Premature infant post-hospital health management method, system, equipment, medium and product

Abstract

The invention discloses a premature infant post-hospital health management method, system and device, a medium and a product, and relates to the field of medical health, the method comprises the following steps: according to first data of a target premature infant, carrying out initial grading on the target premature infant to obtain a health risk level of the target premature infant at an initial moment; the first data comprises a medical record, birth gestational age and birth weight of the premature infant; the updating operation is circularly executed until the month age of the target premature infant reaches the month age threshold value, second data, collected newly, of the target premature infant are obtained, and the second data comprise at least one of vital sign monitoring data, growth and development data and home care data; dynamically updating the health risk level of the target premature infant according to a preset updating period and newly collected second data; after the updating operation is executed each time, personalized nursing suggestions of the target premature infant are generated according to newly collected second data and the updated health risk level; according to the invention, the management effect of the premature infant after discharge is improved.

Description

Technical Field

[0001] The present application relates to the field of medical health, and in particular to a method, system, equipment, medium and product for post-hospital health management of premature infants. Background Art

[0002] Premature infants are generally those born before 37 weeks of gestation. Because their organs and body systems are not yet fully developed, they require special attention and care. Health management is crucial to the growth and development of premature infants and is both a key and challenging aspect of neonatal clinical medicine and healthcare. Currently, medical staff primarily monitor the growth and development of premature infants through regular follow-up examinations, identify and address potential health issues, and provide appropriate care recommendations to ensure the health management of premature infants after discharge.

[0003] However, regular follow-up examinations for the health management of premature infants after discharge do not enable medical staff to fully and timely understand the growth and development of premature infants, and cannot timely detect the increase in health risks of premature infants. As a result, it is impossible to provide and apply corresponding nursing measures in time when the health risks of premature infants increase, resulting in unsatisfactory nursing effects for premature infants after discharge. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, equipment, medium and product for post-hospital health management of premature infants, which can improve the nursing effect of premature infants after discharge.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for post-hospital health management of premature infants, comprising:

[0007] performing an initial classification of the target premature infant based on first data of the target premature infant to obtain a health risk level of the target premature infant at an initial moment; wherein the first data includes the medical history, gestational age, and birth weight of the premature infant;

[0008] The updating operation is executed cyclically until the age of the target premature infant reaches the age threshold; wherein the updating operation includes:

[0009] Acquiring the latest collected second data of the target premature infant; wherein the second data includes at least one of vital sign monitoring data, growth and development data, and home care data;

[0010] Dynamically updating the health risk level of the target premature infant according to a preset update cycle and based on the latest collected second data;

[0011] After each execution of the updating operation, personalized care recommendations for the target premature infant are generated based on the most recently collected second data and the updated health risk level.

[0012] Optionally, performing an initial classification of the target premature infant according to the first data of the target premature infant specifically includes:

[0013] If the target premature infant meets the following conditions: the gestational age at birth is less than the first gestational age threshold, the birth weight is less than the first weight threshold, the percentile of any growth indicator at discharge is less than the first percentile threshold, and any one of the first complications after birth, the target premature infant is classified into the fifth level, and the health risk level of the target premature infant is five; wherein the growth indicators include height, weight, and head circumference;

[0014] If the target premature infant meets the following conditions: the gestational age at birth is less than the second gestational age threshold but not less than the first gestational age threshold, the birth weight is less than the second weight threshold but not less than the first weight threshold, the percentile of any growth indicator at discharge is not less than the first percentile threshold but less than the second percentile threshold, and any one of the second category complications is present after birth, then the target premature infant is classified into the fourth level, and the health risk level of the target premature infant is obtained as four;

[0015] If the target premature infant meets the following conditions: the gestational age at birth is less than the third gestational age threshold and not less than the second gestational age threshold, the birth weight is less than the third weight threshold and not less than the second weight threshold, the percentile of any growth indicator at discharge is not less than the second percentile threshold and less than the third percentile threshold, and any one of the third category complications is present after birth, then the target premature infant is classified into the third level, and the health risk level of the target premature infant is obtained as three;

[0016] If the target premature infant meets the following conditions: the gestational age at birth is less than 37 weeks and not less than the third gestational age threshold, the birth weight is not less than the third weight threshold, the percentile of any growth indicator at discharge is not less than the fourth percentile threshold, and the health condition is normal with no complications, then the target premature infant is classified into the second level, and the health risk level of the target premature infant is obtained as two;

[0017] If the target premature infant meets the requirements of having a special medical history after birth, or if the percentile of either weight or head circumference at discharge is not less than the fourth percentile threshold, the target premature infant will be classified into the first level, and the health risk level of the target premature infant will be one.

[0018] Optionally, dynamically updating the health risk level of the target premature infant based on the most recently collected second data of the target premature infant includes:

[0019] Preprocessing the newly collected second data and historical health data of the target premature infant to obtain third data; wherein the historical health data includes the first data and the historical second data, and the preprocessing includes data cleaning and data standardization;

[0020] The third data is input into the constructed risk prediction model, and the risk prediction model predicts and outputs the health risk level based on the third data to obtain an updated health risk level of the target premature infant.

[0021] Optionally, generating personalized care recommendations for the target premature infant based on the most recently collected second data and the updated health risk level includes:

[0022] Retrieving relevant nursing measures from a constructed knowledge base based on the newly collected second data of the target premature infant and the updated health risk level; wherein the knowledge base stores medical guidelines, expert consensus, and nursing standards for premature infants;

[0023] The input data is input into a target large language model, and the target large language model generates personalized care recommendations for the target premature infant based on the input data; wherein the input data includes the retrieved care measures and the most recently collected second data, historical health data and updated health risk level of the target premature infant.

[0024] Optionally, the method for post-hospital health management of premature infants further includes:

[0025] After each follow-up review, the health risk level of the target premature infant after follow-up was determined.

[0026] Optionally, determining the health risk level of the target premature infant after follow-up includes:

[0027] Directly match health risk level:

[0028] If the target premature infant meets the following criteria during follow-up: severe anemia, a bone density T-score no greater than -2.5, and a risk of metabolic bone disease, and any growth indicator percentile is less than any of the first percentile thresholds, then the health risk level obtained by matching is five; wherein the growth indicators include height, weight, and head circumference;

[0029] If the target premature infant meets any of the following conditions during follow-up: moderate anemia, the percentile of any growth indicator is not less than the first percentile threshold but less than the second percentile threshold, and the bone density T value is not greater than -2.5, then the matching health risk level is four.

[0030] If the target premature infant meets any of the following conditions during follow-up: a bone density T-value greater than -2.5 but not greater than -1.0; mild intraventricular hemorrhage after birth and mild anemia during follow-up; the percentile of any growth indicator is not less than the second percentile threshold but less than the third percentile threshold; and the Child Heart Scale Developmental Quotient is less than 80, then the matching health risk level is three.

[0031] If the target premature infant meets the following requirements during follow-up: the bone density T value is greater than -1.0 but not greater than 1.0, the health condition is normal and there are no complications, and the percentile of any growth indicator is not less than the third percentile threshold but less than the fourth percentile threshold, then the matching health risk level is two.

[0032] If the percentile of either weight or head circumference of the target premature infant during follow-up is greater than the fourth percentile threshold, the matched health risk level is one;

[0033] The larger of the health risk level obtained by matching and the health risk level most recently updated by the risk prediction model is selected as the health risk level of the target premature infant after follow-up.

[0034] In a second aspect, the present application provides a post-hospital health management system for premature infants, comprising:

[0035] an initial grading module, configured to perform an initial grading on the target premature infant based on the first data of the target premature infant, and obtain a health risk level of the target premature infant at an initial moment;

[0036] A database for storing relevant data of the target premature infant; the relevant data includes first data and second data; the first data includes medical history, gestational age at birth, and birth weight; the second data includes at least one of vital sign monitoring data, growth and development data, and home care data;

[0037] a communication interface, configured to obtain the first data of the target premature infant from the database according to an instruction of the initial classification module;

[0038] A monitor for monitoring the vital signs of the target premature infant and uploading the data to the database for storage;

[0039] A first human-computer interaction interface is used to receive growth and development data and / or home care data input by a user, and upload the data to the database for storage via the communication interface;

[0040] A dynamic update module is configured to cyclically execute an update operation until the age of the target premature infant reaches a threshold age; wherein the update operation includes:

[0041] Acquiring the latest collected second data of the target premature infant; dynamically updating the health risk level of the target premature infant according to a preset update cycle and based on the latest collected second data;

[0042] a recommendation generating module, configured to generate personalized care recommendations for the target premature infant based on the most recently collected second data and the updated health risk level after each execution of the updating operation;

[0043] The first display terminal is used to display the latest vital sign monitoring data collected by the monitor, the health risk level updated by the dynamic update module, and the personalized care suggestions generated by the suggestion generation module.

[0044] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described methods for post-hospital health management of premature infants.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for post-hospital health management of premature infants.

[0046] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for post-hospital health management of premature infants.

[0047] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0048] The present application provides a method, system, device, medium and product for post-hospital health management of premature infants. By initially grading the target premature infant according to the first data of the target premature infant, the health risk level of the target premature infant at the initial moment is obtained, so as to facilitate subsequent graded management of the target premature infant; by cyclically executing the update operation until the age of the target premature infant reaches the age threshold: obtaining the latest collected second data of the target premature infant (at least one of vital signs monitoring data, growth and development data and home care data), the growth and development status of the target premature infant can be fully and timely understood, and the health risk level of the target premature infant can be dynamically updated according to the preset update cycle and based on the latest collected second data of the target premature infant. When the updated health risk level of the target premature infant is higher than the unupdated health risk level, it means that the health risk of the target premature infant has increased. Therefore, the present application can timely discover the target premature infant's The health risk of premature infants increases when their physical condition is unstable (their age is not greater than the age threshold); after each update operation is performed, personalized nursing recommendations for the target premature infant are generated based on the latest collected second data and the updated health risk level. Therefore, when the health risk of the target premature infant increases, the present application promptly gives personalized nursing recommendations, so that family caregivers can care for the target premature infant according to the personalized nursing recommendations, thereby achieving timely application of corresponding nursing measures when the health risk of the target premature infant increases; in summary, the present application solves the problem that the health management of premature infants after discharge through regular follow-up examinations cannot enable medical staff to fully and timely understand the growth and development status of premature infants, cannot timely discover the increase in the health risk of premature infants, and cannot timely give and apply corresponding nursing measures when the health risk of premature infants increases, thereby improving the health management effect of premature infants after discharge. In addition, the post-hospital health management method for premature infants of the present application implements a hierarchical management model for target premature infants based on the health risk level of premature infants after discharge, combines a dynamic adjustment mechanism and a parent support system, and provides scientific, systematic, and continuous health management for premature infants after discharge. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 This is a diagram of an application environment for a method for post-hospital health management of premature infants in one embodiment of the present application;

[0051] Figure 2 A flowchart of a method for post-hospital health management of premature infants provided in one embodiment of the present application;

[0052] Figure 3 A schematic diagram of the functional modules of a post-hospital health management system for premature infants provided in one embodiment of the present application;

[0053] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0055] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0056] The post-hospital health management method for premature infants provided in the embodiments of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the first data of the target premature infant to the server 104. The first data includes the medical history, gestational age and birth weight of the target premature infant. After the server 104 receives the first data of the target premature infant, for the first data of the target premature infant, the server 104 first performs an initial classification of the target premature infant based on the first data of the premature infant, obtains the health risk level of the target premature infant at the initial moment, and cyclically performs the update operation until the age of the target premature infant reaches the age threshold; the update operation includes: according to the preset update cycle, and based on the latest acquired second data of the target premature infant, dynamically updating the health risk level of the target premature infant; and after each update operation is executed, generating personalized care recommendations for the target premature infant based on the latest acquired second data of the target premature infant, historical health data and updated health risk level. The server 104 can provide the obtained personalized nursing recommendations for the target premature infant to the terminal 102. In addition, in some embodiments, the post-hospital health management method for premature infants can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly generate personalized nursing recommendations, or the server 104 can obtain the first data, the most recently collected second data, and the historical health data of the premature infant from the data storage system, and generate personalized nursing recommendations based on the most recently collected second data, the historical health data, and the updated health risk level of the premature infant.

[0057] Terminal 102 may include, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers, or may be a cloud server.

[0058] In an exemplary embodiment, Figure 2 As shown, a method for post-hospital health management of premature infants is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 Taking the server 104 in FIG. 1 as an example, the method includes the following steps 201 to 203. In which:

[0059] Step 201 : Initially classify the target premature infant based on first data of the target premature infant to obtain the health risk level of the target premature infant at the initial moment; wherein the first health data includes the medical history, gestational age and birth weight of the premature infant.

[0060] In the embodiment of the present application, the target premature infant is a premature infant who is to undergo health management after discharge. The medical record is the medical record of the premature infant during hospitalization, including the APGAR score, complication data, medical history record (including the health status, complications and treatment process of the premature infant during the NICU (Neonatal Intensive Care Unit)), intervention record (medical intervention information, such as drug use, surgery, special care measures, etc.), and the first data can be entered by medical staff. There is no specific limitation on the total number of health risk levels and the grading rules here, and they can be set according to actual needs.

[0061] Step 202: cyclically execute the update operation until the target premature infant's age reaches a threshold.

[0062] In the embodiments of the present application, age in months refers to the number of months the target premature infant has experienced since birth. The age in months threshold generally refers to the age in months corresponding to the target premature infant's physical condition being stable and no longer requiring real-time monitoring of the target premature infant's second data, but only requiring regular hospital checkups. The age in months threshold is not specifically defined here and can be set according to actual needs. For example, setting the age in months threshold to 36 means that the cyclic update operation stops when the target premature infant reaches 36 months of age.

[0063] The above-mentioned update operation includes the following steps 2021 to 2022:

[0064] Step 2021, obtaining the latest collected second data of the target premature infant; wherein the second data includes at least one of vital sign monitoring data, growth and development data, and home care data.

[0065] In the embodiments of the present application, vital sign monitoring data refers to vital sign data collected by IoT devices (according to a preset collection cycle (e.g., one day)). Vital sign data may include heart rate, blood oxygen, respiratory rate, and body temperature. Growth and development data may include growth indicators and developmental indicators. Growth indicators include weight, height, and head circumference. Developmental indicators may include at least one of neuromotor ability, perception and sensory ability, cognitive development, language and communication ability, emotional and social ability, and reflex and neurological function. Home care data may include at least one of feeding data, daily care operation data, infant physiological response data, behavioral performance data, and health warning data. Feeding data may include feeding method (breast milk or formula milk, breastfeeding or bottle feeding), milk volume (single or daily), feeding duration (e.g., the time interval between two formula feedings), feeding frequency (e.g., the number of times formula is consumed per day), the addition of breast milk fortifiers, formula milk, complementary food additions, and trace element supplementation. Daily care operation data may include urination and defecation conditions, skin condition, environmental adaptation, vaccination status, and interventions in hearing, language, and movement. Bowel and bladder conditions refer to the infant's bowel movements, such as constipation, diarrhea, and diaper rash. Skin condition refers to the presence of rashes, dryness, or sores on the skin. Environmental adaptation refers to the infant's adaptation to the environment (e.g., home environment), such as sensitivity to temperature, humidity, and noise. Infant physiological response data includes feeding, sleep, and crying. Feeding refers to whether the infant can eat smoothly (including breast milk or formula), and whether there is vomiting or choking. Sleep refers to sleep duration and quality, as well as excessive irritability or sleepiness. Crying refers to the frequency, duration, and cause of crying (e.g., hunger, discomfort, need for diaper changes, etc.). Behavioral performance data includes motor development, interactive behavior, and emotional state. Motor development refers to the presence of normal reflexes, such as sucking and grasping reflexes, and the ability to follow hearing and sight, as well as the ability to turn over and raise the head on time. Interactive behavior refers to the presence of social behaviors such as eye contact and smiling, and the ability to respond to external stimuli (e.g., sound and light). Emotional state refers to whether a child is easily agitated or appears relatively calm, and whether there are mood swings, such as irritability. Health alert data includes abnormal signals and signs of illness. Abnormal signals are abnormal phenomena discovered by caregivers (such as parents), such as high or low body temperature, rapid breathing, purple or cyanotic skin, cold hands and feet, etc. Signs of illness are symptoms observed by caregivers that may be related to health problems, such as fever, persistent restlessness, and refusal to eat.

[0066] Step 2022: Dynamically update the health risk level of the target premature infant according to a preset update cycle and based on the latest collected second data.

[0067] In the embodiment of the present application, the most recently collected second data is the second data acquired last time before the health risk level of the target premature infant is dynamically updated.

[0068] Step 203: After each update operation is performed, generate personalized care recommendations for the target premature infant based on the latest collected second data and the updated health risk level.

[0069] In an embodiment of the present application, personalized care recommendations are generated for the target premature infant so that family caregivers can provide daily care and feeding for the target premature infant according to the personalized care recommendations.

[0070] Implement the above-mentioned steps 201 to 203, and perform an initial classification of the target premature infant based on the first data of the target premature infant to obtain the health risk level of the target premature infant at the initial moment, so as to subsequently perform graded management of the target premature infant; by cyclically executing the update operation until the age of the target premature infant reaches the age threshold: obtain the latest collected second data of the target premature infant (at least one of vital signs monitoring data, growth and development data, and home care data), so as to fully and timely understand the growth and development status of the target premature infant, and dynamically update the health risk level of the target premature infant according to the preset update cycle and based on the latest collected second data of the target premature infant. When the updated health risk level of the target premature infant is higher than the unupdated health risk level, it means that the health risk of the target premature infant is increased. Therefore, the present application can timely discover the target premature infant's physical The health risk increases when the status is unstable (age in months is not greater than the age threshold); after each update operation is performed, personalized care recommendations for the target premature infant are generated based on the latest collected second data and the updated health risk level. Therefore, when the health risk of the target premature infant increases, the present application promptly gives personalized care recommendations, so that family caregivers can care for the target premature infant according to the personalized care recommendations, thereby realizing timely application of corresponding care measures when the health risk of the target premature infant increases; in summary, the present application solves the problem that regular follow-up examinations are used for health management of premature infants after discharge, which makes it impossible for medical staff to fully and timely understand the growth and development status of premature infants, and to timely discover the increase in health risks of premature infants, resulting in the inability to promptly give and apply corresponding care measures when the health risks of premature infants increase, thereby improving the care effect for premature infants after discharge.

[0071] In addition, existing follow-up and nursing services usually adopt a single model and fail to implement hierarchical management based on individual differences of premature infants and family care conditions, resulting in unsatisfactory nursing results. The post-hospital health management method for premature infants in the embodiment of the present application implements a hierarchical management model for target premature infants based on the health risk level of premature infants after discharge, combined with a dynamic adjustment mechanism and a parent support system, to provide scientific, systematic and continuous health management for premature infants after discharge.

[0072] Optionally, in other embodiments of the present application, the personalized care recommendations include at least one of disease prevention recommendations, nutrition management recommendations, developmental training recommendations, second data collection frequency recommendations, and medication use plan recommendations.

[0073] In the embodiments of the present application, disease prevention recommendations include recommendations for the prevention of complications of target premature infants, and may also include recommendations for the prevention of diseases that are easily contracted by the target premature infants in their age group. Nutritional management recommendations include recommendations on milk volume, feeding duration, feeding frequency, addition of breast milk fortifiers, formula milk, complementary food additions, and trace element supplementation. Developmental training recommendations refer to training recommendations for neuromotor ability, perception and sensory ability, cognitive development, language and communication ability, emotional and social ability, reflexes and neurological functions, etc. The medication use plan recommendation is arranged according to the medical advice given by the medical staff during the most recent follow-up visit to the hospital.

[0074] In another exemplary embodiment of the present application, the above step 201 includes:

[0075] If the target premature infant meets the following conditions: the gestational age at birth is less than the first gestational age threshold, the birth weight is less than the first weight threshold, the percentile of any growth indicator at discharge is less than the first percentile threshold, and any one of the first category complications is present after birth, then the health risk level of the target premature infant will be classified as the fifth level, and the health risk level of the target premature infant will be five.

[0076] In the embodiments of the present application, the percentiles of growth indicators are the percentiles of height, weight and head circumference in the growth curve of the target premature infant at the time of discharge. The percentiles of height, weight and head circumference are the percentiles of the target premature infants in height, weight and head circumference in the same age and gender groups within a set range (such as the national range). The first category of complications refers to critical complications, including respiratory distress after birth, the need for mechanical ventilation and ventilation time of not less than two weeks, severe neonatal asphyxia (Apgar score 0-3), intracerebral hemorrhage (IVH is grade IV), receiving ROP (Retinopathy of Prematurity) treatment, undergoing surgery in the neonatal period (such as NEC (Necrotizing Enterocolitis) surgery, PDA (Patent Ductus Arteriosus) closure surgery, etc.), or the need for non-invasive ventilator-assisted breathing or oxygen inhalation (FiO2 ≥ 30%) at the time of discharge. If the target premature infant suffers from any of the above critical complications, the health risk level of the target premature infant will be classified as level five.

[0077] The first gestational age threshold, the first weight threshold, and the first percentile threshold are not specifically limited in this embodiment of the application and can be set according to actual needs. For example, the first gestational age threshold is set to 28 weeks, the first weight threshold is set to 1000g (grams), and the first percentile threshold is set to 3%.

[0078] If the target premature infant meets the following conditions: gestational age at birth is less than the second gestational age threshold but not less than the first gestational age threshold, birth weight is less than the second weight threshold but not less than the first weight threshold, the percentile of any growth indicator at discharge is not less than the first percentile threshold but less than the second percentile threshold, and any of the second type of complications is present after birth, the target premature infant will be classified as the fourth level, and the target premature infant's health risk level will be four.

[0079] In the embodiments of the present application, the second type of complications refers to more serious but controllable complications, including respiratory distress after birth, the need for mechanical ventilation and ventilation time of 1-2 weeks, moderate intraventricular hemorrhage (IVH is grade III), or the need for oxygen inhalation (21%≤FiO2<30%) upon discharge.

[0080] The second gestational age threshold, the second weight threshold, and the second percentile threshold are not specifically limited in this embodiment of the application and can be set according to actual needs. For example, the second gestational age threshold is set to 32 weeks, the second weight threshold is set to 1500g (grams), and the second percentile threshold is set to 10%.

[0081] If the target premature infant meets the following conditions: gestational age at birth is less than the third gestational age threshold and not less than the second gestational age threshold, birth weight is less than the third weight threshold and not less than the second weight threshold, the percentile of any growth indicator at discharge is not less than the second percentile threshold and less than the third percentile threshold, and any one of the third category complications is present after birth, then the target premature infant will be classified as the third level, and the target premature infant's health risk level will be three.

[0082] In the embodiments of the present application, the third category of complications refers to complications that are mild but still require continuous observation, including respiratory distress after birth, the need for mechanical ventilation and the ventilation time does not exceed 1 week, or mild intraventricular hemorrhage (IVH is grade I-II).

[0083] The third gestational age threshold, third weight threshold, and third percentile threshold are not specifically limited in this embodiment of the application and can be set according to actual needs. For example, the second gestational age threshold is set to 34 weeks, the second weight threshold is set to 2000g (grams), and the third percentile threshold is set to 30%.

[0084] If the target premature infant meets the following conditions: gestational age is less than 37 weeks and not less than the third gestational age threshold, birth weight is not less than the third weight threshold, the percentile of any growth indicator at discharge is not less than the third percentile threshold and less than the fourth percentile threshold, and the health condition is normal and there are no complications, then the target premature infant will be classified into the second level, and the health risk level of the target premature infant will be two.

[0085] The fourth weight threshold and the fourth percentile threshold are not specifically limited in the present embodiment and can be set according to actual needs. For example, the fourth percentile threshold is set to 90%.

[0086] If the target premature infant meets the conditions of having a special medical history after birth, or if the percentile of either weight or head circumference at discharge is not less than the fourth percentile threshold, the target premature infant will be classified into the first level, and the health risk level of the target premature infant will be one.

[0087] In the embodiments of the present application, special medical history includes but is not limited to congenital nervous system diseases, congenital metabolic diseases, etc.

[0088] Optionally, in the embodiments of the present application, different colors are used to represent different health risk levels, so that the real-time health risk level of the target premature infant can be viewed more intuitively. For example, red represents level 5, orange represents level 4, yellow represents level 3, green represents level 2, and blue represents level 1.

[0089] Optionally, in other embodiments of the present application, the above step 202 includes the following steps 301 to 302. Among them:

[0090] Step 301 , preprocessing the newly collected second data and historical health data of the target premature infant to obtain third data; wherein the historical health data includes the first data and the historical second data, and the preprocessing includes data cleaning and data standardization.

[0091] In the embodiment of the present application, the historical second data is the historical second data. Data cleaning includes missing value processing and outlier processing. Missing value processing includes filling missing values in the newly collected second data and historical health data of the target premature infant. Outlier processing includes performing abnormal data detection on the newly collected second data and historical health data of the target premature infant, and eliminating or correcting the detected abnormal data. Data normalization is to uniformly convert the newly collected second data and historical health data of the target premature infant into a fixed range, usually to [0,1].

[0092] Step 302: Input the third data into the constructed risk prediction model. The risk prediction model predicts and outputs the health risk level based on the third data to obtain an updated health risk level of the target premature infant.

[0093] Optionally, in an embodiment of the present application, the mean interpolation method and the Lagrange interpolation method are used to fill missing values in different data of the newly collected second data of the target premature infant and the historical health data.

[0094] In the embodiment of the present application, the mean interpolation method is used when the data distribution is relatively stable and there are relatively few missing data. The process of using the mean interpolation method to fill the missing values of the newly collected second data and historical health data of the target premature infant includes:

[0095] For each data feature containing missing values, calculate the mean of the data feature and use the calculated mean to fill the missing value position of the data feature.

[0096] For example, if breastfeeding frequency contains missing values, that is, there is no breastfeeding frequency on a certain day, the mean breastfeeding frequency of one day in the remaining days is calculated, and the calculated mean breastfeeding frequency is used to fill the missing breastfeeding frequency on that day.

[0097] Lagrangian interpolation is used to process temporal or sequential data, such as infant vital sign monitoring data and behavioral performance data. The process of using Lagrangian interpolation to fill missing values in the newly collected secondary data and historical health data of the target premature infant includes:

[0098] First, a data series with missing values (for example, a baby's body temperature data or feeding frequency) is selected. Based on the existing data points in the data series, a Lagrange interpolation polynomial is constructed. The missing values of the data series are estimated using the Lagrange interpolation polynomial.

[0099] For example, the target premature infant may have missing feeding amounts on one or some days, and the Lagrange interpolation can be used to infer the feeding amounts on one or some days.

[0100] For complication data, missing values were not filled in, and they were marked as missing or deleted, which could better ensure the authenticity of the data and the accuracy of the analysis.

[0101] Optionally, in an embodiment of the present application, abnormal data detection is performed on the newly collected second data and historical health data of the target premature infant using a Z-score or IQR method.

[0102] In the examples of this application, the Z-score method is used for numerical data, especially when the data is normally distributed or close to normally distributed. The IQR method is used when the data does not follow a normal distribution.

[0103] The process of detecting abnormal data using the Z-score on the newly collected second data and historical health data of the target premature infant includes:

[0104] Calculate the mean and standard deviation: For each data feature (e.g., feeding amount in home care data, crying frequency in behavioral performance data, etc.), calculate its mean and standard deviation;

[0105] Calculate the Z-score: For each data of each data feature, calculate its Z-score;

[0106] Determine the outlier threshold: If the |Z-score| of a data is greater than the set Z-score threshold, it means that the data is an outlier.

[0107] For example, the Z-score threshold is set to 3. If the Z-score of a data is greater than 3 or less than -3, it means that the data is an outlier, which means that the data deviates from the mean by more than 3 times the standard deviation and can be considered abnormal.

[0108] The process of detecting abnormal data using the IQR method on the newly collected second data and historical health data of the target premature infant includes:

[0109] Calculate quartiles: For each characteristic (e.g., complication monitoring data, behavioral performance data, etc.), calculate Q1 (25% quantile) and Q3 (75% quantile);

[0110] Calculate IQR: Calculate IQR by IQR = Q3 - Q1;

[0111] Determine the outlier threshold: Calculate the upper and lower bounds of the outlier based on the IQR:

[0112] Upper bound = Q3 + 1.5 × IQR;

[0113] Lower bound = Q1 - 1.5 × IQR;

[0114] Identifying outliers: Data outside the upper and lower bounds of outliers are considered outliers.

[0115] After the detection identifies outliers, you can choose to remove them or fill them with reasonable values.

[0116] For complication data, manual processing of outliers was used.

[0117] Optionally, in an embodiment of the present application, when performing data standardization on the newly collected second data and historical health data of the target premature infant, One-Hot encoding is used for standardization of categorical data (such as "whether there is respiratory distress", "whether there is jaundice", etc.), and the categorical data is converted into binary (0 or 1) variables, thereby realizing numerical conversion.

[0118] For numerical data (such as weight, body temperature, feeding amount, etc.) and frequency data (such as the number of times the baby cries, feeding frequency, etc.), the Z-score standardization method is used to calculate the mean and standard deviation, and the data is converted into a standardized value with a mean of 0 and a standard deviation of 1.

[0119] Depending on the specific distribution characteristics of the data, Min-Max standardization, logarithmic standardization, and quantile standardization methods are also used.

[0120] Optionally, in an embodiment of the present application, the above-mentioned risk prediction model adopts a radial basis function (RBF) network model, including an input layer, a hidden layer and an output layer, the input layer is used to input the third data, the hidden layer includes several nodes that use the radial basis function as the activation function, and the output layer is used to generate an updated health risk level by linearly combining the output of the hidden layer.

[0121] In the embodiment of the present application, the output layer can use the Softmax function to convert the score of each health risk level into a probability, obtain the probability of each health risk level, and use the health risk level with the highest probability as the updated health risk level. The formula of the Softmax function is:

[0122]

[0123] Among them, x i is the i-th element of the input vector of the Softmax function, is the jth element of the input vector of the Softmax function, n is the total number of elements of the input vector of the Softmax function, Softmax(x i ) is x i The probability value of

[0124] During the risk estimation model training process, the loss function can use the mean square error function, and the gradient descent method (such as Adam) can be used to update the model parameters.

[0125] Optionally, in an embodiment of the present application, the above step 203 includes the following steps 401 to 402. Among them:

[0126] Step 401: Retrieve relevant nursing measures from a constructed knowledge base based on the newly collected second data of the target premature infant and the updated health risk level; wherein the knowledge base stores medical guidelines, expert consensus and nursing standards for premature infants.

[0127] In the embodiments of the present application, the medical guidelines for premature infants include comprehensive premature infant care recommendations to promote the healthy growth of premature infants and reduce the risk of complications. The expert consensus on premature infants refers to a guiding document jointly developed by experts in pediatrics, neonatology and related fields based on the latest scientific research and clinical experience. The nursing standards for premature infants include the basic principles and recommendations for premature infant care. Relevant nursing measures refer to nursing measures that match / correspond to the second data and updated health risk level of the target premature infant.

[0128] In step 402, the input data is input into the target large language model, and the target large language model generates personalized care recommendations for the target premature infant based on the input data; wherein the input data includes the retrieved care measures and the second data, historical health data, and updated health risk level of the target premature infant.

[0129] In the embodiment of the present application, the target large language model is a large language model used to generate personalized nursing recommendations for the target premature infant. While inputting the second data, historical health data and updated health risk level of the target premature infant, the nursing measures retrieved from the knowledge base are input, and the target large language model can be guided by the nursing measures to generate personalized nursing recommendations for the target premature infant, thereby improving the accuracy of the personalized nursing recommendations generated by the target large language model. When constructing the target large language model, the Pytorch framework can be used, the database can be MySQL, Pandas and NumPy are used for data preprocessing, the cloud server hosts the model, supports real-time prediction, and uses RESTful API to integrate the model into the application.

[0130] Optionally, in other embodiments of the present application, if the input data includes images or multi-dimensional data, step 402 may use multimodality to generate personalized care recommendations with charts and images.

[0131] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0132] Based on user feedback and nursing effect evaluation, reinforcement learning is used to optimize the personalized nursing recommendations generated by the target large language model to recommend more effective nursing measures.

[0133] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0134] Feedback the first real-time data of the target premature infant to the parents, including real-time vital signs monitoring data, updated health risk level and personalized care recommendations.

[0135] In the embodiment of the present application, the real-time vital sign monitoring data is the vital sign monitoring data within a preset health risk level update period.

[0136] Optionally, in other embodiments of the present application, the above-mentioned first real-time data also includes reasons for changes in health risk levels and reasons for adjustments to personalized care recommendations.

[0137] In the embodiments of the present application, the reason for the change in health risk level refers to which indicators lead to the change in health risk level. The reason for the adjustment of personalized care advice refers to which indicators lead to the adjustment of personalized care advice.

[0138] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0139] Feedback the second real-time data of the target premature infant to the medical side, where the second real-time data includes the latest collected second data, personalized nursing suggestions, and the expected effects of the personalized nursing suggestions.

[0140] In the embodiment of the present application, if the personalized nursing recommendations output by the target large language model are optimized, the optimized personalized nursing recommendations are fed back to the medical and nursing end. The expected effect of the personalized nursing recommendations refers to the expected growth and development data of the target premature infant after the nursing measures in the real-time personalized nursing recommendations.

[0141] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0142] After each follow-up review, the health risk level of the target premature infant after follow-up was determined.

[0143] Optionally, in other embodiments of the present application, the above-mentioned determination of the health risk level of the target premature infant after follow-up includes the following steps 501 to 502. Among them:

[0144] Step 501, directly matching health risk level:

[0145] If the target premature infant meets the following conditions during follow-up: severe anemia, bone density T-score no greater than -2.5, and metabolic bone disease risk, and any growth indicator percentile is less than any of the first percentile thresholds, the matching health risk level is five.

[0146] In the embodiment of the present application, whether there is a risk of metabolic bone disease will be written in the case after follow-up. The embodiment of the present application only needs to determine whether "there is a risk of metabolic bone disease" is written in the case. If it is written, it is considered that the target child is at risk of metabolic bone disease during follow-up.

[0147] If the target premature infant meets any of the following conditions during follow-up: moderate anemia, the percentile of any growth indicator is not less than the first percentile threshold but less than the second percentile threshold, and the bone density T value is not greater than -2.5, the matching health risk level is four.

[0148] If the target premature infant meets any of the following conditions during follow-up: a bone density T-score greater than -2.5 but not greater than -1.0; mild intraventricular hemorrhage (IVH grade I-II) after birth and mild anemia during follow-up; the percentile of any growth indicator is not less than the second percentile threshold but less than the third percentile threshold; and the developmental quotient of the Child Heart Scale (developmental quotient in the Child Mental Development Scale) is less than 80, then the matching health risk level is three.

[0149] If the target premature infant meets the following conditions during follow-up: bone density T value greater than -1.0 but not greater than 1.0, normal health status, no complications, and the percentile of any growth indicator is not less than the third percentile threshold but less than the fourth percentile threshold, then the matching health risk level is two.

[0150] If the target preterm infant's percentile for either weight or head circumference at follow-up was greater than the fourth percentile threshold, the matched health risk level was one.

[0151] Step 502 : Select the larger of the matched health risk level and the health risk level most recently updated by the risk prediction model as the health risk level of the target premature infant after follow-up.

[0152] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0153] Get personalized care recommendations confirmed or modified by your healthcare provider.

[0154] In an embodiment of the present application, in order to further ensure the accuracy and effectiveness of personalized care recommendations, the generated or optimized personalized care recommendations can be fed back to the medical end, and the medical staff at the medical end can confirm or modify the fed-back personalized care recommendations.

[0155] Optionally, in other embodiments of the present application, the personalized care recommendations in the aforementioned second real-time data refer to personalized care recommendations confirmed or modified by medical staff.

[0156] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0157] Based on the latest collected second data of the target premature infant and the updated health risk level, a follow-up plan is generated and fed back to the parents.

[0158] In the embodiment of the present application, the follow-up plan includes the frequency and time of follow-up examinations of the target premature infants in the hospital.

[0159] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0160] Reminder information is generated according to the follow-up plan and fed back to the parents to remind them to follow up on schedule.

[0161] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0162] Monitor vital signs data that are outside the normal range and generate early warning information to feed back to medical staff.

[0163] In an embodiment of the present application, the early warning information includes monitoring data of vital signs that are outside the normal range, prompting medical staff that the health condition of the target premature infant may deteriorate.

[0164] Optionally, in other embodiments of the present application, the above-mentioned method for post-hospital health management of premature infants further includes:

[0165] Provide medical staff with feedback on the indicator development trend of target premature infants.

[0166] In the embodiments of the present application, the indicator development trend graph includes a trend graph of changes in vital signs over time, a trend graph of changes in various growth indicators over time, a trend graph of changes in various developmental indicators over time, a trend graph of changes in complication rate over time, a trend graph of changes in feeding amount and feeding frequency over time, a trend graph of changes in sleep time and crying frequency over time, and a trend graph of nursing effectiveness. The trend graph of changes in vital sign data over time can help medical staff observe changes in the target premature infant's vital sign monitoring data over a certain period of time and detect health abnormalities in advance. The trend graph of changes in various growth indicators over time shows the growth and development of the target premature infant at different time points. The trend graph of changes in various developmental indicators over time shows the changing trends of the target premature infant's developmental indicators at different periods of time, so that they can be compared with normal reference values. The trend graph of changes in feeding amount and feeding frequency over time shows changes in the target premature infant's feeding status over time, helping to evaluate whether the feeding plan is reasonable. The trend graph of changes in sleep time and crying frequency over time shows changes in behavioral observation indicators such as sleep quality and crying frequency of the target premature infant at different time periods, helping to evaluate the target premature infant's mood or health status.

[0167] Based on the same inventive concept, the embodiments of the present application also provide a premature infant post-hospital health management system for implementing the aforementioned premature infant post-hospital health management method. The implementation solution provided by this system is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations in one or more premature infant post-hospital health management system embodiments provided below can be found in the above-mentioned limitations on the premature infant post-hospital health management method, and will not be repeated here.

[0168] In an exemplary embodiment, Figure 3 As shown, a premature infant post-hospital health management system 60 is provided, comprising:

[0169] An initial grading module 601 is configured to perform an initial grading on the target premature infant based on the first data of the target premature infant, and obtain a health risk level of the target premature infant at an initial moment;

[0170] Database 602, for storing relevant data of the target premature infant; the relevant data includes first data and second data; the first data includes medical history, gestational age at birth, and birth weight; the second data includes at least one of vital sign monitoring data, growth and development data, and home care data;

[0171] The communication interface 603 is configured to obtain the first data of the target premature infant from the database 602 according to the instruction of the initial classification module 601;

[0172] Monitor 604, used to monitor the vital signs of the target premature infant and upload the data to database 602 for storage;

[0173] The first human-computer interaction interface 605 is used to receive growth and development data and / or home care data input by the user and upload them to the database 602 for storage via the communication interface 603;

[0174] The dynamic update module 606 is configured to execute the update operation cyclically until the age of the target premature infant reaches the age threshold. The update operation includes:

[0175] Obtaining the latest collected second data of the target premature infant; dynamically updating the health risk level of the target premature infant according to the latest collected second data according to a preset update cycle;

[0176] a suggestion generating module 607 for generating personalized nursing suggestions for the target premature infant based on the latest collected second data and the updated health risk level after each update operation is performed;

[0177] The first display terminal 608 is used to display the latest vital sign monitoring data collected by the monitor 604 , the health risk level updated by the dynamic update module 606 , and the personalized care recommendations generated by the recommendation generation module 607 .

[0178] Optionally, in other embodiments of the present application, the initial classification module 601 is further configured to:

[0179] Perform an initial classification of the target premature infant based on the first data of the target premature infant according to the following steps to obtain the health risk level of the target premature infant at the initial moment:

[0180] If the target premature infant meets the following conditions: the gestational age at birth is less than the first gestational age threshold, the birth weight is less than the first weight threshold, the percentile of any growth indicator at discharge is less than the first percentile threshold, and any one of the first category complications occurs after birth, then the health risk level of the target premature infant is classified as the fifth level, and the health risk level of the target premature infant is five;

[0181] If the target premature infant meets the following conditions: the gestational age at birth is less than the second gestational age threshold and not less than the first gestational age threshold, the birth weight is less than the second weight threshold and not less than the first weight threshold, the percentile of any growth indicator at discharge is not less than the first percentile threshold and less than the second percentile threshold, and any one of the second category complications is present after birth, then the target premature infant is classified into the fourth level, and the target premature infant's health risk level is four;

[0182] If the target premature infant meets the following conditions: the gestational age at birth is less than the third gestational age threshold and not less than the second gestational age threshold, the birth weight is less than the third weight threshold and not less than the second weight threshold, the percentile of any growth indicator at discharge is not less than the second percentile threshold and less than the third percentile threshold, and any one of the third category complications is present after birth, then the target premature infant is classified into the third level, and the health risk level of the target premature infant is three;

[0183] If the target premature infant meets the following conditions: the gestational age at birth is less than 37 weeks and not less than the third gestational age threshold, the birth weight is not less than the third weight threshold, the percentile of any growth indicator at discharge is not less than the third percentile threshold and less than the fourth percentile threshold, and the health status is normal and there are no complications, then the target premature infant is classified into the second level, and the health risk level of the target premature infant is obtained as two;

[0184] If the target premature infant meets the conditions of having a special medical history after birth, or if the percentile of either weight or head circumference at discharge is not less than the fourth percentile threshold, the target premature infant will be classified into the first level, and the health risk level of the target premature infant will be one.

[0185] In the embodiments of the present application, the relevant descriptions of the first type of complications, the second type of complications, the third type of complications and special medical history can be found in the records of the above method embodiments, which will not be repeated here.

[0186] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0187] Follow the steps below to dynamically update the health risk level of a target premature infant:

[0188] Preprocessing the newly collected second data and historical health data of the target premature infant to obtain third data; wherein the historical health data includes the first data and the historical second data, and the preprocessing includes data cleaning and data standardization;

[0189] The third data is input into the constructed risk prediction model, and the risk prediction model predicts and outputs the health risk level based on the third data to obtain an updated health risk level of the target premature infant.

[0190] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0191] Mean interpolation method and Lagrange interpolation method were used to fill missing values in different data of the newly collected second data and historical health data of target premature infants.

[0192] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0193] Abnormal data detection is performed on the newly collected second data and historical health data of the target premature infants using the Z-score or IQR method.

[0194] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0195] When standardizing the newly collected second data and historical health data of target premature infants, one-hot encoding is used for standardization of categorical data (such as "whether there is respiratory distress syndrome", "whether there is jaundice", etc.), converting categorical data into binary (0 or 1) variables to achieve numerical conversion.

[0196] For numerical data (such as weight, body temperature, feeding amount, etc.) and frequency data (such as the number of times the baby cries, feeding frequency, etc.), the Z-score standardization method is used to calculate the mean and standard deviation, and the data is converted into a standardized value with a mean of 0 and a standard deviation of 1.

[0197] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0198] The radial basis function (RBF) network model is used as the risk prediction model.

[0199] The radial basis function (RBF) network model includes an input layer, a hidden layer, and an output layer. The input layer is used to input third data. The hidden layer includes several nodes that use radial basis functions as activation functions. The output layer is used to generate an updated health risk level by linearly combining the outputs of the hidden layers. The output layer can use a softmax function to convert the score of each health risk level into a probability, obtaining the probability of each health risk level. The health risk level with the highest probability is used as the updated health risk level.

[0200] Optionally, in other embodiments of the present application, the suggestion generating module 607 is further configured to:

[0201] Retrieve relevant nursing measures from a constructed knowledge base based on the newly collected secondary data and updated health risk level of the target premature infant; the knowledge base stores medical guidelines, expert consensus, and nursing standards for premature infants;

[0202] The input data is input into the target large language model, and the target large language model generates personalized care recommendations for the target premature infant based on the input data; wherein the input data includes the retrieved care measures and the second data, historical health data and updated health risk level of the target premature infant.

[0203] Optionally, in other embodiments of the present application, if the input data includes images or multi-dimensional data, the suggestion generation module 607 is further configured to:

[0204] Use multimodality to generate personalized care recommendations with charts and images.

[0205] Optionally, in other embodiments of the present application, the above-mentioned premature infant post-hospital health management system further includes:

[0206] The suggestion optimization module 609 is used to use reinforcement learning to optimize the personalized nursing suggestions generated by the target large language model based on the user's effect feedback and nursing effect evaluation, so as to recommend nursing measures with better effects.

[0207] Optionally, in other embodiments of the present application, the above-mentioned premature infant post-hospital health management system further includes:

[0208] The second display terminal 6010 is used to display the second real-time data of the target premature infant, where the second real-time data includes the latest collected second data, personalized nursing suggestions, and expected effects of the personalized nursing suggestions.

[0209] Optionally, in other embodiments of the present application, the above-mentioned premature infant post-hospital health management system further includes:

[0210] The second human-computer interaction interface 6011 is used to receive the confirmed or modified personalized care suggestions input by the medical staff.

[0211] At this time, the personalized nursing suggestions in the above-mentioned first real-time data refer to the personalized nursing suggestions confirmed or modified by the medical staff.

[0212] Optionally, in other embodiments of the present application, the suggestion generating module 607 is further configured to:

[0213] A follow-up plan is generated based on the newly collected second data of the target premature infant and the updated health risk level, and is uploaded to the database 602 through the communication interface 603 for storage.

[0214] Accordingly, the first display terminal 608 is further configured to:

[0215] The follow-up plan generated by the suggestion generation module 607 is displayed.

[0216] Optionally, in other embodiments of the present application, the above-mentioned premature infant post-hospital health management system further includes:

[0217] The reminder module 6012 is used to generate reminder information for each follow-up review according to the follow-up plan to remind parents to follow up on schedule.

[0218] Accordingly, the first human-computer interaction interface 605 is further used to:

[0219] Receive the reminder information generated by the reminder module 6012.

[0220] Optionally, in other embodiments of the present application, the second human-computer interaction interface 6011 is further used to:

[0221] Receive the follow-up review data input by the medical staff and upload it to the database through the communication interface for storage.

[0222] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0223] After each follow-up review, the health risk level of the target premature infant after follow-up was determined.

[0224] Optionally, in other embodiments of the present application, the dynamic update module 606 is further configured to:

[0225] Follow these steps to determine the target premature infant's health risk level after follow-up:

[0226] Directly match health risk level:

[0227] If the target premature infant meets the following conditions during follow-up: severe anemia, bone density T-score no greater than -2.5, and metabolic bone disease risk, and any growth index percentile is less than any of the first percentile thresholds, the matching health risk level is five;

[0228] If the target premature infant meets any of the following conditions during follow-up: moderate anemia, percentile of any growth indicator is not less than the first percentile threshold but less than the second percentile threshold, and bone density T value is not greater than -2.5, the matching health risk level is four;

[0229] If the target premature infant meets any of the following conditions during follow-up: bone density T value greater than -2.5 but not greater than -1.0, mild intraventricular hemorrhage (IVH grade I-II) after birth and mild anemia during follow-up, the percentile of any growth index is not less than the second percentile threshold but less than the third percentile threshold, and the developmental quotient of the Child Heart Scale (developmental quotient in the Child Mental Development Scale) is less than 80, then the matching health risk level is three;

[0230] If the target premature infant meets the following conditions during follow-up: the bone density T value is greater than -1.0 but not greater than 1.0, the health status is normal and there are no complications, and the percentile of any growth indicator is not less than the third percentile threshold but less than the fourth percentile threshold, then the matching health risk level is two;

[0231] If the percentile of either weight or head circumference of the target preterm infant at follow-up was greater than the fourth percentile threshold, the matching resulted in a health risk level of one;

[0232] The larger of the matched health risk level and the health risk level most recently updated by the risk prediction model is selected as the health risk level of the target premature infant after follow-up.

[0233] Optionally, in other embodiments of the present application, the above-mentioned premature infant post-hospital health management system further includes:

[0234] The early warning module 6013 is used to monitor vital sign monitoring data that exceeds the normal range and generate early warning information.

[0235] Accordingly, the second human-computer interaction interface 6011 is further used to:

[0236] Receive the warning information generated by the warning module 6013.

[0237] Optionally, in other embodiments of the present application, the second human-computer interaction interface 6011 is further used to:

[0238] Receive indicator development trend charts for target premature infants.

[0239] In the embodiments of the present application, the relevant description of the indicator development trend graph is detailed in the description of the above method embodiments and will not be repeated here.

[0240] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for post-hospital health management of premature infants is implemented.

[0241] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0242] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0243] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0244] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0245] 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0246] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may 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 may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0247] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0248] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, 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.

[0249] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for post-hospital health management of premature infants, characterized in that: The post-hospital health management method for premature infants includes: performing an initial classification of the target premature infant based on first data of the target premature infant to obtain a health risk level of the target premature infant at an initial moment; wherein the first data includes the medical history, gestational age, and birth weight of the premature infant; The updating operation is executed cyclically until the age of the target premature infant reaches the age threshold; wherein the updating operation includes: Acquiring the latest collected second data of the target premature infant; wherein the second data includes at least one of vital sign monitoring data, growth and development data, and home care data; Dynamically updating the health risk level of the target premature infant according to a preset update cycle and based on the latest collected second data; After each execution of the updating operation, personalized care recommendations for the target premature infant are generated based on the most recently collected second data and the updated health risk level.

2. The method for post-hospital health management of premature infants according to claim 1, characterized in that: The performing an initial classification of the target premature infant according to the first data of the target premature infant specifically includes: If the target premature infant meets the following conditions: the gestational age at birth is less than the first gestational age threshold, the birth weight is less than the first weight threshold, the percentile of any growth indicator at discharge is less than the first percentile threshold, and any one of the first complications after birth, the target premature infant is classified into the fifth level, and the health risk level of the target premature infant is five; wherein the growth indicators include height, weight, and head circumference; If the target premature infant meets the following conditions: the gestational age at birth is less than the second gestational age threshold but not less than the first gestational age threshold, the birth weight is less than the second weight threshold but not less than the first weight threshold, the percentile of any growth indicator at discharge is not less than the first percentile threshold but less than the second percentile threshold, and any one of the second category complications is present after birth, then the target premature infant is classified into the fourth level, and the health risk level of the target premature infant is obtained as four; If the target premature infant meets the following conditions: the gestational age at birth is less than the third gestational age threshold and not less than the second gestational age threshold, the birth weight is less than the third weight threshold and not less than the second weight threshold, the percentile of any growth indicator at discharge is not less than the second percentile threshold and less than the third percentile threshold, and any one of the third category complications is present after birth, then the target premature infant is classified into the third level, and the health risk level of the target premature infant is obtained as three; If the target premature infant meets the following conditions: the gestational age at birth is less than 37 weeks and not less than the third gestational age threshold, the birth weight is not less than the third weight threshold, the percentile of any growth indicator at discharge is not less than the fourth percentile threshold, and the health condition is normal with no complications, then the target premature infant is classified into the second level, and the health risk level of the target premature infant is obtained as two; If the target premature infant meets the requirements of having a special medical history after birth, or if the percentile of either weight or head circumference at discharge is not less than the fourth percentile threshold, the target premature infant will be classified into the first level, and the health risk level of the target premature infant will be one.

3. The method for post-hospital health management of premature infants according to claim 1, characterized in that: The dynamically updating the health risk level of the target premature infant according to the latest collected second data of the target premature infant includes: Preprocessing the newly collected second data and historical health data of the target premature infant to obtain third data; wherein the historical health data includes the first data and the historical second data, and the preprocessing includes data cleaning and data standardization; The third data is input into the constructed risk prediction model, and the risk prediction model predicts and outputs the health risk level based on the third data to obtain an updated health risk level of the target premature infant.

4. The method for post-hospital health management of premature infants according to claim 1, characterized in that: Generating personalized care recommendations for the target premature infant based on the newly collected second data and the updated health risk level includes: Retrieving relevant nursing measures from a constructed knowledge base based on the newly collected second data of the target premature infant and the updated health risk level; wherein the knowledge base stores medical guidelines, expert consensus, and nursing standards for premature infants; The input data is input into a target large language model, and the target large language model generates personalized care recommendations for the target premature infant based on the input data; wherein the input data includes the retrieved care measures and the most recently collected second data, historical health data and updated health risk level of the target premature infant.

5. The method for post-hospital health management of premature infants according to claim 3, characterized in that: Also includes: After each follow-up review, the health risk level of the target premature infant after follow-up was determined.

6. The method for post-hospital health management of premature infants according to claim 5, characterized in that: Determining the health risk level of the target premature infant after follow-up includes: Directly match health risk level: If the target premature infant meets the following criteria during follow-up: severe anemia, a bone density T-score no greater than -2.5, and a risk of metabolic bone disease, and any growth indicator percentile is less than any of the first percentile thresholds, then the health risk level obtained by matching is five; wherein the growth indicators include height, weight, and head circumference; If the target premature infant meets any of the following conditions during follow-up: moderate anemia, the percentile of any growth indicator is not less than the first percentile threshold but less than the second percentile threshold, and the bone density T value is not greater than -2.5, then the matching health risk level is four. If the target premature infant meets any of the following conditions during follow-up: a bone density T-value greater than -2.5 but not greater than -1.0; mild intraventricular hemorrhage after birth and mild anemia during follow-up; the percentile of any growth indicator is not less than the second percentile threshold but less than the third percentile threshold; and the Child Heart Scale Developmental Quotient is less than 80, then the matching health risk level is three. If the target premature infant meets the following requirements during follow-up: the bone density T value is greater than -1.0 but not greater than 1.0, the health condition is normal and there are no complications, and the percentile of any growth indicator is not less than the third percentile threshold but less than the fourth percentile threshold, then the matching health risk level is two. If the percentile of either weight or head circumference of the target premature infant during follow-up is greater than the fourth percentile threshold, the matched health risk level is one; The larger of the health risk level obtained by matching and the health risk level most recently updated by the risk prediction model is selected as the health risk level of the target premature infant after follow-up.

7. A post-hospital health management system for premature infants, characterized in that: The premature infant post-hospital health management system includes: an initial grading module, configured to perform an initial grading on the target premature infant based on the first data of the target premature infant, and obtain a health risk level of the target premature infant at an initial moment; A database for storing relevant data of the target premature infant; the relevant data includes first data and second data; the first data includes medical history, gestational age at birth, and birth weight; the second data includes at least one of vital sign monitoring data, growth and development data, and home care data; a communication interface, configured to obtain the first data of the target premature infant from the database according to an instruction of the initial classification module; A monitor for monitoring the vital signs of the target premature infant and uploading the data to the database for storage; A first human-computer interaction interface is used to receive growth and development data and / or home care data input by a user, and upload the data to the database for storage via the communication interface; A dynamic update module is configured to cyclically execute an update operation until the age of the target premature infant reaches a threshold age; wherein the update operation includes: Acquiring the latest collected second data of the target premature infant; dynamically updating the health risk level of the target premature infant according to a preset update cycle and based on the latest collected second data; a recommendation generating module, configured to generate personalized care recommendations for the target premature infant based on the most recently collected second data and the updated health risk level after each execution of the updating operation; The first display terminal is used to display the latest vital sign monitoring data collected by the monitor, the health risk level updated by the dynamic update module, and the personalized care suggestions generated by the suggestion generation module.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for post-hospital health management of premature infants according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for post-hospital health management of premature infants according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for post-hospital health management of premature infants according to any one of claims 1 to 6 are implemented.

Images