overall R value from the set of templates is determined by the template matching module 330 to be the best-fit match for that region. The template matching module 330 finds a best-fit match for each region of the chromatogram. In other embodiments, other measures of closeness of fit may be used.

[0028] In some embodiments, the template matching module 330 matches every template in a set stored in the template store 325 associated with a particular region. In other embodiments, the template matching module 330 may use a determined measure of closeness of fit to expedite the determination of the best-fit match. For example, if the template matching module 330 determines a correlation coefficient R value for a first template that exceeds a threshold, this triggers additional comparisons to a subset of templates similar to the first template. Similarly, if the template matching module 330 determines a correlation coefficient R value for a second template that is below a threshold, this triggers the template matching module 330 to skip comparisons to the subset of templates similar to the second template.

[0029] The template matching module 330 may also add one or more comments. For example, the comments may identify potential diagnostic pitfalls associated with the preliminary pattern; may suggest further testing to help arrive at a diagnosis; or may identify other factors that should be considered (e.g., the subject's ethnicity).

[0030] The result evaluation module 340 receives output from the template matching module 330 for each region and generates a report. The result evaluation module 340 incorporates the best-fit match for each region into an overall analysis. Calibrated area percentages or other preprocessing results may be combined with the region match information to determine a possible medical condition. In some embodiments, the result evaluation module 340 may combine each best-match template end-to-end to generate an overall best-fit template. In another embodiment, normalized regions are individually overlaid with the best-match template and displayed side-by-side, as in FIG. 7 . The report generated by the result evaluation module 340 identifies one or more possible medical conditions or otherwise identifies a determination of normality; or returns a result of "No assignment - possible variant." For example, a region may have a best-fit match template associated with it that indicates a likely medical condition and a recommendation for further testing. In some embodiments, a single template may indicate multiple possible medical conditions. In another embodiment, the combination of the best-fit match templates determined for two or more regions and the results of pre-processing may indicate a medical condition or may indicate a higher likelihood of that condition than either template match alone.

[0031] The report generated by the result evaluation module 340 may also include comments or advice regarding the interpretation of the report based on data associated with individual templates or combinations of templates. For example, the comments may include an indication of the individual's likelihood of having one or more medical conditions; recommendations for further testing; common pitfalls associated with the one or more medical conditions; or additional information about each medical condition. For example, when testing for beta-thalassemia, the generated report may include information about the hemoglobin pattern along with HbA1c and / or A2 / E results, along with associated comments and notes. The added comments may alert laboratory scientists and assist clinicians in interpreting the results. In another example, the comments added by the result evaluation module 340 may include comments regarding characteristics of the test results, such as the presence of a particular hemoglobin variant, or may flag the test results as being suppressed or repeated (e.g., if the analysis suggests the results are unreliable).

[0032] 7A shows an example of a visual representation of a region of chromatogram data overlaid with a best-fit match template. Figure 7A includes a visual representation of region 1 710, a visual representation of region 2 720, a visual representation of region 3 730, a visual representation of region 4 740, and a visual representation of region 5 750. Region identification module 320 divides chromatogram data 760 (see FIG. 7B) into regions represented by visual representations 710, 720, 730, 740, and 750. Each visual representation 710, 720, 730, 740, and 750 of each region includes a plot 712, 722, 732, 742, and 752 of the chromatogram data for that region, respectively, and a best-fit template 714, 724, 734, 744, and 754 determined by template matching module 330. Each visual representation 710, 720, 730, 740, 750 also includes a summary of results 716, 726, 736, 746, 756 that provides offset and R values for the match between the chromatogram data plot 712, 722, 732, 742, 752 and the best-fit template 714, 724, 734, 744, 754 for the respective region as determined by the template matching module 330.

[0033] For example, visual representation 710 for region 1 includes plot 712 of chromatogram data for region 1 overlaid with best-fit template 714 for chromatogram data 712. While chromatogram data plot 712 is not identical to best-fit template 714, it is similar in shape. For example, the peaks have similar shapes but slightly different heights. Template matching module 330 determined that best-fit template 714 is the prototypical shape for chromatogram data plot 712 with the highest correlation coefficient R value of all templates for region 1 in template store 325. The correlation coefficient R value for best-fit template 714 and chromatogram data plot 712 is 0.9324, as shown by result 716. Other templates for region 1 in template store 325 have correlation coefficient R values lower than 0.9324 with chromatogram data plot 712. Best-fit template 714 may be associated with one or more medical conditions.

[0034] FIG. 7B illustrates example chromatogram data 760 and report 770 that may be generated by chromatogram analysis tool 240 according to one embodiment. Chromatogram data 760 may be divided into regions of chromatogram data plots 712, 722, 732, 742, and 752. Chromatogram data 760 is displayed with an overlay indicating each region number associated with chromatogram data plots 712, 722, 732, 742, and 752. Chromatogram analysis tool 240 generates report 770 from the example chromatogram analysis data 760. Best fit templates 714, 724, 734, 744, and 754 for chromatogram data plots 712, 722, 732, 742, and 752 in FIG. 7A visualize the best fit match templates determined by the chromatogram analysis tool for each region of chromatogram data 760. A report 770 is generated based on the best-fit matches 714, 724, 734, 744, 754 for each region.

[0035] Report 770 provides information about chromatogram data 760. In the embodiment shown in Figure 7B, report 770 includes a variety of information, including patient information 771, best-fit match template name, list of regions 772 each with associated best-fit match template name 773 and associated correlation coefficient R value 774, comments 775, and optional notes 776. In other embodiments, report 770 may include additional or alternative information about chromatogram data 760.

[0036] Patient information 771 includes relevant information about the patient, such as patient ID and rack and position indicating the location of the sample that was tested to produce chromatogram data 760. In other embodiments, patient information 771 may additionally or alternatively include name, blood type, treating physician, demographic data, test date and time, and other health information associated with the patient. Patient information may be stored in local storage 260 rather than provided by chromatogram analysis tool 240.

[0037] The list of regions 772 lists the regions of the chromatogram data 760. Each region in the list of regions 772 is associated with a listed best-fit match template name 773 and an associated correlation coefficient R value 774 for the best-fit match template. The best-fit match template names 773 listed in the report 770 are unique names associated with the best-fit matches 714, 724, 734, 744, and 754 for each region shown in FIG. 7A. For example, the best-fit match 714 is called "BARTS and H1." The correlation coefficient R value 774 listed in the report 770 is the same as the R value listed in the results summary 716, 726, 736, 746, and 756 in FIG. 7A. For example, the correlation coefficient R value for region 1 is 0.934, as shown in both FIGS. 7A and 7B.

[0038] Comments 775 indicate one or more possible medical conditions or other medical information. Comment 76 in FIG. 7B indicates that the patient likely has "BARTS with Constant Spring." In other embodiments, comments 775 may indicate other possible medical conditions or indicators of normality, such as the example described below with respect to FIG. 8. In one embodiment, comments 775 generated by chromatogram analysis tool 240 are presented to a lab supervisor (e.g., at terminal 130) and are included on report 770 only if the lab supervisor approves them.

[0039] Note 776 shows the %A2 result along with the expected %A2 range for that medical disorder. Note 776 may be provided by preprocessing module 310 of chromatogram analysis tool 240. In alternative embodiments, note 776 may include additional or alternative information.

[0040] 8 shows an example of a report 800 of multiple results generated by the chromatogram analysis tool 240 according to one embodiment. The report 800 includes multiple results obtained from multiple analyzed samples. The summary 800 may be displayed on the terminal 130. In some embodiments, the summary report information may be exported in a format usable by a spreadsheet application or printed. The report 800 includes, for each sample, the sample name, the text name and correlation coefficient for each region, comments, and optional notes.

[0041] The text name for each region in each sample indicates the name for the best-fit match template associated with that particular region for that particular sample, as determined by chromatogram analysis tool 240. The column title for each region's text name is abbreviated in report 800 as "Region 1 Text" for Region 1, and similarly for the other regions. For example, sample 5 has a Region 3 text name of "A0 Predominate."

[0042] The correlation coefficient for each region in each sample is a value (e.g., an R value) that indicates the closeness between the chromatogram data in the region and the best-fit match template. The column title for correlation coefficients is abbreviated in report 800 as "Region 1 CC," and similarly for other regions. Each correlation coefficient is associated with a best-fit match template, which is associated with a text name immediately to the left of the respective correlation coefficient. For example, sample 5 has a region 3 correlation coefficient of 0.9246 for the best-fit match template called A0 dominant.

[0043] Comments for each sample provide an indication of one or more possible medical conditions. The comments are provided by the chromatogram analysis tool 240. The column title for the comments is "Comments" in the report 800. As listed in FIG. 8, possible medical conditions indicated by the comments include, but are not limited to, HbH, BARTS, Constant Spring, High F, Beta Thalassemia Major, Beta O / E, SC, O-Arab, CC, SS, EE, and Beta Thalassemia Trait.

[0044] Notes for each sample provide additional information about that sample. The comments may be provided by the chromatogram analysis tool 240 or another module. The column title for notes is "Notes" in report 800. For example, in FIG. 8, the first row contains the note that the A2 peak / E peak percentage is 0.70. The text names, correlation coefficients, comments, and notes associated with the samples in report 800 make it easy to read multiple samples at once. Report 800 may be provided in addition to or as an alternative to report 770 of FIG. 7B.

[0045] An embodiment of the present invention was run on a set of 97 chromatograms with variant reactions, and the results were compared with the assignments obtained by manual review. Twenty-two chromatograms were variant samples not contained in the template library. Of the 22 chromatograms, 20 returned a result of "No assignment—possible variant," and two returned a result of BARTS. Either result would trigger escalation of testing and further review of the sample. Two additional chromatograms were from post-transfusion samples, which also returned a result of "No assignment—possible variant." Of the remaining 73 chromatograms, 67 were assigned as aligned with the manual chromatogram assignments. Four of the six discrepancies were thought to be attributable to differences in interpretation of the %A2 results; therefore, a different %A2 cutoff for normal was used between this method and the manual review. These four chromatograms were identified as normal but were manually assigned beta-thalassemia trait. The remaining two mismatches returned results of A2+A2' but were still manually assigned to beta-thalassemia, triggering further investigation.

[0046] Computing System Architecture 4 illustrates an exemplary computer 400 suitable for use as a lab terminal 120 or LIS 110 according to one embodiment. The exemplary computer 400 includes at least one processor 402 coupled to a chipset 404. The chipset 404 includes a memory controller hub 420 and an input / output (I / O) controller hub 422. A memory 406 and a graphics adapter 412 are coupled to the memory controller hub 420, and a display 418 is coupled to the graphics adapter 412. A storage device 408, a keyboard 410, a pointing device 414, and a network adapter 416 are coupled to the I / O controller hub 422. Other embodiments of the computer 400 have different architectures.

[0047] 4, storage device 408 is a non-transitory computer-readable medium such as a hard drive, compact disc read-only memory (CD-ROM), DVD, or solid-state memory device. Memory 406 holds instructions and data used by processor 402. Pointing device 414 is a mouse, trackball, touch screen, or other type of pointing device and is used in combination with keyboard 410 (which may be an on-screen keyboard) to input data into computer system 400. Graphics adapter 412 displays images and other information on display 418. Network adapter 416 couples computer system 400 to one or more computer networks.

[0048] The types of computers used by the entities in Figures 1-3 may vary depending on the embodiment and the processing power required by the entities. For example, LIS 110 may include a distributed database system with multiple blade servers working together to provide the functionality described herein. Furthermore, the computers may lack some of the components described above, such as keyboard 410, graphics adapter 412, and display 418.

[0049] Exemplary Methods 9 is a flowchart illustrating a method for generating a report on blood chromatography data according to one embodiment. The steps in FIG. 9 are illustrated from the perspective of a chromatogram analysis tool 240 performing the method. However, some or all of the steps may be performed by other entities or components. Additionally, in some embodiments, steps may be performed in parallel, steps may be performed in a different order, or different steps may be performed.

[0050] 9 , the method begins at step 910, in which chromatogram analysis tool 240 receives blood test chromatographic data for a patient's blood sample. In some embodiments, chromatogram analysis tool 240 receives the blood test chromatographic data from laboratory equipment 120. In other embodiments, chromatography analysis tool 240 receives the blood test chromatographic data from LIS 110. The received blood test chromatographic data includes multiple peaks. Each peak corresponds to a type of hemoglobin and has a value indicative of the amount of hemoglobin of the corresponding type present in the blood sample. After receiving 910, pre-processing module 310 may analyze the quality of the blood test chromatographic data, perform sample analysis, calculate special sums, or perform baseline subtraction.

[0051] The chromatogram analysis tool 240 identifies 920 multiple regions of the chromatographic data. The identifying step 920 is performed by the region identification module 320 described with respect to FIG. 3. Each region contains chromatographic data from a different chromatographic peak range. The start and end points of each region may be identified 920 based on features of the chromatographic data or by absolute time.

[0052] For each region, the chromatography analysis tool 240 retrieves 930 a plurality of region templates corresponding to that region and identifies 940 a best-fit matching region template by comparing the region template with the chromatographic data contained within that region. The plurality of region templates are retrieved 930 from the template store 325 by the template matching module 330. The step of identifying 940 a best-fit matching region is performed by the template matching module 330.

[0053] The chromatography analysis tool 240 generates 950 a report based on the best-fit match region template for each region. In one embodiment, the chromatography analysis tool 240 generates 950 the report additionally based on information from the preprocessing module 310, such as %A2 / E. The generating 950 is performed by the results evaluation module 340. The generated 950 report may include one or more medical conditions; comments on the chromatogram data; and comments on the one or more medical conditions, including common pitfalls, recommendations for additional testing, or additional information. The report may be generated 950 for display, for example, by the display subsystem or any other display terminal.

[0054] Additional Considerations Some portions of the foregoing description describe aspects in terms of algorithmic processing of operations. These algorithmic descriptions and representations are commonly used by those skilled in the data processing arts to effectively convey the substance of their work to others skilled in the art. While these operations are described functionally, computationally, or logically, they are understood to be implemented by computer programs comprising instructions for execution by a processor, or equivalent electrical circuits or microcode, etc. Further, it has proven convenient at times, without loss of generality, to refer to these arrangements of functional operations as modules.

[0055] As used herein, a reference to "one embodiment" or "an embodiment" means that a particular element, feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment. The appearances of the phrase "in one embodiment" in various places in this specification do not necessarily all refer to the same embodiment.

[0056] Some aspects may be described using the terms "coupled" and "connected," along with their derivatives. It should be understood that these terms are not intended as synonyms for each other. For example, some aspects may be described using the term "connected" to indicate that two or more elements are in direct physical or electrical contact with each other. In another example, some aspects may be described using the term "coupled" to indicate that two or more elements are in direct physical or electrical contact with each other. However, the term "coupled" can also mean that two or more elements are not in direct contact with each other, but yet still cooperate or interact with each other. The aspects are not limited in this context.

[0057] As used herein, the terms "comprises," "comprising," "includes," "including," "has," "having," or any other variation thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, article, or apparatus that includes a list of elements is not necessarily limited to only those elements and may include other elements not expressly listed or inherent in that process, method, article, or apparatus. Furthermore, unless expressly stated otherwise, "or" refers to an inclusive "or / or" rather than an exclusive "or / or." For example, condition A or B can be satisfied by any one of A being true (or present) and B being false (or absent), A being false (or absent) and B being true (or present), and both A and B being true (or present).

[0058] Additionally, the use of "a" or "an" is utilized to describe elements and components of aspects. This is done merely for convenience and to give a general sense of the disclosure. This description should be read as including one or at least one, and the singular also includes the plural unless clearly meant otherwise.

[0059] Those skilled in the art, upon reading this disclosure, will recognize additional alternative structural and functional designs for the system and process for providing a chromatogram analysis tool to aid in the evaluation of hemoglobinopathies. Thus, while particular embodiments and applications have been illustrated and described above, it should be understood that the description is not limited to the precise construction and components disclosed herein, and that various modifications, changes, and variations that will be recognized by those skilled in the art may be made in the arrangement, operation, and details of the disclosed methods and apparatus. The scope of protection is to be limited only by the appended claims.

[0060] Patentable subject matter includes, but is not limited to, the following claims.

Claims

1. 1. A method for generating a report from blood test data, the method comprising: receiving blood test chromatography data for a patient's blood sample, the data including a plurality of peaks, each peak corresponding to one or more types of hemoglobin and having a value indicative of the amount of the corresponding type of hemoglobin present in the blood sample; dividing the chromatographic data into a plurality of regions, each region containing chromatographic data from a different retention time range within the chromatographic data; For each area, retrieving a plurality of region templates corresponding to the region; and identifying a best-fit matching region template based on a matching measure indicating how closely each region template matches the chromatographic data contained within the region; and Generating a report indicating one or more medical conditions based on the best-fit match region template for each region.

2. 10. The method of claim 1, wherein the report includes at least one comment providing advice regarding interpretation of the report.

3. 3. The method of claim 2, wherein the advice regarding interpretation of the report includes at least one of common pitfalls associated with the one or more medical conditions, recommendations for additional testing, or additional information about the medical condition.

4. Providing reports for display on the device 10. The method of claim 1, further comprising:

5. 2. The method of claim 1, wherein each region of the plurality of regions has a corresponding predetermined range, each range being defined by a start and end feature within the chromatogram.

6. 6. The method of claim 5, wherein at least two of the corresponding predetermined ranges are of different lengths.

7. Determining an indicator of the quality of the chromatographic data; and generating a notification if the quality indicator falls below a predetermined threshold.

10. The method of claim 1, further comprising:

8. identifying a best-fit matching region template for each region, For each region template, determining the maximum correlation coefficient R value between the chromatographic data of said region and said region template; and determining the best-fit match region template based on the maximum correlation coefficient R value; 2. The method of claim 1, comprising:

9. Determining the maximum correlation coefficient R value for a given region template sliding the given region template across the region of the chromatography data; calculating R values for different positions of the given region template within the region of the chromatographic data; and selecting the largest of the R values as the maximum R value for the given region template.

9. The method of claim 8, comprising:

10. 2. The method of claim 1, wherein each template represents an archetypical shape of a chromatogram in said region, including one or more peaks.

11. below: receiving blood test chromatography data for a patient's blood sample, the data including a plurality of peaks, each peak corresponding to one or more types of hemoglobin and indicating an amount of the corresponding one or more types of hemoglobin present in the blood sample; dividing the chromatographic data into a plurality of regions, each region containing chromatographic data from a different retention time range within the chromatographic data; For each area, retrieving a plurality of region templates corresponding to the region; and identifying a best-fit matching region template based on a matching measure indicating how closely each region template matches the chromatographic data contained within the region; and generating a report indicating one or more medical conditions based on the best-fit match region template for each region; A non-transitory computer-readable medium storing computer program instructions executable by a processor to perform operations including:

12. 12. The non-transitory computer-readable medium of claim 11, wherein the report includes at least one comment providing advice regarding interpretation of the report.

13. 13. The non-transitory computer-readable medium of claim 12, wherein advice regarding interpretation of the report includes at least one of common pitfalls associated with the one or more medical conditions, recommendations for additional testing, or additional information about the medical condition.

14. Providing reports for display on the device 12. The non-transitory computer-readable medium of claim 11 having stored thereon instructions further comprising:

15. 12. The non-transitory computer-readable medium of claim 11, wherein each region of the plurality of regions has a corresponding predetermined range, each range being defined by a start feature and an end feature in the chromatogram.

16. 16. The non-transitory computer-readable medium of claim 15, wherein at least two of the corresponding predetermined ranges have different lengths.

17. determining an indicator of the quality of the chromatographic data to determine; and generating a notification if the quality indicator falls below a predetermined threshold; 12. The non-transitory computer-readable medium of claim 11, further comprising:

18. identifying a best-fit matching region template for each region; For each region template, determining an R value between the chromatographic data of the region and the region template; and Determine the best-fit match area based on the highest R value 12. The non-transitory computer-readable medium of claim 11, further comprising:

19. 12. The non-transitory computer-readable medium of claim 11, wherein each template represents a hemoglobin composition of a prototypical shape of a chromatogram in said region, including one or more peaks.

20. a port for injecting a blood sample extracted from the patient; one or more processors; When executed, receiving blood test chromatography data for a patient's blood sample, the data including a plurality of peaks, each peak corresponding to one or more types of hemoglobin and having a value indicative of the amount of the corresponding type of hemoglobin present in the blood sample; dividing the chromatographic data into a plurality of regions, each region containing chromatographic data from a different retention time range within the chromatographic data; For each area, retrieving a plurality of region templates corresponding to the region; and identifying a best-fit matching region template based on a matching measure indicating how closely each region template matches the chromatographic data contained within the region; and generating a report based on the best-fit match region template for each region; a computer-readable medium having stored thereon computer program code that causes the one or more processors to perform operations including:

1. A chromatography device for generating a report from blood test data, comprising:

Images