Patient access amount monitoring method and system based on flexible electronics and multi-parameter fusion

Abstract

This invention discloses a method and system for monitoring patient fluid intake and output based on flexible electronics and multi-parameter fusion. The method includes: acquiring multiple monitoring parameters of a target patient using multiple monitoring devices incorporating flexible electronic designs; determining the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters; determining the correlation between the monitoring items based on the disease type corresponding to the target patient; and calculating the corresponding fluid intake and output parameters of the target patient based on the correlation between the monitoring items and the fluid volume parameter of the target patient for each monitoring item. Therefore, this invention can achieve accurate fluid intake and output assessment based on multiple parameters of flexible devices and disease correlation, improving the accuracy of patient fluid management and treatment safety, and reducing the risk of fluid imbalance.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for monitoring patient intake and output based on flexible electronics and multi-parameter fusion. Background Technology

[0002] With the increasing demand for precision medicine and patient monitoring, medical institutions are placing greater emphasis on optimizing patient fluid management through multi-parameter monitoring to improve treatment safety. Current technologies typically collect patient monitoring parameters using a single electronic device and employ fixed threshold analysis or manual calculation methods to assess intake and output parameters to support clinical treatment or research decisions. Existing solutions lack comprehensive analysis of fluid volume parameters from multiple monitoring items and correlation modeling between disease types. This makes it difficult to accurately determine the correlations between monitoring items and optimize intake and output calculations. Commonly used isolated monitoring strategies are unsuitable for complex disease scenarios, resulting in insufficient accuracy in fluid management, a high risk of fluid imbalance, and limitations on patient treatment safety and efficacy. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for monitoring patient fluid intake and output based on flexible electronics and multi-parameter fusion, which can realize accurate assessment of fluid intake and output based on multiple parameters of flexible devices and disease correlation, improve the accuracy of patient fluid management and treatment safety, and reduce the risk of fluid imbalance.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a method for monitoring patient fluid intake and output based on flexible electronics and multi-parameter fusion, the method comprising:

[0005] Multiple monitoring parameters of the target patient are acquired through multiple monitoring devices, including those with flexible electronic designs.

[0006] Based on the monitoring parameters, determine the fluid volume parameters of the target patient for each monitoring item;

[0007] Based on the disease type of the target patient, the corresponding monitoring items and their relationships are determined;

[0008] Based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item, the corresponding intake and output parameters of the target patient are calculated.

[0009] As an optional implementation, in the first aspect of the present invention, the monitoring device is an ingestion monitoring camera, a weighing plate, an infusion monitoring device, a urine output monitoring device, or a dehydration monitoring device.

[0010] As an optional implementation, in the first aspect of the invention, determining the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters includes:

[0011] For each monitoring item, identify multiple relevant monitoring devices corresponding to that monitoring item; optionally, the monitoring item may be a high-temperature water loss item, an ingestion item, an infusion effect item, or an excretion item.

[0012] The monitoring parameters obtained by all the relevant monitoring devices are input into the liquid volume calculation model corresponding to the monitoring item to obtain the liquid volume parameters corresponding to the monitoring item.

[0013] As an optional implementation, in the first aspect of the present invention, determining the plurality of related monitoring devices corresponding to the monitoring item includes:

[0014] The historical impact period corresponding to the monitoring item is determined in the historical database; the historical impact period is used to characterize the time period during which the patient performed an action that led to a change in the fluid volume of the monitoring item.

[0015] For each of the monitoring devices, obtain the historical working records corresponding to that monitoring device;

[0016] Calculate the similarity between the time period in the historical work record where the monitored quantity is greater than a preset threshold and the historical influence time period to obtain the correlation of the monitoring device.

[0017] From all the monitoring devices, devices with a correlation greater than a preset correlation threshold are selected to obtain multiple related monitoring devices corresponding to the monitoring item.

[0018] As an optional implementation, in the first aspect of the present invention, the liquid volume calculation model is a random forest model, which includes multiple decision tree models; each decision tree model is trained using a training dataset that includes multiple sets of training monitoring parameters and corresponding liquid volume labels; the set of training monitoring parameters includes training monitoring parameters corresponding to multiple monitoring devices.

[0019] As an optional implementation, in the first aspect of the present invention, determining the correlation of corresponding monitoring items based on the disease type corresponding to the target patient includes:

[0020] Determine the type of disease corresponding to the target patient;

[0021] Determine the historical medical records corresponding to the disease type in the preset database;

[0022] Based on the occurrence of monitoring items in the historical medical records, the correlation between the corresponding monitoring items is determined.

[0023] As an optional implementation, in the first aspect of the present invention, determining the correlation between monitoring items based on the occurrence of monitoring items in the historical medical records includes:

[0024] Screen out medical records containing at least one of the monitored items from the historical medical records;

[0025] For any two monitoring items, calculate the ratio of the number of abnormal records in all the disease records in which the parameters of the two monitoring items are abnormal to the total number of disease records, and obtain the proportional parameters corresponding to the two monitoring items.

[0026] For each abnormal record, calculate the normalized ratio between the parameter differences of the two monitoring items and the normal parameters in the abnormal record to obtain the difference similarity corresponding to the abnormal record;

[0027] Calculate the average of the difference similarity corresponding to all the abnormal records to obtain the abnormal similarity between the two monitoring items;

[0028] Calculate the weighted sum of the proportional parameter and the anomaly similarity to obtain the correlation parameters corresponding to the two monitoring items.

[0029] As an optional implementation, in the first aspect of the invention, calculating the intake and output parameters corresponding to the target patient based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item includes:

[0030] For any of the monitoring items, calculate the average value of the correlation parameters between the monitoring item and all other monitoring items to obtain the key parameters of the monitoring item;

[0031] Calculate the correction weights that are proportional to the key parameters;

[0032] Calculate the product of the correction weight and the liquid volume parameter corresponding to the monitoring item to obtain the correction liquid volume parameter corresponding to the monitoring item;

[0033] Calculate the average value of the corrected fluid volume parameters corresponding to all the monitored items to obtain the intake and output parameters corresponding to the target patient.

[0034] A second aspect of this invention discloses a patient intake and output monitoring system based on flexible electronics and multi-parameter fusion, the system comprising:

[0035] The acquisition module is used to acquire multiple monitoring parameters of the target patient through multiple monitoring devices, including flexible electronic designs.

[0036] The first determining module is used to determine the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters;

[0037] The second determining module is used to determine the correlation between the corresponding monitoring items based on the disease type corresponding to the target patient;

[0038] The calculation module is used to calculate the intake and output parameters of the target patient based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item.

[0039] As an optional implementation, in a second aspect of the invention, the monitoring device is an ingestion monitoring camera, a weighing plate, an infusion monitoring device, a urine output monitoring device, or a dehydration monitoring device.

[0040] As an optional implementation, in a second aspect of the invention, the first determining module determines the specific method by which it determines the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters, including:

[0041] For each monitoring item, identify multiple relevant monitoring devices corresponding to that monitoring item; optionally, the monitoring item may be a high-temperature water loss item, an ingestion item, an infusion effect item, or an excretion item.

[0042] The monitoring parameters obtained by all the relevant monitoring devices are input into the liquid volume calculation model corresponding to the monitoring item to obtain the liquid volume parameters corresponding to the monitoring item.

[0043] As an optional implementation, in a second aspect of the invention, the first determining module determines the specific method by which it determines the multiple related monitoring devices corresponding to the monitoring item, including:

[0044] The historical impact period corresponding to the monitoring item is determined in the historical database; the historical impact period is used to characterize the time period during which the patient performed an action that led to a change in the fluid volume of the monitoring item.

[0045] For each of the monitoring devices, obtain the historical working records corresponding to that monitoring device;

[0046] Calculate the similarity between the time period in the historical work record where the monitored quantity is greater than a preset threshold and the historical influence time period to obtain the correlation of the monitoring device.

[0047] From all the monitoring devices, devices with a correlation greater than a preset correlation threshold are selected to obtain multiple related monitoring devices corresponding to the monitoring item.

[0048] As an optional implementation, in the second aspect of the present invention, the liquid volume calculation model is a random forest model, which includes multiple decision tree models; each decision tree model is trained using a training dataset that includes multiple sets of training monitoring parameters and corresponding liquid volume labels; the set of training monitoring parameters includes training monitoring parameters corresponding to multiple monitoring devices.

[0049] As an optional implementation, in a second aspect of the invention, the second determining module determines the specific method by which it determines the correlation between the corresponding monitoring items based on the disease type corresponding to the target patient, including:

[0050] Determine the type of disease corresponding to the target patient;

[0051] Determine the historical medical records corresponding to the disease type in the preset database;

[0052] Based on the occurrence of monitoring items in the historical medical records, the correlation between the corresponding monitoring items is determined.

[0053] As an optional implementation, in a second aspect of the invention, the specific method by which the second determining module determines the correlation between monitoring items based on the occurrence of monitoring items in the historical medical record includes:

[0054] Screen out medical records containing at least one of the monitored items from the historical medical records;

[0055] For any two monitoring items, calculate the ratio of the number of abnormal records in all the disease records in which the parameters of the two monitoring items are abnormal to the total number of disease records, and obtain the proportional parameters corresponding to the two monitoring items.

[0056] For each abnormal record, calculate the normalized ratio between the parameter differences of the two monitoring items and the normal parameters in the abnormal record to obtain the difference similarity corresponding to the abnormal record;

[0057] Calculate the average of the difference similarity corresponding to all the abnormal records to obtain the abnormal similarity between the two monitoring items;

[0058] Calculate the weighted sum of the proportional parameter and the anomaly similarity to obtain the correlation parameters corresponding to the two monitoring items.

[0059] As an optional implementation, in a second aspect of the invention, the specific method by which the calculation module calculates the intake and output parameters corresponding to the target patient based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item includes:

[0060] For any of the monitoring items, calculate the average value of the correlation parameters between the monitoring item and all other monitoring items to obtain the key parameters of the monitoring item;

[0061] Calculate the correction weights that are proportional to the key parameters;

[0062] Calculate the product of the correction weight and the liquid volume parameter corresponding to the monitoring item to obtain the correction liquid volume parameter corresponding to the monitoring item;

[0063] Calculate the average value of the corrected fluid volume parameters corresponding to all the monitored items to obtain the intake and output parameters corresponding to the target patient.

[0064] A third aspect of this invention discloses another patient intake and output monitoring system based on flexible electronics and multi-parameter fusion, the system comprising:

[0065] Memory containing executable program code;

[0066] A processor coupled to the memory;

[0067] The processor calls the executable program code stored in the memory to execute some or all of the steps in the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion disclosed in the first aspect of the present invention.

[0068] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion disclosed in the first aspect of the present invention.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] This invention acquires monitoring parameters of the target patient through multiple flexible electronic design monitoring devices to determine the fluid volume parameters of each monitoring item, determines the correlation between the monitoring items and the patient's disease type, and calculates the intake and output parameters based on the correlation and fluid volume parameters. This enables accurate intake and output assessment based on multiple parameters of flexible devices and disease correlation, improves the accuracy of patient fluid management and treatment safety, and reduces the risk of fluid imbalance. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a flowchart illustrating a patient intake and output monitoring method based on flexible electronics and multi-parameter fusion disclosed in an embodiment of the present invention.

[0073] Figure 2 This is a schematic diagram of a patient intake and output monitoring system based on flexible electronics and multi-parameter fusion disclosed in an embodiment of the present invention.

[0074] Figure 3 This is a schematic diagram of another patient intake and output monitoring system based on flexible electronics and multi-parameter fusion disclosed in an embodiment of the present invention. Detailed Implementation

[0075] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0077] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0078] This invention discloses a method and system for monitoring patient fluid intake and output based on flexible electronics and multi-parameter fusion. It acquires monitoring parameters of the target patient using multiple flexible electronic monitoring devices to determine the fluid volume parameters for each monitoring item. The correlation between these parameters and the patient's disease type is then determined. Based on the correlation and fluid volume parameters, fluid intake and output parameters are calculated. This enables accurate fluid intake and output assessment based on flexible devices, multi-parameter data, and disease correlation, improving the accuracy of patient fluid management and treatment safety, and reducing the risk of fluid imbalance. Detailed explanations follow.

[0079] Example 1

[0080] Please see Figure 1 , Figure 1 This is a schematic flowchart of a patient intake and output monitoring method based on flexible electronics and multi-parameter fusion disclosed in an embodiment of the present invention. Figure 1 The described patient intake and output monitoring method based on flexible electronics and multi-parameter fusion can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, this patient intake and output monitoring method based on flexible electronics and multi-parameter fusion may include the following operations:

[0081] 101. Acquire multiple monitoring parameters of the target patient through multiple monitoring devices, including those with flexible electronic designs.

[0082] Optionally, the flexible electronic design may include flexible sensors, flexible circuit boards, or wearable monitoring modules, and the present invention does not limit these.

[0083] Optionally, the monitoring device can acquire data through real-time acquisition, periodic sampling, or triggered recording; this invention does not impose any limitations on this method.

[0084] 102. Based on the monitoring parameters, determine the fluid volume parameters for each monitoring item for the target patient.

[0085] Optionally, the liquid volume parameter can be liquid intake, liquid output, or net change in liquid volume; this invention does not impose any limitation on this parameter.

[0086] 103. Based on the disease type of the target patient, determine the correlation of the corresponding monitoring items.

[0087] Optionally, the condition can be diabetes, heart disease, kidney failure, or dehydration; this invention does not limit the specific condition.

[0088] Optionally, the correlation of the monitoring project can be a correlation coefficient, correlation strength, or causal relationship weight, which is not limited in this invention.

[0089] 104. Based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item, calculate the corresponding intake and output parameters of the target patient.

[0090] As can be seen, the above-mentioned embodiments of the invention acquire the monitoring parameters of the target patient through multiple flexible electronic design monitoring devices to determine the fluid volume parameters of each monitoring item, determine the correlation between the monitoring items in combination with the patient's disease type, and calculate the intake and output parameters based on the correlation and fluid volume parameters. This enables accurate intake and output assessment based on multiple parameters of flexible devices and disease correlation, improves the accuracy of patient fluid management and treatment safety, and reduces the risk of fluid imbalance.

[0091] As an optional embodiment, the monitoring device in the above steps can be a food monitoring camera, a weighing plate, an infusion monitoring device, a urine monitoring device, or a dehydration monitoring device.

[0092] Optionally, the monitoring parameter can be ingestion image data, ingestion food weight data, infusion flow rate data, urine output data, urine temperature data, or hidden water loss parameters; the present invention does not limit this.

[0093] In one specific implementation scheme, to assist in realizing the monitoring technology solution disclosed in this invention, an inflow / outflow monitoring system including multiple intelligent monitoring devices is implemented, comprising:

[0094] 1. The smart plate has a built-in weight sensor and a food image recognition sensor to directly acquire the weight of food and images of the food being eaten. It can further identify the water content of the food. For example, it can identify a 200g apple and automatically calculate the water content as 185ml by calling the FDA food composition database to obtain the corresponding liquid volume parameter.

[0095] 2. Infusion monitor, which uses a MEMS flow sensor with an accuracy of ±2ml, is used to acquire infusion flow data.

[0096] 3. The intelligent urine bag system uses ultrasonic liquid level sensing and temperature compensation to acquire urine output data and urine temperature data.

[0097] 4. The latent water loss calculation module estimates skin evaporation using a wristband bioimpedance meter and calculates latent water loss parameters using the following formula:

[0098] Latent water loss (ml) = body surface area (m²) 2 )×(15+respiratory rate)×0.5*.

[0099] 5. Weight scale, used to obtain data on changes in the patient's weight.

[0100] By utilizing the different modules of the aforementioned monitoring system and combining them with the monitoring method steps disclosed in this invention, multimodal sensor data of patients can be accurately acquired and accurate intake and output predictions can be made. Specifically, the monitoring system also includes an early warning module, with the following early warning logic: a yellow warning is given when the 4-hour intake and output deviation is >10%, while a red warning is given when the 1-hour urine output is <0.5 ml / kg.

[0101] Specifically, the hardware configuration of this monitoring system includes:

[0102] Weighing tray: Employs a high-precision strain gauge sensor (range 0-5kg, accuracy ±1g), model HX711;

[0103] Image recognition camera: Raspberry Pi Camera V3 (supports 120° wide-angle);

[0104] Data processing terminal: Embedded Linux system (Raspberry Pi 4B).

[0105] The infusion monitoring unit adopts:

[0106] Non-contact flow sensor: adopts ultrasonic Doppler principle, model UF-1000, accuracy ±2ml / min;

[0107] Bubble detection: Integrated infrared photoelectric sensor with a detection sensitivity of Φ≥1mm bubbles.

[0108] The wristband for monitoring hidden water loss uses a sensor array, including a TI AFE4300 chip and an SHT40 environmental sensor.

[0109] As can be seen, the above optional embodiments limit the details of the monitoring equipment to obtain more diverse monitoring parameters, assist in achieving accurate intake and output assessment based on multiple parameters and disease correlation, improve the accuracy of patient fluid management and treatment safety, and reduce the risk of fluid imbalance.

[0110] As an optional embodiment, the step above, determining the target patient's fluid volume parameter for each monitoring item based on the monitoring parameters, includes:

[0111] For each monitoring item, identify multiple relevant monitoring devices corresponding to that monitoring item; optionally, the monitoring item may be a high-temperature water loss item, an ingestion item, an infusion effect item, or an excretion item.

[0112] Input the monitoring parameters obtained from all relevant monitoring devices into the liquid volume calculation model corresponding to the monitoring item to obtain the liquid volume parameters corresponding to the monitoring item.

[0113] As can be seen, through the above optional embodiments, by determining the relevant monitoring equipment for each monitoring item and inputting its monitoring parameters into the corresponding fluid volume calculation model to obtain fluid volume parameters, accurate fluid volume assessment based on multi-device data and item characteristics can be achieved, thereby improving the accuracy of target patient's intake and output calculation and treatment safety, and reducing the risk of fluid imbalance.

[0114] As an optional embodiment, the step of determining the multiple related monitoring devices corresponding to the monitoring item in the above steps includes:

[0115] Determine the historical impact period corresponding to the monitoring item in the historical database; optionally, the historical impact period is used to characterize the time period during which the patient performed behaviors that led to changes in the fluid volume of the monitoring item.

[0116] For each monitoring device, obtain the historical work records corresponding to that monitoring device;

[0117] Calculate the similarity between the time period in the historical work record where the monitored quantity is greater than a preset threshold and the historical impact time period to obtain the correlation of the monitoring device.

[0118] From all monitoring devices, devices with a correlation greater than a preset correlation threshold are selected to obtain multiple relevant monitoring devices corresponding to the monitoring item.

[0119] Optionally, the historical database can be a local database, a cloud database, or a distributed database; this invention does not impose any limitations.

[0120] Optionally, the historical impact period can be a time range of minutes, hours, or days; this invention does not impose any limitations.

[0121] Optionally, the determination of the historical impact period can be based on timestamp matching, behavior log analysis, or event association rules, and this invention does not impose any limitations.

[0122] Optionally, the acquisition of these historical work records can be filtered based on device identifier, time range, or data type; this invention does not impose any limitations on this.

[0123] Optionally, the historical work record may include real-time data, historical data, or statistical data, and this invention does not limit it.

[0124] Optionally, the similarity can be calculated based on time overlap rate, Jaccard coefficient or time series matching algorithm, and the present invention does not limit it.

[0125] Optionally, the preset similarity threshold can be a fixed threshold, a dynamic threshold, or a threshold adjusted based on the monitored items; this invention does not impose any limitations.

[0126] As can be seen, through the above optional embodiments, by determining the historical impact time period corresponding to the monitoring item in the historical database, obtaining the historical working records of each monitoring device, calculating the similarity between the recording time period when the monitoring quantity exceeds the threshold and the historical impact time period as the correlation, and screening devices with a correlation exceeding the threshold as relevant monitoring devices, the accurate screening of relevant devices based on historical behavior time and monitoring data can be achieved, thereby improving the accuracy of patient fluid volume parameter assessment and treatment safety, and reducing the risk of fluid imbalance.

[0127] As an optional embodiment, in the above steps, the liquid volume calculation model is a random forest model, which includes multiple decision tree models; each decision tree model is trained using a training dataset that includes multiple sets of training monitoring parameters and corresponding liquid volume labels; the set of training monitoring parameters includes training monitoring parameters corresponding to multiple monitoring devices.

[0128] Optionally, the random forest model may include a fixed number of decision trees, dynamically adjusted decision trees, or an optimized set of subtrees; this invention does not impose any limitations on this.

[0129] Optionally, the training dataset may include historical monitoring data, simulation data, or clinical trial data, and this invention does not impose any limitations.

[0130] As can be seen, the above optional embodiments define the model architecture and training details of the fluid volume calculation model, so as to accurately calculate the precise fluid volume parameters, assist in achieving accurate intake and output assessment based on multiple parameters and disease correlation, improve the accuracy of patient fluid management and treatment safety, and reduce the risk of fluid imbalance.

[0131] As an optional embodiment, the step above, determining the correlation of corresponding monitoring items based on the disease type of the target patient, includes:

[0132] Determine the type of disease corresponding to the target patient;

[0133] Determine the historical medical records corresponding to the disease type in the preset database;

[0134] Based on the occurrence of monitoring items in historical medical records, the correlation between the corresponding monitoring items is determined.

[0135] Optionally, the type of disease can be determined based on medical diagnosis, patient medical records, or real-time vital signs data; this invention does not impose any limitations on this.

[0136] Optionally, the disease type can be an acute disease, a chronic disease, or a combination of diseases; this invention does not limit the types.

[0137] Optionally, this determination process may be combined with doctor's diagnosis, automatic classification model or data mining algorithm, and the present invention is not limited thereto.

[0138] Optionally, the historical medical record may include the patient's medical history, treatment records, or monitoring data records, and this invention does not limit this.

[0139] Optionally, the determination of the historical medical record can be based on symptom code matching, keyword retrieval, or semantic analysis, and this invention does not impose any limitations.

[0140] Optionally, the occurrence status of the monitored item can be the frequency of occurrence, the rate of abnormality, or the correlation pattern of the monitored item; this invention does not impose any limitations.

[0141] As can be seen, through the above optional embodiments, by determining the disease type of the target patient and obtaining the corresponding historical disease records from the preset database, the correlation between monitoring items is determined based on the occurrence of monitoring items in the records, thereby realizing accurate correlation analysis of monitoring items based on disease type and historical data, improving the accuracy of patient fluid volume parameter calculation and treatment safety, and reducing the risk of fluid imbalance.

[0142] As an optional embodiment, the step above, determining the correlation between monitoring items based on the occurrence of monitoring items in historical medical records, includes:

[0143] Screen out medical records that contain at least one monitoring item in their historical medical records;

[0144] For any two monitoring items, calculate the ratio of the number of abnormal records in all medical records where the parameters of the two monitoring items are abnormal to the total number of medical records, and obtain the proportional parameters corresponding to the two monitoring items.

[0145] For each abnormal record, calculate the normalized ratio between the parameter differences of the two monitoring items in the abnormal record and the normal parameters to obtain the difference similarity corresponding to the abnormal record;

[0146] Calculate the average of the difference similarity corresponding to all abnormal records to obtain the abnormal similarity between the two monitoring items;

[0147] The weighted sum of the proportional parameter and the anomaly similarity is calculated to obtain the correlation parameters corresponding to the two monitoring items.

[0148] Optionally, the ratio parameter can be a percentage, a fraction, or a normalized ratio, and the present invention does not limit it.

[0149] Optionally, the identification of the abnormal record can be based on threshold judgment, anomaly detection algorithm or machine learning classification, and the present invention does not limit it.

[0150] Optionally, the normalization ratio can be calculated based on minimum-maximum normalization, Z-score normalization, or logarithmic transformation; this invention does not impose any limitations on this.

[0151] As can be seen, through the above optional embodiments, by screening records containing at least one monitoring item in historical medical records, calculating the proportion of abnormal records with abnormal parameters in any two monitoring items to the total number of records, calculating the normalized ratio of the difference between the two monitoring item parameters for each abnormal record as the difference similarity, calculating the average of the difference similarities of all abnormal records to obtain the abnormal similarity, and then calculating the weighted sum of the proportion parameter and the abnormal similarity as the correlation parameter, a precise monitoring item correlation assessment based on abnormal co-occurrence and parameter differences can be achieved, improving the accuracy of patient fluid volume parameter calculation and treatment safety, and reducing the risk of fluid imbalance.

[0152] As an optional embodiment, the step above, calculating the target patient's fluid intake and output parameters based on the correlation of the monitoring items and the target patient's fluid volume parameters for each monitoring item, includes:

[0153] For any given monitoring item, calculate the average value of the correlation parameters between that monitoring item and all other monitoring items to obtain the key parameters of that monitoring item;

[0154] Calculate the correction weights that are proportional to the key parameters;

[0155] Calculate the product of the correction weight and the liquid volume parameter corresponding to the monitoring item to obtain the correction liquid volume parameter corresponding to the monitoring item;

[0156] Calculate the average value of the corrected fluid volume parameters corresponding to all monitored items to obtain the intake and output parameters corresponding to the target patient.

[0157] As can be seen, through the above optional embodiments, key parameters are obtained by calculating the average value of the correlation parameters between any monitoring item and other monitoring items. Correction weights are determined proportionally based on the key parameters. The product of the correction weights and the fluid volume parameters is calculated to obtain the corrected fluid volume parameters. The average value of the corrected fluid volume parameters of all monitoring items is then taken as the intake and output parameters of the target patient. This achieves accurate intake and output calculation based on correlation weighting, improves the accuracy of patient fluid management and treatment safety, and reduces the risk of fluid imbalance.

[0158] Example 2

[0159] Please see Figure 2 , Figure 2 This is a schematic diagram of a patient intake and output monitoring system based on flexible electronics and multi-parameter fusion, as disclosed in an embodiment of the present invention. Figure 2The described patient intake and output monitoring system based on flexible electronics and multi-parameter fusion can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the patient intake and output monitoring system based on flexible electronics and multi-parameter fusion may include:

[0160] The acquisition module 201 is used to acquire multiple monitoring parameters of the target patient through multiple monitoring devices including flexible electronic designs.

[0161] The first determining module 202 is used to determine the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters.

[0162] The second determining module 203 is used to determine the correlation of the corresponding monitoring items based on the disease type of the target patient.

[0163] The calculation module 204 is used to calculate the intake and output parameters of the target patient based on the correlation of the monitoring items and the fluid volume parameters of the target patient in each monitoring item.

[0164] As can be seen, the above-mentioned embodiments of the invention acquire the monitoring parameters of the target patient through multiple flexible electronic design monitoring devices to determine the fluid volume parameters of each monitoring item, determine the correlation between the monitoring items in combination with the patient's disease type, and calculate the intake and output parameters based on the correlation and fluid volume parameters. This enables accurate intake and output assessment based on multiple parameters of flexible devices and disease correlation, improves the accuracy of patient fluid management and treatment safety, and reduces the risk of fluid imbalance.

[0165] As an optional embodiment, the monitoring device is a food monitoring camera, a weighing plate, an infusion monitoring device, a urine monitoring device, or a dehydration monitoring device.

[0166] As can be seen, the above optional embodiments limit the details of the monitoring equipment to obtain more diverse monitoring parameters, assist in achieving accurate intake and output assessment based on multiple parameters and disease correlation, improve the accuracy of patient fluid management and treatment safety, and reduce the risk of fluid imbalance.

[0167] As an optional embodiment, the first determining module determines the specific method by which it determines the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters, including:

[0168] For each monitoring item, identify multiple relevant monitoring devices corresponding to that monitoring item; optionally, the monitoring item may be a high-temperature water loss item, an ingestion item, an infusion effect item, or an excretion item.

[0169] Input the monitoring parameters obtained from all relevant monitoring devices into the liquid volume calculation model corresponding to the monitoring item to obtain the liquid volume parameters corresponding to the monitoring item.

[0170] As can be seen, through the above optional embodiments, by determining the relevant monitoring equipment for each monitoring item and inputting its monitoring parameters into the corresponding fluid volume calculation model to obtain fluid volume parameters, accurate fluid volume assessment based on multi-device data and item characteristics can be achieved, thereby improving the accuracy of target patient's intake and output calculation and treatment safety, and reducing the risk of fluid imbalance.

[0171] As an optional embodiment, the first determining module determines the specific method of determining the multiple related monitoring devices corresponding to the monitoring item, including:

[0172] Determine the historical impact period corresponding to the monitoring item in the historical database; optionally, the historical impact period is used to characterize the time period during which the patient performed behaviors that led to changes in the fluid volume of the monitoring item.

[0173] For each monitoring device, obtain the historical work records corresponding to that monitoring device;

[0174] Calculate the similarity between the time period in the historical work record where the monitored quantity is greater than a preset threshold and the historical impact time period to obtain the correlation of the monitoring device.

[0175] From all monitoring devices, devices with a correlation greater than a preset correlation threshold are selected to obtain multiple relevant monitoring devices corresponding to the monitoring item.

[0176] As can be seen, through the above optional embodiments, by determining the historical impact time period corresponding to the monitoring item in the historical database, obtaining the historical working records of each monitoring device, calculating the similarity between the recording time period when the monitoring quantity exceeds the threshold and the historical impact time period as the correlation, and screening devices with a correlation exceeding the threshold as relevant monitoring devices, the accurate screening of relevant devices based on historical behavior time and monitoring data can be achieved, thereby improving the accuracy of patient fluid volume parameter assessment and treatment safety, and reducing the risk of fluid imbalance.

[0177] As an optional embodiment, the liquid volume calculation model is a random forest model, which includes multiple decision tree models; each decision tree model is trained using a training dataset that includes multiple sets of training monitoring parameters and corresponding liquid volume labels; the set of training monitoring parameters includes training monitoring parameters corresponding to multiple monitoring devices.

[0178] As can be seen, the above optional embodiments define the model architecture and training details of the fluid volume calculation model, so as to accurately calculate the precise fluid volume parameters, assist in achieving accurate intake and output assessment based on multiple parameters and disease correlation, improve the accuracy of patient fluid management and treatment safety, and reduce the risk of fluid imbalance.

[0179] As an optional embodiment, the second determining module determines the specific method of the correlation between the corresponding monitoring items based on the disease type of the target patient, including:

[0180] Determine the type of disease corresponding to the target patient;

[0181] Determine the historical medical records corresponding to the disease type in the preset database;

[0182] Based on the occurrence of monitoring items in historical medical records, the correlation between the corresponding monitoring items is determined.

[0183] As can be seen, through the above optional embodiments, by determining the disease type of the target patient and obtaining the corresponding historical disease records from the preset database, the correlation between monitoring items is determined based on the occurrence of monitoring items in the records, thereby realizing accurate correlation analysis of monitoring items based on disease type and historical data, improving the accuracy of patient fluid volume parameter calculation and treatment safety, and reducing the risk of fluid imbalance.

[0184] As an optional embodiment, the second determining module determines the specific method of the correlation between monitoring items based on the occurrence of monitoring items in historical medical records, including:

[0185] Screen out medical records that contain at least one monitoring item in their historical medical records;

[0186] For any two monitoring items, calculate the ratio of the number of abnormal records in all medical records where the parameters of the two monitoring items are abnormal to the total number of medical records, and obtain the proportional parameters corresponding to the two monitoring items.

[0187] For each abnormal record, calculate the normalized ratio between the parameter differences of the two monitoring items in the abnormal record and the normal parameters to obtain the difference similarity corresponding to the abnormal record;

[0188] Calculate the average of the difference similarity corresponding to all abnormal records to obtain the abnormal similarity between the two monitoring items;

[0189] The weighted sum of the proportional parameter and the anomaly similarity is calculated to obtain the correlation parameters corresponding to the two monitoring items.

[0190] As can be seen, through the above optional embodiments, by screening records containing at least one monitoring item in historical medical records, calculating the proportion of abnormal records with abnormal parameters in any two monitoring items to the total number of records, calculating the normalized ratio of the difference between the two monitoring item parameters for each abnormal record as the difference similarity, calculating the average of the difference similarities of all abnormal records to obtain the abnormal similarity, and then calculating the weighted sum of the proportion parameter and the abnormal similarity as the correlation parameter, a precise monitoring item correlation assessment based on abnormal co-occurrence and parameter differences can be achieved, improving the accuracy of patient fluid volume parameter calculation and treatment safety, and reducing the risk of fluid imbalance.

[0191] As an optional embodiment, the calculation module calculates the target patient's intake and output parameters according to the correlation of the monitoring items and the target patient's fluid volume parameters for each monitoring item in a specific way, including:

[0192] For any given monitoring item, calculate the average value of the correlation parameters between that monitoring item and all other monitoring items to obtain the key parameters of that monitoring item;

[0193] Calculate the correction weights that are proportional to the key parameters;

[0194] Calculate the product of the correction weight and the liquid volume parameter corresponding to the monitoring item to obtain the correction liquid volume parameter corresponding to the monitoring item;

[0195] Calculate the average value of the corrected fluid volume parameters corresponding to all monitored items to obtain the intake and output parameters corresponding to the target patient.

[0196] As can be seen, through the above optional embodiments, key parameters are obtained by calculating the average value of the correlation parameters between any monitoring item and other monitoring items. Correction weights are determined proportionally based on the key parameters. The product of the correction weights and the fluid volume parameters is calculated to obtain the corrected fluid volume parameters. The average value of the corrected fluid volume parameters of all monitoring items is then taken as the intake and output parameters of the target patient. This achieves accurate intake and output calculation based on correlation weighting, improves the accuracy of patient fluid management and treatment safety, and reduces the risk of fluid imbalance.

[0197] Example 3

[0198] Please see Figure 3 , Figure 3 This is another patient intake and output monitoring system based on flexible electronics and multi-parameter fusion disclosed in the embodiments of the present invention. Figure 3 The described patient intake and output monitoring system based on flexible electronics and multi-parameter fusion is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). Figure 3As shown, the patient intake and output monitoring system based on flexible electronics and multi-parameter fusion may include:

[0199] Memory 301 storing executable program code;

[0200] Processor 302 coupled to memory 301;

[0201] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion described in Embodiment 1.

[0202] Example 4

[0203] This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion described in Embodiment 1.

[0204] Example 5

[0205] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion described in Embodiment 1.

[0206] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0207] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0208] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0209] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0211] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0212] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0213] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0214] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0215] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0216] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0217] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0218] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0219] Finally, it should be noted that the patient intake and output monitoring method and system based on flexible electronics and multi-parameter fusion disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A patient access amount monitoring method based on flexible electronics and multi-parameter fusion, characterized in that, The method includes: Multiple monitoring parameters of the target patient are acquired through multiple monitoring devices, including those with flexible electronic designs. Based on the monitoring parameters, the fluid volume parameters of the target patient for each monitoring item are determined, including: For each monitoring item, the corresponding historical impact time period is determined in the historical database; the historical impact time period is used to characterize the time period during which the patient performed an action that caused a change in the fluid volume of the monitoring item. For each of the monitoring devices, obtain the historical working records corresponding to that monitoring device; Calculate the similarity between the time period in the historical work record where the monitored quantity is greater than a preset threshold and the historical influence time period to obtain the correlation of the monitoring device. From all the monitoring devices, devices with a correlation greater than a preset correlation threshold are selected to obtain multiple related monitoring devices corresponding to the monitoring item; the monitoring item is a high-temperature water loss item, a feeding item, an infusion effect item, or an excretion item; The monitoring parameters obtained by all the relevant monitoring devices are input into the liquid volume calculation model corresponding to the monitoring item to obtain the liquid volume parameters corresponding to the monitoring item. Based on the disease type corresponding to the target patient, the correlation of the corresponding monitoring items is determined, including: Determine the type of disease corresponding to the target patient; Determine the historical medical records corresponding to the disease type in the preset database; Screen out medical records containing at least one of the monitored items from the historical medical records; For any two monitoring items, calculate the ratio of the number of abnormal records in all the disease records in which the parameters of the two monitoring items are abnormal to the total number of disease records, and obtain the proportional parameters corresponding to the two monitoring items. For each abnormal record, calculate the normalized ratio between the parameter differences of the two monitoring items and the normal parameters in the abnormal record to obtain the difference similarity corresponding to the abnormal record; Calculate the average of the difference similarity corresponding to all the abnormal records to obtain the abnormal similarity between the two monitoring items; Calculate the weighted sum of the ratio parameter and the anomaly similarity to obtain the correlation parameters corresponding to the two monitoring items; Based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item, the corresponding intake and output parameters of the target patient are calculated.

2. The patient fluid intake and output monitoring method based on flexible electronics and multi-parameter fusion according to claim 1, characterized in that, The monitoring equipment may be a food intake monitoring camera, a weighing plate, an infusion monitoring device, a urine output monitoring device, or a dehydration monitoring device.

3. The patient access monitoring method based on flexible electronics and multi-parameter fusion according to claim 1, characterized in that, The liquid volume calculation model is a random forest model, which includes multiple decision tree models; each decision tree model is trained using a training dataset that includes multiple sets of training monitoring parameters and corresponding liquid volume labels; the set of training monitoring parameters includes training monitoring parameters corresponding to multiple monitoring devices.

4. The patient access monitoring method based on flexible electronics and multi-parameter fusion according to claim 1, characterized in that, The step of calculating the intake and output parameters corresponding to the target patient based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item includes: For any of the monitoring items, calculate the average value of the correlation parameters between the monitoring item and all other monitoring items to obtain the key parameters of the monitoring item; Calculate the correction weights that are proportional to the key parameters; Calculate the product of the correction weight and the liquid volume parameter corresponding to the monitoring item to obtain the correction liquid volume parameter corresponding to the monitoring item; Calculate the average value of the corrected fluid volume parameters corresponding to all the monitored items to obtain the intake and output parameters corresponding to the target patient.

5. A patient access monitoring system based on flexible electronics and multi-parameter fusion, characterized in that, The system is used to perform the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion as described in any one of claims 1-4, the system comprising: The acquisition module is used to acquire multiple monitoring parameters of the target patient through multiple monitoring devices, including flexible electronic designs. The first determining module is used to determine the fluid volume parameter of the target patient for each monitoring item based on the monitoring parameters; The second determining module is used to determine the correlation between the corresponding monitoring items based on the disease type of the target patient; The calculation module is used to calculate the intake and output parameters of the target patient based on the correlation of the monitoring items and the fluid volume parameters of the target patient for each monitoring item.

6. A patient intake and output monitoring system based on flexible electronics and multi-parameter fusion, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the patient intake and output monitoring method based on flexible electronics and multi-parameter fusion as described in any one of claims 1-4.

Images