Microbial infection assisted analysis system and method based on timing alignment

Abstract

The application relates to a kind of microbial infection auxiliary analysis system and method based on timing alignment, belong to medical biological information data processing technical field.System includes data monitoring and triggering, multi-modal timing data alignment, intermediate layer semantic conversion, big model inference scoring module, and LIS, HIS system docking.Method with microorganism positive as trigger event, self-adaptive determination dynamic data acquisition window, isomorphic data such as temperature, inspection, medical order are aligned on uniform time axis and semantized conversion, and combined with local epidemiology knowledge base, complete antibiotic matching quantization scoring, output auxiliary diagnosis result after review.The present application realizes the timing fusion of microbiological test and clinical diagnosis and treatment data, solves the problem of isolated data in prior art, lack of quantitative decision basis, can accurately distinguish colonizing bacteria and pathogenic bacteria, provides objective scoring support for empirical anti-infection treatment, and improves infection diagnosis efficiency and accuracy.

Description

Technical Field

[0001] This application relates to the field of medical bioinformatics data processing technology, and in particular to a time-aligned auxiliary analysis system and method for microbial infection. Background Technology

[0002] Currently, in the field of microbial testing and clinical infection diagnosis, there is a common problem of separation between laboratory data and clinical diagnosis and treatment data.

[0003] Existing healthcare information systems typically operate microbiology testing (LIS) and clinical electronic medical records (HIS) as independent modules. When the LIS system detects pathogens (such as a positive blood culture), it can only push a static test report (containing the name and morphology of the bacterial species) to the doctor's end. After receiving the report, the doctor needs to manually switch to the HIS system, manually query and review the patient's temperature records, blood routine trends, imaging reports, and historical antibiotic prescriptions scattered across different time points, and then rely on personal experience to piece together this information to determine the infection status.

[0004] The existing technology has the following drawbacks and shortcomings: First, there is a lack of ability to correlate heterogeneous data over time: existing technologies cannot automatically align the key event of "positive microbial test" with the patient's "peak body temperature", "drug administration time" and "changes in inflammatory indicators" on the timeline. The data is presented in isolated tables, making it difficult for doctors to intuitively judge the temporal causal relationship between the disease progression and drug intervention.

[0005] Second, the lack of contextual information makes it difficult to make judgments: existing LIS reports lack clinical context and cannot automatically filter out interference from non-infectious factors (such as non-infectious fever), which can easily lead to misidentification of colonizing bacteria and pathogenic bacteria.

[0006] Third, there is a lack of quantitative decision support tools: In the empirical treatment phase before the results of drug sensitivity tests are issued, the existing system cannot calculate the antibiotic matching degree based on the hospital's historical epidemiological data and the patient's current status, and relies solely on the doctor's personal experience, lacking objective quantitative scoring support.

[0007] Therefore, there is an urgent need for a method in the relevant technologies that can solve the problem of insufficient auxiliary diagnostic evidence caused by the lack of temporal correlation between microbial test data and clinical diagnosis and treatment data in existing technologies. Summary of the Invention

[0008] Therefore, it is necessary to provide a time-aligned auxiliary analysis system and method for microbial infection to address the aforementioned technical problems.

[0009] In a first aspect, this application provides a time-series aligned microbial infection auxiliary analysis system, including a data monitoring and triggering module, a multimodal time-series data alignment module, an intermediate-layer semantic conversion module, and a large-model inference and scoring module. The system connects to a laboratory information system and a hospital information system via data interfaces, wherein: The data monitoring and triggering module is used to monitor microbial test data and generate infection triggering events, and to determine the baseline time point and dynamic data acquisition window; The multimodal time series data alignment module is used to construct a unified time axis and map heterogeneous data to fixed-granularity time slices to complete time series alignment. The intermediate semantic transformation module is used to transform the aligned data into a unified semantic vector to generate structured infection data; The large-scale model inference scoring module is used to combine an epidemiological knowledge base to complete the quantification scoring of antibiotic matching.

[0010] Optionally, in one embodiment of this application, the data monitoring and triggering module adaptively adjusts the range of the data acquisition window based on the changing trend of inflammatory indicators.

[0011] Optionally, in one embodiment of this application, the multimodal time series data alignment module extracts feature values ​​from high-frequency data, uses forward hold-and-fill for low-frequency data, and marks medical order data as a persistent state interval.

[0012] Optionally, in one embodiment of this application, the intermediate layer semantic conversion module converts numerical time-series data into clinical trend semantic labels, extracts pathological feature entities from the text data, and anchors them to the time axis.

[0013] Optionally, in one embodiment of this application, the large model reasoning scoring module uses a retrieval enhancement generation mechanism to call the epidemiological knowledge base and calculates the matching score by combining the antibacterial spectrum coverage, the slope of improvement of clinical indicators and epidemiological probability.

[0014] Secondly, this application also provides a time-aligned auxiliary analysis method for microbial infection. The method includes: Monitoring microbiological test data generates infection-triggered events, determines baseline time points and dynamic data acquisition windows, and collects heterogeneous data from laboratory information systems and hospital information systems; Constructing a unified timeline maps heterogeneous data to fixed-granularity time slices to achieve time-series alignment. The aligned data is transformed into a unified semantic vector to generate structured infection data; The antibiotic matching quantification score is completed by combining the epidemiological knowledge base, and the auxiliary diagnostic results are output after review.

[0015] Optionally, in one embodiment of this application, during the time alignment process, feature values ​​are extracted from high-frequency data, forward hold-and-fill is used for low-frequency data, and medical order data is marked as a persistent state interval.

[0016] Optionally, in one embodiment of this application, during the semantic transformation process, numerical time-series data is converted into clinical trend semantic labels, and pathological feature entities of text data are extracted and anchored to the time axis.

[0017] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the steps of the methods described in the various embodiments above.

[0018] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods described in the various embodiments above.

[0019] Compared with existing technologies, the above-mentioned time-aligned microbial infection auxiliary analysis system and method have the following advantages: First, it enables the spatiotemporal logical reconstruction of heterogeneous medical data, improving the accuracy of assisted diagnosis. Through multimodal temporal alignment technology, microbial results are correlated with body temperature, inflammatory markers, and imaging features on the same timeline, automatically identifying the causal relationship between bacterial detection and clinical symptoms, reducing misdiagnosis rates, and avoiding antibiotic overuse.

[0020] Second, an event-driven dynamic data acquisition mechanism is established to address the timeliness and completeness issues of static queries. An infection event time window slicing algorithm is adopted, adaptively scaling the acquisition window based on pathogen characteristics and inflammatory indicator trends to fully cover the entire infection cycle and provide a complete chain of diagnostic evidence.

[0021] Third, it provides quantifiable antibiotic matching evaluation criteria, filling the gap in empirical treatment decision-making tools. By combining large-scale model reasoning with a local epidemiological knowledge base, it outputs objective quantitative scores, providing a standardized basis for adjusting antibiotic regimens and shortening the time to effective treatment initiation. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of a time-aligned microbial infection auxiliary analysis system in one embodiment; Figure 2 This is a flowchart illustrating a time-aligned-based auxiliary analysis method for microbial infection in one embodiment. Figure 3 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] In one embodiment, such as Figure 1 As shown, a time-series aligned microbial infection auxiliary analysis system is provided, including a data monitoring and triggering module, a multimodal time-series data alignment module, an intermediate layer semantic conversion module, and a large model inference and scoring module. The system connects to a Laboratory Information System (LIS) and a Hospital Information System (HIS) via data interfaces, wherein: The data monitoring and triggering module is used to monitor microbial test data and generate infection triggering events, and to determine the baseline time point and dynamic data acquisition window; The multimodal time series data alignment module is used to construct a unified time axis and map heterogeneous data to fixed-granularity time slices to complete time series alignment. The intermediate semantic transformation module is used to transform the aligned data into a unified semantic vector to generate structured infection data; The large-scale model inference scoring module is used to combine an epidemiological knowledge base to complete the quantification scoring of antibiotic matching.

[0025] Each module executes a time-aligned auxiliary analysis method for microbial infection, such as... Figure 2 As shown, the specific steps include: S201: Monitor microbiological test data to generate infection triggering events, determine the baseline time point and dynamic data acquisition window, and collect heterogeneous data from the laboratory information system and the hospital information system.

[0026] In this embodiment, the system first deploys a daemon-style real-time listener on the LIS database interface to continuously scan the microbial testing status field; when a positive sample culture or smear result is detected, an infection trigger event is generated, the positive report timestamp is locked as the baseline time point T0, and the patient's unique identifier is extracted.

[0027] Afterwards, the system initializes the baseline window to 72 hours before T0 and 12 hours after T0, and scans the trend of inflammatory indicators such as CRP and PCT within the window. If the indicators show an upward slope, the window is backtracked to the inflection point to complete the adaptive correction of the acquisition window.

[0028] Finally, multimodal data is captured in parallel through the HIS interface: high-frequency body temperature time series data, medium and low frequency blood routine / CRP / PCT test data, antibiotic prescriptions and imaging report text data, and temporarily stored in the memory buffer.

[0029] S202: Construct a unified timeline to map heterogeneous data to fixed-granularity time slices to complete time alignment.

[0030] In this embodiment, an absolute time axis is constructed with T0 as the origin, and the dynamic window is divided into time slices with fixed granularity (4 hours). The data is traversed and mapped to the corresponding time slices according to the timestamp: the maximum value within the time slice of high-frequency body temperature data is extracted as the feature value; the forward hold-fill strategy is adopted for low-frequency test data to ensure data continuity; antibiotic orders are marked as a continuous state interval, covering the start and end time of the order.

[0031] S203: Transform the aligned data into a unified semantic vector to generate structured infection data.

[0032] In this embodiment, the intermediate layer semantic conversion module is activated to convert numerical data into clinical trend semantic labels (such as "persistent high fever"), extract pathological feature entities from imaging reports and anchor them to the time axis, and generate a structured infection panoramic data package containing time, physiological state and intervention measures.

[0033] S204: Combine the epidemiological knowledge base to complete the antibiotic matching quantification score, and output the auxiliary diagnostic results after review.

[0034] In this embodiment, structured data packets are input into the medical big language model inference engine and transformed into a model-understandable context through prompt word engineering; the RAG mechanism is used to call the hospital's epidemiological knowledge base to obtain historical bacterial resistance rates and antibiotic sensitivity data.

[0035] The inference engine performs multi-dimensional analysis: determining whether empirical medication covers the pathogen, analyzing the clinical indicator response after medication, and assessing the possibility of drug resistance; combining the antibacterial spectrum coverage, the slope of clinical indicator improvement, and epidemiological probability, it calculates an antibiotic-pathogen matching score of 0-100.

[0036] The system generates a draft auxiliary diagnostic report based on the reasoning suggestions and matching scores, and pushes it to the terminal of the microbiology laboratory group leader / reviewing physician. The reviewing physician can accept, modify or reject the draft. After review and approval, the system pushes the official report to the clinical HIS workstation and mobile terminal, completing the diagnostic loop.

[0037] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0038] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a time-aligned auxiliary analysis method for microbial infection. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0039] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0040] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0041] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0042] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0043] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0044] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0045] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0046] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A time-aligned microbial infection auxiliary analysis system, characterized in that, The system includes a data monitoring and triggering module, a multimodal time-series data alignment module, an intermediate layer semantic conversion module, and a large model inference and scoring module. The system connects to the laboratory information system and the hospital information system via data interfaces. The data monitoring and triggering module is used to monitor microbial test data and generate infection triggering events, and to determine the baseline time point and dynamic data acquisition window; The multimodal time series data alignment module is used to construct a unified time axis and map heterogeneous data to fixed-granularity time slices to complete time series alignment. The intermediate semantic transformation module is used to transform the aligned data into a unified semantic vector to generate structured infection data; The large-scale model inference scoring module is used to combine an epidemiological knowledge base to complete the quantification scoring of antibiotic matching.

2. The system according to claim 1, characterized in that, The data monitoring and triggering module adaptively adjusts the range of the data acquisition window based on the changing trends of inflammation indicators.

3. The system according to claim 1, characterized in that, The multimodal time-series data alignment module extracts feature values ​​from high-frequency data, uses forward hold-and-fill for low-frequency data, and marks medical order data as a continuous state interval.

4. The system according to claim 1, characterized in that, The intermediate semantic conversion module transforms numerical time-series data into clinical trend semantic labels, extracts pathological feature entities from text data, and anchors them to the time axis.

5. The system according to claim 1, characterized in that, The large model reasoning and scoring module uses a retrieval-enhanced generation mechanism to call the epidemiological knowledge base and calculates the matching score by combining the antibacterial spectrum coverage, the slope of improvement of clinical indicators and epidemiological probability.

6. A time-aligned auxiliary analysis method for microbial infection, characterized in that, The method includes: Monitoring microbiological test data generates infection-triggered events, determines baseline time points and dynamic data acquisition windows, and collects heterogeneous data from laboratory information systems and hospital information systems; Constructing a unified timeline maps heterogeneous data to fixed-granularity time slices to achieve time-series alignment. The aligned data is transformed into a unified semantic vector to generate structured infection data; The antibiotic matching quantification score is completed by combining the epidemiological knowledge base, and the auxiliary diagnostic results are output after review.

7. The method according to claim 6, characterized in that, During the time alignment process, feature values ​​are extracted from high-frequency data, forward hold-and-fill is used for low-frequency data, and medical order data are marked as persistent state intervals.

8. The method according to claim 6, characterized in that, During the semantic transformation process, numerical time-series data is converted into clinical trend semantic labels, and pathological feature entities of text data are extracted and anchored to the time axis.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 6 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 6 to 8.

Images