A blockchain-integrated distributed prenatal screening information processing system
By combining blockchain technology to build a distributed prenatal screening information processing system, the problems of isolated prenatal screening data and untimely information exchange have been solved, and efficient and secure data sharing and rapid return of screening results have been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING YOUDA MEDICAL INFORMATION TECH CO LTD
- Filing Date
- 2023-05-11
- Publication Date
- 2026-05-12
AI Technical Summary
Existing prenatal screening data is isolated, information exchange is not timely, and time costs are high. In addition, traditional cloud processing methods have high network requirements, put a lot of pressure on the core network, and are prone to leakage of personal privacy data.
Design a distributed prenatal screening information processing system that incorporates blockchain, including a data acquisition layer, a data screening layer, and a knowledge sharing layer. Utilize blockchain technology to construct a consortium blockchain to achieve data and intelligent algorithm sharing. Outlier processing is performed through distributed data screening nodes, and the complexity of the intelligent algorithms is optimized in the cloud.
It effectively reduced the pressure on the core network, quickly returned data sharing results, improved the efficiency and accuracy of data screening, ensured data security and privacy, and enabled efficient data sharing across medical institutions.
Smart Images
Figure CN116738164B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of the Internet of Things, and more specifically to a distributed prenatal screening information processing system that incorporates blockchain. Background Technology
[0002] Prenatal screening data is indispensable in hospitals, treatment processes, and scientific research. Most important data and information from hospital systems and individual patients are stored on modern storage media. Some critical data may also be stored on system terminals such as personal computers, PDAs (Personal Digital Assistants), server storage modules, or other removable storage modules. This data is relatively isolated, stored in hospital information system archives, and cannot be linked to outpatient records. This leads to delayed information exchange and potential patient information leaks during inter-institutional data sharing, increasing time costs. Furthermore, this data lacks encryption, making it vulnerable to unauthorized access to raw data stored on servers, seriously threatening personal privacy.
[0003] Traditional prenatal screening methods involve centrally sending pregnant women's data to a unified server. This traditional cloud processing approach places high demands on the network, puts significant pressure on the core network, and results in slow return of prenatal screening information. Therefore, establishing a distributed prenatal screening information processing system is essential. This platform allows for the collection, preprocessing, management, and unified use of relevant data, providing medical staff involved in prenatal screening and diagnosis with faster and more convenient information retrieval and management services. This improves the efficiency of prenatal screening and health management while ensuring the security of pregnant women's privacy data and the uniqueness of its intended use. Summary of the Invention
[0004] The purpose of this invention is to provide a distributed prenatal screening information processing system that incorporates blockchain technology, which solves the shortcomings of traditional information processing systems, such as relatively isolated data, untimely information exchange, and high time costs.
[0005] To achieve the above functions, this invention designs a distributed prenatal screening information processing system combined with blockchain, including a data acquisition layer, a data screening layer, and a knowledge sharing layer, to realize prenatal data screening and sharing in hospitals.
[0006] The data screening layer consists of a predetermined number of data acquisition nodes distributed across various departments within hospitals. These nodes are used to collect and transmit prenatal data, as well as receive and display shared knowledge. The distributed data screening layer also comprises a predetermined number of distributed data screening nodes, located throughout the hospitals. These nodes receive prenatal data from data acquisition nodes within their respective departments, process outliers in the prenatal data using anomaly processing methods, obtain prenatal screening data, generate anomaly alerts and send them to the corresponding data acquisition nodes, and upload the prenatal screening data to the knowledge sharing layer, where they also receive shared knowledge. The knowledge sharing layer, located in the cloud, collects and stores prenatal screening data uploaded by distributed data screening nodes from the data screening layer. It includes an anomaly detection algorithm update module. Based on the anomaly detection algorithm and the prenatal screening data, this module updates the parameters and adjusts the algorithm on the knowledge sharing layer to detect anomalies in prenatal screening data from various departments of hospitals. The knowledge sharing layer then distributes the generated shared knowledge to the distributed data screening nodes of the data screening layer, completing the screening and sharing of prenatal data within the hospital.
[0007] As a preferred technical solution of the present invention: the data acquisition layer includes a data acquisition module and a shared result display module. The data acquisition module includes data acquisition nodes distributed in various departments of various hospitals, used to collect prenatal data from various departments and upload it to the distributed data screening nodes of the data screening layer. The shared result display module is used to receive and display shared knowledge. The distributed data screening nodes include a data screening module and a shared result distribution module. The data screening module is used to receive prenatal data from various departments of various hospitals, process abnormal values in the prenatal data, upload the obtained prenatal screening data to the knowledge sharing layer, and receive shared knowledge distributed by the knowledge sharing layer. The shared result distribution module is used to receive the shared knowledge and distribute it to the shared result display module of the data acquisition layer.
[0008] As a preferred technical solution of the present invention: the shared knowledge layer includes a data storage module, an abnormal data detection algorithm update module, and a knowledge sharing module; the data storage module is used to receive and store the prenatal screening data uploaded by the data screening layer, and transmit the prenatal screening data to the abnormal data detection algorithm update module; the abnormal data detection algorithm update module can update the algorithm parameters and adjust the detection algorithm on the knowledge sharing layer; the knowledge sharing module is used to receive shared knowledge distributed to each distributed data screening node of the data screening layer.
[0009] As a preferred technical solution of the present invention, the abnormal data processing method on which the distributed data screening node is based is as follows:
[0010] Step S1: The distributed data screening nodes preprocess the received prenatal data, including data cleaning and missing value imputation.
[0011] Step S2: Perform outlier detection on the preprocessed prenatal data;
[0012] Step S3: Based on the number of detected outliers, delete, replace, or interpolate the outliers.
[0013] Beneficial effects: Compared with the prior art, the advantages of the present invention include:
[0014] (1) When the hospital has a need for prenatal screening data sharing, the hospital’s data screening node will directly call the abnormal data processing method to process the data and detect abnormal values in the data. Compared with the traditional data processing method that relies on cloud servers, this method can effectively reduce the pressure on the core network and quickly return the data sharing results.
[0015] (2) This invention places the complex training and optimization process of intelligent algorithms in the cloud, while the data screening nodes on the network edge are only responsible for the inference of intelligent algorithms. This can effectively balance the development of computing resources and the improvement of computing efficiency of data screening nodes.
[0016] (3) The knowledge-sharing layer effectively solves the problem of isolated prenatal screening data among different hospitals, enabling data and intelligent algorithms to be shared in a distributed environment. A consortium blockchain is constructed using blockchain technology. When using the consortium blockchain, only high-powered devices are needed for verification; other data screening nodes can directly share data and intelligent algorithms through nearby high-powered devices. This approach is more cost-effective and efficient. Furthermore, a consensus mechanism is incorporated into the consortium blockchain to ensure the security and efficiency of knowledge transactions. Attached Figure Description
[0017] Figure 1 This is a block diagram of the overall structure of a distributed prenatal screening information processing system incorporating blockchain, provided by an embodiment of the present invention.
[0018] Figure 2 This is a functional module composition and workflow diagram of a distributed prenatal screening information processing system incorporating blockchain, provided by an embodiment of the present invention.
[0019] Figure 3 This is a schematic diagram of the blockchain technology principle applied in the knowledge sharing process of a distributed prenatal screening information processing system combined with blockchain, according to an embodiment of the present invention. Detailed Implementation
[0020] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.
[0021] Reference Figure 1 This invention provides a distributed prenatal screening information processing system incorporating blockchain, comprising a data acquisition layer, a data screening layer, and a knowledge sharing layer, to achieve prenatal data screening and sharing within hospitals.
[0022] The data screening layer consists of a predetermined number of data acquisition nodes distributed across various departments within hospitals. These nodes are used to collect and transmit prenatal data, as well as receive and display shared knowledge. The distributed data screening layer also comprises a predetermined number of distributed data screening nodes, located throughout the hospitals. These nodes receive prenatal data from data acquisition nodes within their respective departments, process outliers in the prenatal data using anomaly processing methods, obtain prenatal screening data, generate anomaly alerts and send them to the corresponding data acquisition nodes, and upload the prenatal screening data to the knowledge sharing layer, where they also receive shared knowledge. The knowledge-sharing layer, residing in the cloud, collects and stores prenatal screening data uploaded by distributed data screening nodes from the data screening layer. It includes an anomaly detection algorithm update module. Based on the anomaly detection algorithm and the prenatal screening data, this module updates the algorithm's parameters and adjusts the algorithm on the knowledge-sharing layer to detect anomalies in prenatal screening data from various departments of hospitals. The knowledge-sharing layer then distributes the generated shared knowledge to the distributed data screening nodes of the data screening layer, completing the screening and sharing of prenatal data across hospitals. This shared knowledge refers to the prenatal screening data from various hospitals after processing using anomaly detection methods.
[0023] The anomaly detection algorithm update module takes into account the differences in anomaly detection algorithms, which may select different features for data from different regions and hospitals, making it impossible to detect anomalies in prenatal screening data from multiple medical institutions. The anomaly detection algorithm update module can update the parameters and adjust the anomaly detection algorithm at the knowledge sharing layer.
[0024] The specific abnormal data processing method upon which the distributed data screening nodes are based is as follows:
[0025] Step S1: The distributed data screening nodes preprocess the received prenatal data, including data cleaning and missing value imputation.
[0026] Step S2: For the preprocessed prenatal data, statistical methods are used to detect outliers, taking the box plot method as an example:
[0027] Box plots are an outlier detection method based on quartiles. Specifically, for a data point x, the distance between its upper and lower quartiles is multiplied by 1.5 to determine if it's an outlier. The specific calculation formula is as follows:
[0028] IQR = Q3 - Q1
[0029] Upper fence = Q3 + 1.5 × IQR
[0030] Lower fence = Q1 - 1.5 × IQR
[0031] Where Q1 and Q3 are the lower and upper quartiles of the data, respectively, IQR is the interquartile range, Upperfence represents the upper limit, and Lower fence represents the lower limit. Data values that are greater than the upper limit or less than the lower limit are considered outliers.
[0032] Step S3: Based on the number of detected outliers, delete, replace, or interpolate the outliers.
[0033] The specific method is as follows:
[0034] (1) Delete
[0035] If the number of outliers is less than a preset lower threshold, these data points are deleted directly. However, it is important to note the impact of deleting data points on the screening results.
[0036] (2) Replacement
[0037] If the number of outliers falls between the preset lower threshold and the preset upper threshold, each outlier will be replaced with a representative value such as the mean, median, or mode. However, it is important to be aware of the impact of the replacement values on the screening results.
[0038] (3) Interpolation
[0039] If the number of outliers exceeds a preset upper threshold, interpolation methods are used to estimate the outliers. Interpolation methods include linear interpolation and spline interpolation. However, it is important to be aware of the impact of interpolation methods on the screening results.
[0040] Reference Figure 2The data acquisition layer includes a data acquisition module and a shared results display module. The data acquisition module includes data acquisition nodes distributed across various departments in different hospitals, used to collect prenatal data from each department and upload it to the distributed data screening nodes of the data screening layer. The shared results display module is used to receive and display shared knowledge. The distributed data screening nodes include a data screening module and a shared results distribution module. The data screening module is used to receive prenatal data from various departments in different hospitals, process outliers in the prenatal data, upload the obtained prenatal screening data to the knowledge sharing layer, and receive shared knowledge distributed by the knowledge sharing layer. The shared results distribution module is used to receive shared knowledge and distribute it to the shared results display module of the data acquisition layer.
[0041] The shared knowledge layer includes a data storage module, an abnormal data detection algorithm update module, and a knowledge sharing module. The data storage module is used to receive and store the prenatal screening data uploaded by the data screening layer and transmit the prenatal screening data to the abnormal data detection algorithm update module. The knowledge sharing module is used to receive shared knowledge distributed to each distributed data screening node of the data screening layer.
[0042] By leveraging the knowledge-sharing layer, prenatal data with regional characteristics can be integrated, and the learning process of abnormal data processing methods for prenatal data can be modified, thereby improving the accuracy of prenatal screening at a global level.
[0043] Reference Figure 3 The knowledge sharing process from the knowledge-sharing layer to each distributed data screening node adopts a distributed peer-to-peer (P2P) model. Prenatal screening data is managed and shared through a consortium blockchain. If a public blockchain were used, the data screening nodes in individual hospitals would be unable to meet deployment requirements due to limitations in computing power and power consumption. Using a consortium blockchain, distributed data screening nodes can utilize high-powered devices near the hospital for verification, thus achieving knowledge sharing. This approach is more cost-effective and efficient. Distributed data screening nodes that upload prenatal screening data are called knowledge producers, and those that acquire shared knowledge are called knowledge acquirers.
[0044] Knowledge aggregation: (1) All distributed data screening nodes will be assigned an ID after accessing the blockchain, which is generated by asymmetric encryption; (2) After generating prenatal screening data, the distributed data screening nodes encrypt it with a private key and upload it to the chain with the help of nearby high-power devices. The knowledge sharing layer obtains the encrypted data from the chain with the help of nearby high-power devices.
[0045] Knowledge Sharing: (1) The knowledge sharing process uses a consortium blockchain, which includes smart contracts. (2) After the knowledge sharing layer performs anomaly detection on the smart algorithm in the anomaly detection algorithm update module based on newly collected prenatal screening data, it uploads the shared knowledge to the blockchain in the form of private key encryption using a high-power device. Similarly, knowledge acquirers also access the shared knowledge on the blockchain through nearby high-power devices.
[0046] The entire process of knowledge aggregation and sharing is completed automatically by smart contract scripts to ensure the efficiency and fairness of knowledge transactions.
[0047] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.
Claims
1. A distributed prenatal screening information processing system incorporating blockchain, characterized in that, It includes a data acquisition layer, a data screening layer, and a knowledge sharing layer to enable prenatal data screening and sharing within the hospital. The data screening layer consists of a predetermined number of data acquisition nodes distributed across various departments within hospitals. These nodes are used to collect and transmit prenatal data, as well as receive and display shared knowledge. The distributed data screening layer also comprises a predetermined number of distributed data screening nodes, located throughout the hospitals. These nodes receive prenatal data from data acquisition nodes within their respective departments, process outliers in the prenatal data using anomaly processing methods, obtain prenatal screening data, generate anomaly alerts and send them to the corresponding data acquisition nodes, and upload the prenatal screening data to the knowledge sharing layer, where they also receive shared knowledge. The knowledge sharing layer, located in the cloud, collects and stores prenatal screening data uploaded by distributed data screening nodes from the data screening layer. It includes an anomaly detection algorithm update module. Based on the anomaly detection algorithm and the prenatal screening data, this module updates the parameters and adjusts the algorithm on the knowledge sharing layer to detect anomalies in prenatal screening data from various departments of hospitals. The knowledge sharing layer then distributes the generated shared knowledge to the distributed data screening nodes of the data screening layer, completing the screening and sharing of prenatal data within the hospital.
2. The distributed prenatal screening information processing system incorporating blockchain according to claim 1, characterized in that, The data acquisition layer includes a data acquisition module and a shared results display module. The data acquisition module includes data acquisition nodes distributed across various departments in different hospitals, used to collect prenatal data from each department and upload it to the distributed data screening nodes of the data screening layer. The shared results display module is used to receive and display shared knowledge. The distributed data screening nodes include a data screening module and a shared results distribution module. The data screening module is used to receive prenatal data from various departments in different hospitals, process outliers in the prenatal data, upload the obtained prenatal screening data to the knowledge sharing layer, and receive shared knowledge distributed by the knowledge sharing layer. It then sends the shared knowledge to the shared results distribution module, which receives the shared knowledge and distributes it to the shared results display module of the data acquisition layer.
3. The distributed prenatal screening information processing system combined with blockchain according to claim 1, characterized in that, The shared knowledge layer includes a data storage module, an abnormal data detection algorithm update module, and a knowledge sharing module. The data storage module is used to receive and store the prenatal screening data uploaded by the data screening layer and transmit the prenatal screening data to the abnormal data detection algorithm update module. The knowledge sharing module is used to receive shared knowledge distributed to each distributed data screening node of the data screening layer.
4. The distributed prenatal screening information processing system incorporating blockchain according to claim 1, characterized in that, The specific abnormal data processing method upon which the distributed data screening nodes are based is as follows: Step S1: The distributed data screening nodes preprocess the received prenatal data, including data cleaning and missing value imputation. Step S2: Perform outlier detection on the preprocessed prenatal data; Step S3: Based on the number of detected outliers, delete, replace, or interpolate the outliers.