Pre-eclampsia evolution prediction, method and system

Abstract

The present invention relates to a method of predicting a health condition of a subject, the method comprising: receiving at least one dynamic attribute data associated with the subject and at least one covariable associated with the subject, processing the at least one dynamic attribute data associated with the subject and the at least one covariable data associated with the subject, in one embodiment, the method includes generating a processing dataset associated with a subject, generating at least one health condition hypothesis based on the processing dataset associated with the subject, and predicting at least one health condition based on the at least one health condition hypothesis. The present invention also relates to a system for predicting a health condition of a subject, the system comprising: at least one processing component configured to receive at least one dynamic attribute data associated with the subject and to receive at least one covariable associated with the subject, processing the at least one piece of dynamic attribute data related to the subject and the at least one piece of covariant data related to the subject to generate a processed data set related to the subject; at least one analysis component configured to analyze the processed data set associated with the subject and to generate at least one health condition hypothesis based on the processed data set associated with the subject, where the system is configured to predict at least one health condition based on the at least one health condition hypothesis, and performing the method according to any one of the preceding claims.

Description

Technical Field

[0001] The present invention belongs to the field of predicting the medical condition of a subject, in particular the field of predicting the evolution and / or development of preeclampsia in a pregnant woman and its effects on the child. The object of the present invention is to provide a method and system for predicting the potential medical outcome of a pregnant woman and / or her child. More specifically, the present invention relates to a system and a method implemented in such a system, and the corresponding uses of the system. Background Art

[0002] Preeclampsia (PE) is a leading cause of short-term and long-term maternal and perinatal morbidity and mortality worldwide (Tanner, 2022), affecting approximately 5% of pregnant women (Mol, 2015). This has prompted a need for better technologies and new approaches to reduce the burden on patients. PE is characterized by the onset of new hypertension during pregnancy or the presence of pre-existing hypertension in the presence of at least one new manifestation of end-organ dysfunction that cannot be explained by causes other than PE.

[0003] PE is one of the most serious complications of pregnancy, posing a significant risk of morbidity and mortality for both mother and baby. PE is a complex disease that is challenging to diagnose because pregnant women often have preexisting conditions that overlap with PE, such as preexisting hypertension or impaired fetal development. In black women, PE affects up to 8% of pregnancies. Despite intensive research, it remains nearly impossible to adequately predict, treat, or prevent PE.

[0004] The effects of PE on the infant and mother persist for many years after pregnancy, as evidenced by fetal programming of adult disease and increased maternal risk of cardiovascular disease (Wellmann, 2014). It is critical to understand the three key pathological stages in the progression of PE: (i) placental hypoxia and oxidative stress, (ii) excessive release of anti-angiogenic and pro-inflammatory factors, and (iii) widespread systemic endothelial dysfunction and vasoconstriction (de Alwis, 2020).

[0005] Over the past few decades, various PE guidelines have evolved and represent state-of-the-art diagnostic methods and best practices for early detection of medical conditions, as recently reviewed by Scott et al. (Scott, 2022). Indeed, the noble goal of all research and subsequent clinical care is to identify PE when the mother and fetus are asymptomatic and prevent its progression to the symptomatic stage.

[0006] MacDonald et al. present an updated review of clinical tools and biomarkers for predicting PE (MacDonald, 2022). Peripheral blood biomarkers, soluble Fms-like tyrosine kinase-1 (sFlt1) and placental growth factor (PlGF), show good performance when used as “rule-out” tests (i.e., excluding subjects). However, the sensitivity for detecting affected subjects is low. The review points to several placental and cardiovascular system biomarkers that could improve diagnostic performance in the future.

[0007] Jhee et al. (Jhee, 2019) proposed a prediction model for late-onset PE using different prediction models (such as logistic regression, decision tree, naive Bayes classifier, support vector machine, etc.). The late-onset (i.e., after 34 weeks of gestation) was predicted for the dataset using maternal characteristics and laboratory parameters in the early second trimester. The detection rate reached 77.1%, and the study endpoint was defined as new-onset hypertension with significant proteinuria.

[0008] Maric et al. (Maric, 2020) proposed an approach that focuses on statistical analysis. The model uses all available clinical and laboratory data for model training and is able to include a large number of missing values. Doppler imaging was not included as a feature because its inclusion would make the validation process more difficult. This approach greatly improves the applicability of the method in different medical settings. Although the method was trained on an elastic net, its performance metrics did not reach a level sufficient for use in clinical settings. Summary of the invention

[0009] In view of the above, an object of the present invention is to overcome or at least alleviate the defects and deficiencies of the prior art. More specifically, an object of the present invention is to provide a method and a corresponding system for predicting a health condition of a subject, which has improved sensitivity and performance and is less prone to making an erroneous prediction of at least one health condition of the subject.

[0010] The present invention meets these objectives.

[0011] In a first aspect, the present invention relates to a method for predicting a health status of a subject, the method comprising: receiving at least one dynamic attribute data related to the subject, receiving at least one covariate data related to the subject, processing at least one dynamic attribute data related to the subject and at least one covariate data related to the subject to generate a processed data set related to the subject, generating at least one health status hypothesis based on the processed data set related to the subject, and predicting at least one health status based on at least one health status hypothesis.

[0012] In one embodiment, the step of predicting at least one health condition can be based on a computer-implemented dynamic model. At least one health condition hypothesis can include a correlation with at least one medical condition of the subject. It should be understood that the subject can be a female subject, such as a pregnant woman and / or a non-pregnant woman. It should be understood that the term "female" as a subject is intended to refer to a female subject of reproductive age and / or childbearing age. In addition, the subject can also be a fetus and / or a newborn. In one embodiment, the method can also include a dynamic behavior of predicting at least one health condition of the subject.

[0013] In a further embodiment, the method may include implementing at least one machine learning technique, wherein the method may include performing any of the foregoing steps using at least one machine learning technique.

[0014] At least one covariate associated with the subject may include at least one biomarker. The at least one biomarker may be associated with at least one medical condition, and the at least one biomarker may include at least one of the following: soluble Fms-like tyrosine kinase-1 (sFlt1); placental growth factor (PlGF); neurofilament (NfL); C-terminal portion of arginine vasopressin (Copeptin); albumin; liver transaminases; urea; hemoglobin; platelets; creatinine; albuminuria; proteinuria; estimated glomerular filtration rate (eGFR); creatinine clearance (CrCl); at least one additional renal function measurement; placental biomarkers, such as placental RNA, placental proteins; endothelial / cardiovascular biomarkers, such as endothelial RNA, endothelial proteins; or any combination thereof.

[0015] At least one subject-related covariate may include at least one mother-related covariate, the at least one mother-related covariate including at least one of the following: age; weight; height; body mass index (BMI); number of pregnancies; parity; number of fetuses in the current pregnancy; race; body temperature; heart rate; heart rate variability; respiratory rate; early rupture of membranes; white blood cells; history of preeclampsia (familial and maternal); comorbidities, such as gestational diabetes, obesity, cardiovascular / renal / kidney / thyroid diseases, autoimmune diseases, anemia, antiphospholipid syndrome, sexually transmitted diseases, headaches; smoking habits before and / or during pregnancy; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); uteroplacental perfusion parameters; Doppler measurements of the umbilical artery, middle cerebral artery, cerebroplacental ratio, uterine artery, fetal descending aorta, ductus venosus, umbilical vein, inferior vena cava, uterine artery pulsatility index; soft tissue parameters, such as arm volume fraction and thigh volume fraction; and at least one measurement of at least one biomarker.

[0016] At least one subject-related covariate may include at least one fetus-related covariate, the at least one fetus-related covariate including at least one of the following: sex; fetal weight during pregnancy; fetal biometric parameters, such as femur length, abdominal circumference, head circumference, mid-thigh circumference, and biparietal diameter; small for gestational age rate; gestational age; heart rate, heart rate variability; respiratory rate; uteroplacental perfusion parameters; and at least one measurement of at least one biomarker. Additionally or alternatively, at least one subject-related covariate may include at least one neonate-related covariate, the at least one neonate-related covariate including at least one of the following: sex; birth weight; weight; length; gestational age at birth; postnatal age; body temperature; heart rate; heart rate variability; respiratory rate; duration of breastfeeding; duration of exclusive breastfeeding; pH; respiratory assistance; oxygen requirement; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); Apgar score; at least one additional neonate biometric parameter; and at least one measurement of at least one biomarker. Additionally or alternatively, the at least one subject-related covariate may include at least one environmental covariate, the at least one environmental covariate comprising at least one of: country of residence, country of birth, date and time of birth, humidity conditions at birth, and ambient temperature at birth.

[0017] In one embodiment, the method may include generating at least one threshold, wherein the at least one threshold represents an indication of at least one potential medical condition. In another embodiment, the method may include outputting at least one potential medical condition, wherein the at least one potential medical condition may include at least one of the following: seizures; respiratory, cardiovascular, hematological dysfunction; endocrine, renal, hepatic, placental dysfunction; fetal growth restriction; unexpected premature birth; placental abruption; elevated hemolytic liver enzymes, low platelets (HELLP) syndrome; and eclampsia. It should be understood that PE may lead to multiple organ involvement, namely seizures, respiratory, cardiovascular, hematological dysfunction, endocrine, renal, hepatic and placental dysfunction including the central nervous system (CNS). In addition, complications of PE may include, but are not limited to: fetal growth restriction because PE affects the arteries that carry blood to the placenta; premature birth. In addition, PE may lead to unexpected premature birth, i.e., delivery before 37 weeks of pregnancy. Therefore, it is noted that the present invention is applicable to pregnancy-induced hypertension and gestational diabetes, and is related to maternal, fetal and neonatal complications of these medical conditions in pregnant women.

[0018] In another embodiment, the method may include determining a minimum threshold of at least one threshold value, and determining a maximum threshold of at least one threshold value. In addition, when at least one data associated with the subject may be below the minimum threshold value, the method may include outputting a monitoring recommendation. When at least one data associated with the subject may be above the maximum threshold value, the method may include outputting a treatment recommendation. In addition, the method may include determining a baseline for at least one data associated with the subject. Additionally or alternatively, the method may include determining at least one intermediate threshold value, wherein the at least one intermediate threshold value may include at least one value between the minimum threshold value and the maximum threshold value.

[0019] In one embodiment, the method may include associating at least one range of at least one intermediate threshold value with at least one medical condition, generating an interpreted data set based on the associating step, and outputting an automated report indicating at least one potential medical condition. In another embodiment, the method may include determining at least one medical condition change indicator, monitoring changes in at least one medical condition change indicator, generating a trend of at least one medical condition change indicator, and predicting the evolution of at least one medical condition, wherein the prediction may be based on the trend of at least one medical condition change indicator. In addition, the method may include monitoring at least one value change of at least one attribute associated with the subject, the method including recording an initial value of at least one attribute associated with the subject, recording at least one subsequent value of at least one attribute associated with the subject, comparing the initial value with at least one of the at least one subsequent value, generating comparative value data, and outputting a hypothesis of the attribute associated with the subject based on the comparative value data. The step of recording at least one subsequent value may include recording a current value of at least one attribute associated with the subject, wherein the current value may be different from the initial value.

[0020] In one embodiment, the method may be a non-diagnostic method. In another embodiment, the method may be a diagnostic method.

[0021] The method may also include performing the method steps described herein using data from at least one database. The at least one database may include at least one of the following: a public health database, a personal database of subjects, a database of medical professionals, a database of healthcare providers, and a private database. Additionally or alternatively, the method may include feeding data to at least one server, training a computer-implemented dynamic model based on the data fed to the at least one server, and generating an adjustment function based on the training data, wherein the adjustment function may be applicable to adjust any step of the method according to any of the foregoing method embodiments.

[0022] In one embodiment, the method may include triggering at least one action suggestion based on at least one health condition hypothesis. Additionally or alternatively, the method may include displaying at least one action suggestion to a user. In another embodiment, the method may include prompting a user to enter at least one of the following: acceptance of at least one action suggestion, and rejection of at least one action suggestion. The user may reject at least one action suggestion, and the method may include prompting the user to provide at least one annotation. The computer-implemented dynamic model may be based on: Bayesian statistical methods; artificial neural network (ANN) methods; convolutional neural network (CNN) methods; recurrent neural network (RNN) methods; quantitative pharmacology (PMX) modeling and / or simulation methods; supervised learning methods; deep learning (DL) methods, multi-layer neural network methods and / or explainable AI (XAI) concepts.

[0023] The at least one medical condition may include at least one of: a fetal growth-related condition; a PE-related condition; a gestational diabetes-related condition; a gestational hypertension-related condition; a medical treatment during pregnancy, such as a cyclooxygenase inhibitor, such as aspirin; at least one related medication; and at least one underlying medical condition.

[0024] In addition, the method may include associating at least one biomarker with at least one medical condition, wherein the at least one medical condition may include a potential disease. The method may also include predicting the occurrence of at least one hypothesis within a given time period, wherein the method may also include identifying a plurality of different time periods, the plurality of different time periods including at least one of the following: prenatal period; pregnancy period; delivery period and postpartum period. In one embodiment, the method may include outputting the likelihood of occurrence associated with each time period. In addition, the method may include executing at least one machine learning (ML) algorithm. At least one ML algorithm may include a supervised algorithm architecture, an unsupervised algorithm architecture, or any combination thereof. Additionally or alternatively, at least one ML algorithm may include at least one artificial deep learning (DL) architecture, wherein at least one artificial DL architecture may include at least one of the following: ANN, CNN, and RNN. The unsupervised algorithm architecture may include at least one clustering method that implements at least one clustering. In addition, at least one analysis method may include at least one of the following: pattern recognition, probabilistic modeling, Bayesian scheme, reinforcement learning, statistical analysis, statistical model, principal component analysis (PCA), independent component analysis, dynamic time warping, maximum likelihood estimation (MLE), modeling, estimation, neural network (NN), CNN, RNN, deep convolutional network, DL, ultra-deep learning, genetic algorithm, Markov model and / or hidden Markov model.

[0025] In another embodiment, the method may include implementing at least one quantitative pharmacology (PMX) model. At least one PMX model may include a computer-implemented PMX model that includes at least one of: a mathematical-statistical pharmacokinetic-pharmacodynamic (PK-PD) model; a physiologically based PK (PBPK) model; a physiologically based PK-PD (PBPKPD) model; a drug exposure-efficacy response model; and a drug exposure-safety response model.

[0026] At least one health condition of the subject may include: PE, gestational diabetes, a fetal growth-related condition, and / or a gestational hypertension-related condition. In one embodiment, the step of predicting at least one health condition based on at least one health condition hypothesis may include using at least one fetal growth-related data. In another embodiment, the step of predicting at least one health condition may include using at least one fetal growth-related data, wherein at least one health condition hypothesis may be based on at least one fetal growth-related data. The at least one fetal growth-related data may be retrieved from at least one database. In another embodiment, the step of predicting at least one health condition may include using at least one PE-related data, wherein at least one health condition hypothesis may be based on at least one PE-related data. The at least one PE-related data may be retrieved from at least one database.

[0027] In addition, the method may include determining at least one drug based on at least one health condition, wherein the at least one drug may be suitable for preventing the occurrence and / or recurrence of at least one medical condition and / or at least one health condition. The method may include determining at least one drug based on at least one health condition, wherein the at least one drug may be suitable for treating at least one medical condition and / or at least one health condition. The at least one drug includes at least one of the following: aspirin; ibuprofen; at least one corticosteroid drug; at least one antihypertensive drug; and at least one cardiovascular-related drug. In addition, the method may include generating at least one drug administration route, wherein the at least one drug administration route may include at least one of the following: intravenous injection; intramuscular injection; subcutaneous; inhalation; transdermal; percutaneous; oral; rectal; and sublingual. The method may include generating at least one dosing regimen for at least one drug. Additionally or alternatively, the method may also include optimizing at least one dosing regimen, wherein the at least one dosing regimen may include at least one of the following: at least one drug; at least one drug administration route; at least one dosage regimen; at least one drug administration duration; and at least one drug administration frequency. The step of optimizing at least one dosing regimen may be based on at least one health condition assumption. The method may also include implementing at least one optimal control theory, wherein at least one optimal control theory is implemented by a computer. It should be understood that the method described herein is a computer-implemented method. The method may include optimizing at least one ongoing treatment for at least one medical condition. The method may include optimizing at least one ongoing treatment for at least one underlying medical condition. The optimizing step may be based on at least one health condition hypothesis and / or at least one health condition. The method may include generating at least one treatment recommendation, wherein the at least one treatment recommendation may be based on at least one health condition hypothesis and / or at least one health condition. The method may include optimizing the at least one treatment recommendation, wherein the method may include performing the optimizing step after performing the at least one treatment recommendation.

[0028] In one embodiment, the method may include adapting any of the foregoing method embodiments to a subject and generating at least one personalized treatment regimen, wherein the at least one personalized treatment regimen may be based on at least one health condition of the subject. The method may include optimizing at least one personalized treatment regimen, wherein the method may include performing an optimization step after executing at least one personalized treatment regimen. In addition, the method may include implementing any of the foregoing optimization steps with the help of a computer-implemented quantitative pharmacology method. The method may include performing the method described herein in the absence of the subject. In addition, the method may include performing the method described herein using at least one historical data. The at least one historical data may be historical data of the subject. The at least one historical data may include at least one of the following: a public health database, a personal database of the subject, a database of a medical professional, a database of a healthcare provider, and a private database.

[0029] In another embodiment, the method may include at least one of the following: capturing at least one image data of a subject; and receiving at least one image data of a subject, wherein the at least one image data may include data related to at least one medical condition and / or at least one potential medical condition of the subject. In addition, the method is suitable for implementation in at least one medical device (e.g., an ultrasound device).

[0030] In a second aspect, the present invention relates to a system for predicting a health status of a subject, the system comprising: at least one processing component, which is configured to receive at least one dynamic attribute data related to the subject and at least one covariate related to the subject, and process at least one dynamic attribute data related to the subject and at least one covariate data related to the subject to generate a processed data set related to the subject; at least one analysis component, which is configured to analyze the processed data set related to the subject and generate at least one health status hypothesis based on the processed data set related to the subject, wherein the system is configured to predict at least one health status based on the at least one health status hypothesis.

[0031] In addition, the system may include at least one storage component configured to store data related to at least one health condition of the subject. The system may also include at least one computing component configured to implement a dynamic model for predicting at least one health condition. The at least one health condition hypothesis may include a correlation with at least one medical condition of the subject.

[0032] The subject may be: a newborn, a fetus, and / or a female, wherein the female may be at least one of the following: a pregnant woman, a non-pregnant woman.

[0033] The system can be configured to predict the dynamic behavior of at least one health condition of the subject.The system can be configured to perform any steps according to any of the foregoing method embodiments by at least one machine learning technique.

[0034] At least one covariate associated with the subject may include at least one biomarker. The at least one biomarker may be associated with at least one medical condition, and the at least one biomarker may include at least one of the following: soluble Fms-like tyrosine kinase-1 (sFlt1); placental growth factor (PlGF); neurofilament (NfL); C-terminal portion of arginine vasopressin (Copeptin); albumin; liver transaminases; urea; hemoglobin; platelets; creatinine; albuminuria; proteinuria; estimated glomerular filtration rate (eGFR); creatinine clearance (CrCl); at least one additional renal function measurement; placental biomarkers, such as placental RNA, placental proteins; endothelial / cardiovascular biomarkers, such as endothelial RNA, endothelial proteins; or any combination thereof.

[0035] At least one covariate associated with the subject may include at least one covariate associated with the newborn, the at least one covariate associated with the newborn including at least one of the following: sex; race; weight; birth weight; gestational age; mode of delivery, such as vaginal delivery, vacuum extraction, cesarean section; body temperature; heart rate; respiratory rate; pH; umbilical cord pH; respiratory assistance; oxygen demand; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); Apgar score; and at least one measurement of at least one biomarker. In addition, at least one covariate associated with the subject may include at least one covariate associated with the mother, the at least one covariate associated with the mother including at least one of the following: age; race; early rupture of membranes; body temperature; risk factors, such as diabetes, obesity, number of pregnancies, parity, white blood cells; and at least one measurement of at least one biomarker. Additionally or alternatively, at least one subject-related covariate may include at least one fetus-related covariate, the at least one fetus-related covariate including at least one of the following: sex; fetal weight during pregnancy; fetal biometric parameters, such as femur length, abdominal circumference, head circumference, mid-thigh circumference, and biparietal diameter; small for gestational age rate; gestational age; heart rate, heart rate variability; respiratory rate; uteroplacental perfusion parameters; and at least one measurement of at least one biomarker. In addition, at least one subject-related covariate may include at least one environmental covariate, the at least one environmental covariate including at least one of the following: country of residence, country of birth, date and time of birth, humidity conditions at birth, and ambient temperature at birth.

[0036] The system may be configured to generate at least one threshold value, wherein the at least one threshold value represents an indication of at least one potential medical condition. The system may be configured to output at least one potential medical condition, wherein the at least one potential medical condition may include at least one of the following: epileptic seizure; respiratory, cardiovascular, hematological dysfunction; endocrine, renal, hepatic, placental dysfunction; fetal growth restriction; unexpected premature birth; placental abruption; elevated hemolytic liver enzymes, low platelets (HELLP) syndrome; and eclampsia. At least one analysis component may be configured to: determine a minimum threshold value of at least one threshold value, and determine a maximum threshold value of at least one threshold value. When at least one data related to the subject may be below the minimum threshold value, the at least one analysis component outputs a monitoring recommendation. When at least one data related to the subject may be above the maximum threshold value, the at least one analysis component outputs a treatment recommendation. At least one analysis component may be configured to determine a baseline for at least one data related to the subject. At least one analysis component may be configured to determine at least one intermediate threshold value, wherein at least one intermediate threshold value may include at least one value between the minimum threshold value and the maximum threshold value. At least one analysis component may be configured to: associate at least one range of at least one intermediate threshold value with at least one medical condition, generate an interpreted data set based on the association step, and output an automated report indicating at least one potential medical condition. At least one analysis component may be configured to determine at least one indicator of a change in medical condition, monitor changes in at least one indicator of a change in medical condition, generate a trend for at least one indicator of a change in medical condition, and predict an evolution of at least one medical condition based on the trend for at least one indicator of a change in medical condition.

[0037] In another embodiment, the system may include at least one monitoring component configured to monitor at least one change in value of at least one attribute associated with the subject, wherein the at least one monitoring component may be further configured to record an initial value of at least one attribute associated with the subject, record at least one subsequent value of at least one attribute associated with the subject, compare the initial value with at least one of the at least one subsequent value, generate comparative value data, and output a hypothesis of the attribute associated with the subject based on the comparative value data. The at least one monitoring component may be configured to record a current value of at least one attribute associated with the subject, wherein the current value may be different from the initial value. The system may be a non-diagnostic system. In another embodiment, the system may be a diagnostic system.

[0038] The system can be configured to use data from at least one database to perform the method steps according to any of the foregoing method embodiments. The at least one database can include at least one of the following: a public health database, a personal database of a subject, a database of a medical professional, a database of a healthcare provider, and a private database. In addition, the system can be configured to feed data to at least one server, train a dynamic model implemented by a computer based on the data fed to the at least one server, and generate an adjustment function based on the training data, wherein the adjustment function can be applicable to adjust any configuration of the system according to any of the foregoing system embodiments. The system can be configured to trigger at least one action suggestion based on at least one health condition hypothesis and / or at least one health condition. The system can be configured to display at least one action suggestion to a user.

[0039] In one embodiment, the system can be configured to prompt the user to input at least one of the following: acceptance of at least one action suggestion, and rejection of at least one action suggestion. When the user rejects at least one action suggestion, the system can be configured to prompt the user to provide at least one annotation. The dynamic model implemented by the computer can be based on: Bayesian statistical methods, artificial neural network (ANN) methods, convolutional neural network (CNN) methods, recurrent neural network (RNN) methods, quantitative pharmacology (PMX) methods, supervised learning methods, deep learning (DL) methods and / or multi-layer neural network methods, and / or explainable AI (XAI) concepts.

[0040] The at least one medical condition may include at least one of the following: fetal growth-related conditions; neonatal thyroid dysfunction; PE-related conditions; gestational diabetes-related conditions; pregnancy-induced hypertension-related conditions; and pregnancy-induced thyroid dysfunction. The system may be configured to associate at least one biomarker with at least one medical condition, wherein at least one medical condition may include an underlying disease. The system may also be configured to predict the occurrence of at least one hypothesis within a given time period, wherein the system may be configured to identify a plurality of different time periods, the plurality of different time periods including at least one of the following: prenatal period, pregnancy period, delivery period, and postnatal period. The system may be configured to output the likelihood of occurrence associated with each time period. In addition, the system may be configured to execute at least one machine learning (ML) algorithm, wherein at least one ML algorithm may include a supervised algorithm architecture, an unsupervised algorithm architecture, or any combination thereof. At least one ML algorithm may include at least one artificial deep learning (DL) architecture, wherein at least one artificial DL architecture may include at least one of the following: ANN, CNN, and RNN. The unsupervised algorithm architecture may be configured to implement at least one clustering method of at least one clustering.

[0041] In addition, the system can be configured to perform at least one analysis method, wherein the at least one analysis method can include at least one of the following: pattern recognition, probabilistic modeling, Bayesian scheme, reinforcement learning, statistical analysis, statistical model, principal component analysis (PCA), independent component analysis, dynamic time warping, maximum likelihood estimation (MLE), modeling, estimation, neural network (NN), convolutional neural network (CNN), recurrent neural network (RNN), deep convolutional network, deep learning (DL), ultra-deep learning, genetic algorithm, Markov model and / or hidden Markov model. The system can be configured to implement at least one quantitative pharmacology (PMX) model, and the at least one PMX model can include at least one of the following: mathematical-statistical pharmacokinetics-pharmacodynamics (PK-PD) model; physiologically based PK (PBPK) model; physiologically based PK-PD (PBPKPD) model; drug exposure-efficacy response model; and drug exposure-safety response model.

[0042] The system may be configured to predict at least one health condition based on at least one health condition hypothesis and use at least one fetal growth-related data. The system may be configured to use at least one fetal growth-related data to predict at least one health condition, wherein the at least one health condition hypothesis may be based on at least one fetal growth-related data. The at least one fetal growth-related data may be retrieved from at least one database. The system may be configured to predict at least one health condition, which may include using at least one PE-related data, wherein the at least one health condition hypothesis may be based on at least one PE-related data. The at least one PE-related data may be retrieved from at least one database.

[0043] The system may include at least one imaging component configured to perform at least one of the following operations: capture at least one image data of a subject and receive at least one image data of the subject, wherein the at least one image data may include data related to at least one medical condition and / or at least one underlying medical condition of the subject.

[0044] Furthermore, the system is configured to perform any of the method steps described herein.

[0045] The system may include at least one implementation component configured to connect the system to at least one medical device (e.g., an ultrasound device), wherein the system, once connected to the at least one medical device, is configured to perform any of the steps according to the methods described herein. The system may be configured to operate without the presence of a subject.

[0046] Furthermore, the method includes using the system described herein to perform any step of the method described herein.

[0047] In a third aspect, the invention relates to a method of treating a medical condition in a subject, wherein the method of treating comprises generating a treatment regimen, the treatment regimen comprising at least one therapeutic agent and a treatment regimen, wherein the treatment regimen is based on at least one health condition hypothesis. The at least one health condition hypothesis can be provided by the methods described herein. The at least one agent can be provided by the methods described herein. The at least one health condition of the subject can include: PE, gestational diabetes, and / or fetal growth problems.

[0048] Treatment may also include treating at least one underlying medical condition in the subject prior to the onset of the at least one medical condition.The subject may be at least one of: a pregnant woman, a non-pregnant woman, a fetus, and / or a newborn.

[0049] In a fourth aspect, the present invention relates to a diagnostic method for diagnosing a medical condition of a subject, wherein the diagnosis includes generating at least one diagnostic result, the diagnostic result including at least one medical condition of the subject, wherein the at least one diagnostic result is based on at least one health condition hypothesis. The diagnostic method may include generating at least one treatment method, wherein the at least one treatment method can be used to treat at least one medical condition of the subject. The diagnostic method may include generating at least one diagnostic result, wherein at least one diagnostic result may include at least one medical condition of the subject before the onset of the at least one medical condition. The diagnostic method includes at least one preventive treatment method, wherein at least one preventive treatment method can be used to treat at least one medical condition of the subject before the onset of the at least one medical condition. The at least one health condition hypothesis may be provided by a method according to any of the foregoing method embodiments.

[0050] The diagnostic method may include providing at least one drug, wherein the at least one drug may be provided by a method according to any of the foregoing method embodiments. The at least one health condition of the subject may include: PE, pregnancy-induced hypertension, gestational diabetes, and / or fetal growth problems. The subject may be at least one of: a pregnant woman, a non-pregnant woman, a fetus, and / or a newborn. The diagnostic method may include suggesting a treatment method according to any of the foregoing treatment method embodiments.

[0051] In a fifth aspect, the present invention relates to using a system as described herein to perform a method as described herein. The method may include the step of causing a system as described herein to perform a method as described herein. Using the method as described herein to implement a method of treatment as described herein. Using the method as described herein to implement a method of diagnosis as described herein. Using the method as described herein to implement a method of diagnosis as described herein and a method of treatment as described herein, wherein the diagnostic method is performed prior to the treatment method.

[0052] In short, the present invention relates to the prediction of diseases in the field of medicine in the perinatal period. More specifically, the method of the present invention is able to combine different components such as machine learning, data enhancement, artificial intelligence, dynamic quantitative pharmacology and quantitative pharmacology suitable for neonatology and obstetrics. In addition, the present invention can also use a variety of PE-related biomarkers in clinical studies (for example, in the past 15 years) to detect and monitor long-term stress factors in the mother, fetus and neonate. Since PE is a progressive multi-system disease, the present invention allows the detection of a variety of PE-related biomarkers, such as (i) cardiovascular markers detected at triage (Wellmann, 2014); (ii) biomarkers for detecting and monitoring subclinical dysfunction of maternal end organs (such as Copeptin in the renal system (Wellmann, 2014) and NfL in the central nervous system (Evers, 2018)); and (iii) biomarkers for diagnosing and monitoring fetal stress reactions (Burkhardt, 2012) and adverse neonatal outcomes (Letzner 2011, Depoorter 2018). This is particularly advantageous because the combined analysis of these biomarkers allows the present invention to predict the health status of a subject. It should be understood that the prediction of health status can include the current, future and / or past health status of the subject. That is, the present invention can predict the future health status of a subject before the onset of the disease, and can also predict the current health status of a subject before the onset of the disease. In summary, the present invention provides a comprehensive method that includes combining and utilizing multidimensional and longitudinal data, processing data with the assistance of computer-implemented methods, and utilizing computer-implemented models based on AI and PMX to personalize and optimize the prevention, diagnosis, management and treatment of PE. Another advantage of the present invention is that it can avoid complications associated with PE in subjects or groups of subjects, such as avoiding complications in mothers and their unborn and born children. Therefore, the present invention combines available multi-source inputs to improve the perinatal prevention, diagnosis and management of PE and its complications, wherein the methods of the present invention allow such combination to be performed without human intervention because the computer-implemented methods allow the use of sequential multi-source data to achieve: integrating data at all levels by optimizing the prevention, diagnosis and management of the disease, providing solutions that can reduce prenatal (i.e., mother and fetus) and postpartum (i.e., mother and newborn) morbidity, utilizing the concept of intelligent integration of multiple components (including clinical data, biomarkers, uteroplacental perfusion and fetal growth data, signal processing data, and longitudinal measurements), combining ML and other AI methods with pharmacological principles and innovative dynamic pharmacology computer models, and utilizing computer-implemented simulation methods of pharmacology to optimize and personalize drug delivery to maximize the efficacy / safety balance for mothers and their unborn and born children.This method is particularly advantageous because it provides a more accurate, effective and efficient method and corresponding system or method for predicting a health condition of a subject having improved sensitivity and performance and being less prone to making an erroneous prediction of at least one health condition of the subject.

[0053] The technology is also described by the following numbered embodiments.

[0054] The following will discuss method embodiments. These embodiments are represented by the letter abbreviation "M" and numbers. When the method embodiments are mentioned in this article, these embodiments are referred to.

[0055] M1. A method for predicting the health status of a subject, the method comprising:

[0056] receiving at least one dynamic attribute data associated with a subject,

[0057] receives at least one covariate associated with the subject,

[0058] processing at least one dynamic attribute data associated with the subject and at least one covariate data associated with the subject to generate a processed data set associated with the subject,

[0059] generating at least one health condition hypothesis based on the processed data set associated with the subject, and

[0060] At least one health condition is predicted based on the at least one health condition hypothesis.

[0061] M2. A method according to the preceding embodiment, wherein the step of predicting at least one health condition is based on a computer-implemented dynamic model.

[0062] M3. A method according to any of the preceding method embodiments, wherein at least one health condition hypothesis includes an association with at least one medical condition of the subject.

[0063] M4. A method according to any of the preceding method embodiments, wherein the subject is a female subject.

[0064] M5. The method according to the preceding embodiment, wherein the female subject is a pregnant woman.

[0065] M6. A method according to any one of the two preceding embodiments, wherein the female subjects include non-pregnant women.

[0066] M7. A method according to any of the preceding method embodiments, wherein the subject is a fetus.

[0067] M8. A method according to any of the preceding method embodiments, wherein the subject is a neonate.

[0068] M9. A method according to any of the preceding method embodiments, wherein the method further comprises predicting the dynamic behavior of at least one health condition of the subject.

[0069] M10. A method according to any of the preceding method embodiments, wherein the method includes implementing at least one machine learning technique, wherein the method includes using at least one machine learning technique to perform any of the preceding steps.

[0070] M11. A method according to any of the preceding method embodiments, wherein at least one subject-related covariate comprises at least one biomarker.

[0071] M12. The method according to the preceding embodiment, wherein at least one biomarker is associated with at least one medical condition.

[0072] M13. A method according to any one of the three preceding embodiments, wherein at least one biomarker includes at least one of the following: soluble Fms-like tyrosine kinase-1 (sFlt1); placental growth factor (PlGF); neurofilament (NfL); C-terminal portion of arginine vasopressin (Copeptin); albumin; liver transaminases; urea; hemoglobin; platelets; creatinine; albuminuria; proteinuria; estimated glomerular filtration rate (eGFR); creatinine clearance (CrCl); at least one additional renal function measurement; placental biomarkers, such as placental RNA, placental proteins; endothelial / cardiovascular biomarkers, such as endothelial RNA, endothelial proteins; or any combination thereof.

[0073] M14. A method according to any of the foregoing method embodiments and having the features of embodiments M4 to M6, wherein at least one subject-associated covariate includes at least one mother-associated covariate, and the at least one mother-associated covariate includes at least one of the following: age; weight; height; body mass index (BMI); number of pregnancies; parity; number of fetuses in the current pregnancy; race; body temperature; heart rate; heart rate variability; respiratory rate; early rupture of membranes; white blood cells; history of PE (family and maternal); comorbidities, such as gestational diabetes, obesity, cardiovascular / renal / kidney / thyroid diseases, autoimmune diseases, anemia, antiphospholipid syndrome, sexually transmitted diseases, headaches; smoking habits before and / or during pregnancy; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); uteroplacental perfusion parameters; Doppler measurements of the umbilical artery, middle cerebral artery, cerebroplacental ratio, uterine artery, fetal descending aorta, ductus venosus, umbilical vein, inferior vena cava, and uterine artery pulsatility index; soft tissue parameters, such as arm volume fraction and thigh volume fraction; and at least one measurement value of at least one biomarker.

[0074] M15. A method according to any of the foregoing method embodiments and having the features of embodiment M7, wherein at least one subject-related covariate includes at least one fetus-related covariate, and the at least one fetus-related covariate includes at least one of the following: gender; fetal weight during pregnancy; fetal biometric parameters, such as femur length, abdominal circumference, head circumference, mid-thigh circumference and biparietal diameter; the rate of small for gestational age infants; gestational age; heart rate, heart rate variability; respiratory rate; uteroplacental perfusion parameters; and at least one measurement value of at least one biomarker.

[0075] M16. A method according to any of the foregoing method embodiments and having the features of embodiment M8, wherein at least one subject-related covariate includes at least one neonate-related covariate, and the at least one neonate-related covariate includes at least one of the following: gender; birth weight; weight; height; gestational age at birth; postnatal age; body temperature; heart rate; heart rate variability; respiratory rate; breastfeeding; duration of exclusive breastfeeding; pH value; respiratory assistance; oxygen demand; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); Apgar score; at least one additional neonatal biometric parameter; and at least one measurement value of at least one biomarker.

[0076] M17. A method according to any of the preceding method embodiments, wherein at least one covariate associated with the subject includes at least one environmental covariate, wherein the at least one environmental covariate includes at least one of the following: country of residence, country of birth, date and time of birth, humidity conditions at birth, and ambient temperature at birth.

[0077] M18. A method according to any of the preceding method embodiments, wherein the method includes generating at least one threshold, wherein the at least one threshold represents an indication of at least one underlying medical condition.

[0078] M19. A method according to any of the preceding method embodiments, wherein the method may include outputting at least one potential medical condition, wherein the at least one potential medical condition includes at least one of the following: epileptic seizures; respiratory, cardiovascular, and blood dysfunction; endocrine, renal, hepatic, and placental dysfunction; fetal growth restriction; unexpected premature birth; placental abruption; elevated hepatolytic enzymes and low platelets (HELLP) syndrome; and eclampsia.

[0079] M20. A method according to any of the preceding method embodiments, wherein the method comprises:

[0080] determining a minimum threshold of at least one threshold, and

[0081] A maximum threshold value of at least one threshold value is determined.

[0082] M21. A method according to the preceding embodiment, wherein when at least one data related to the subject is below a minimum threshold, the method includes outputting a monitoring recommendation.

[0083] M22. A method according to any one of the two preceding embodiments, wherein when at least one data related to the subject is above a maximum threshold, the method includes outputting a treatment recommendation.

[0084] M23. A method according to any one of the three preceding embodiments, wherein the method comprises determining a baseline of at least one data associated with the subject.

[0085] M24. A method according to any one of the four preceding embodiments, wherein the method includes determining at least one intermediate threshold, wherein the at least one intermediate threshold includes at least one value between a minimum threshold and a maximum threshold.

[0086] M25. The method according to the preceding embodiment, wherein the method comprises:

[0087] associating at least one range of at least one intermediate threshold value with at least one medical condition,

[0088] Generate an interpreted dataset based on the association step, and

[0089] An automated report is outputted indicating at least one underlying medical condition.

[0090] M26. A method according to any of the preceding method embodiments, wherein the method comprises:

[0091] Identify at least one indicator of a change in medical condition,

[0092] monitoring a change in at least one indicator of a change in medical condition,

[0093] generating a trend for at least one indicator of change in medical condition, and

[0094] An evolution of at least one medical condition is predicted, wherein the prediction is based on a trend of at least one indicator of change in the medical condition.

[0095] M27. A method according to any of the preceding method embodiments, wherein the method comprises monitoring at least one change in value of at least one attribute associated with the subject, the method comprising:

[0096] record the initial value of at least one attribute associated with the subject,

[0097] recording at least one subsequent value of at least one attribute associated with the subject,

[0098] comparing the initial value to at least one of the at least one subsequent value,

[0099] Generate comparison value data, and

[0100] Output attribute hypotheses associated with the subject based on the comparison value data.

[0101] M28. A method according to the preceding embodiment, wherein the step of recording at least one subsequent value comprises recording a current value of at least one attribute associated with the subject, wherein the current value is different from the initial value.

[0102] M29. A method according to any of the preceding method embodiments, wherein the method is a non-diagnostic method.

[0103] M30. A method according to any of the preceding method embodiments, wherein the method is a diagnostic method.

[0104] M31. A method according to any of the preceding method embodiments, wherein the method includes using data from at least one database to perform the method steps described in any of the preceding method embodiments.

[0105] M32. A method according to the aforementioned embodiment, wherein at least one database comprises at least one of the following: a public health database, a personal database of a subject, a database of medical professionals, a database of healthcare providers, and a private database.

[0106] M33. A method according to any of the preceding method embodiments, wherein the method comprises:

[0107] Feed data to at least one server,

[0108] training a computer-implemented dynamic model based on data fed to at least one server, and

[0109] Generate an adjustment function based on the training data,

[0110] The adjustment function is suitable for adjusting any step of the method according to any of the aforementioned method embodiments.

[0111] M34. A method according to any of the preceding method embodiments, wherein the method includes triggering at least one action recommendation based on at least one health status hypothesis.

[0112] M35. A method according to the aforementioned embodiment, wherein the method includes displaying at least one action suggestion to the user.

[0113] M36. A method according to any one of the above two embodiments, wherein the method includes prompting the user to enter at least one of the following

[0114] acceptance of at least one proposed action, and

[0115] A rejection of at least one proposed action.

[0116] M37. A method according to the aforementioned embodiment, wherein when the user rejects at least one action suggestion, the method includes prompting the user to provide at least one annotation.

[0117] M38. A method according to any of the preceding method embodiments, wherein the dynamic model implemented by a computer is based on a Bayesian statistical method.

[0118] M39. A method according to any of the preceding method embodiments, wherein the dynamic model implemented by a computer is based on an ANN, CNN or RNN method.

[0119] M40. A method according to any of the preceding method embodiments, wherein the dynamic model implemented by a computer is based on quantitative pharmacological modeling and / or simulation methods.

[0120] M41. A method according to any of the preceding method embodiments, wherein the dynamic model implemented by a computer is based on a supervised learning method.

[0121] M42. A method according to any of the preceding method embodiments, wherein the dynamic model implemented by a computer is based on deep learning and / or multi-layer neural network methods.

[0122] M43. A method according to any of the preceding method embodiments, wherein the dynamic model implemented by a computer is based on the concept of explainable AI (XAI).

[0123] M44. A method according to any of the preceding method embodiments, wherein at least one medical condition includes at least one of the following: a fetal growth-related condition; a PE-related condition; a gestational diabetes-related condition; a gestational hypertension-related condition; medical treatment during pregnancy, such as a cyclooxygenase inhibitor, such as aspirin; at least one related medication; and at least one underlying medical condition.

[0124] M45. A method according to any of the preceding method embodiments and having the features of embodiment M13, wherein the method comprises associating at least one biomarker with at least one medical condition, wherein the at least one medical condition comprises an underlying disease.

[0125] M46. A method according to any of the preceding method embodiments, wherein the method includes predicting the occurrence of at least one hypothesis within a given time period, wherein the method also includes identifying a plurality of different time periods, the plurality of different time periods including at least one of the following: prenatal period; pregnancy period; delivery period and postnatal period.

[0126] M47. A method according to the aforementioned embodiment, wherein the method includes outputting the probability of occurrence associated with each time period.

[0127] M48. A method according to any of the preceding method embodiments, wherein the method includes executing at least one machine learning algorithm.

[0128] M49. A method according to the above-mentioned embodiment, wherein at least one machine learning algorithm includes a supervised algorithm architecture, an unsupervised algorithm architecture, or any combination thereof.

[0129] M50. A method according to any of the preceding method embodiments, wherein at least one machine learning algorithm comprises at least one artificial deep learning (DL) architecture.

[0130] M51. A method according to the aforementioned embodiment, wherein at least one artificial deep learning architecture includes at least one of the following: ANN, CNN and RNN.

[0131] M52. A method according to any of the preceding method embodiments and having the features of embodiment M49, wherein the unsupervised algorithm architecture comprises at least one clustering method for implementing at least one clustering.

[0132] M53. A method according to any of the preceding method embodiments, wherein the method includes performing at least one analysis method, wherein the at least one analysis method includes at least one of the following: pattern recognition, probabilistic modeling, Bayesian scheme, reinforcement learning, statistical analysis, statistical model, principal component analysis, independent component analysis, dynamic time warping, maximum likelihood estimation, modeling, estimation, neural network, convolutional network, recurrent network, deep convolutional network, deep learning, ultra-deep learning, genetic algorithm, Markov model and / or hidden Markov model.

[0133] M54. A method according to any of the preceding method embodiments, wherein the method comprises implementing at least one quantitative pharmacology model.

[0134] M55. A method according to the above-mentioned embodiments, wherein at least one quantitative pharmacology model includes a computer-implemented quantitative pharmacology model, which includes at least one of the following: a mathematical-statistical PKPD model; a physiologically-based PK (PBPK) model; a physiologically-based PKPD (PBPKPD) model; a drug exposure-efficacy response model; and a drug exposure-safety response model.

[0135] M56. A method according to any of the preceding method embodiments, wherein at least one health condition of the subject includes PE.

[0136] M57. A method according to any of the preceding method embodiments, wherein at least one health condition of the subject includes gestational diabetes.

[0137] M58. A method according to any of the preceding method embodiments, wherein at least one health condition of the subject includes a fetal growth-related condition.

[0138] M59. A method according to any of the preceding method embodiments, wherein at least one health condition of the subject includes a condition related to pregnancy-induced hypertension.

[0139] M60. A method according to any of the preceding method embodiments, wherein the step of predicting at least one health condition based on at least one health condition hypothesis includes using at least one fetal growth-related data.

[0140] M61. A method according to any of the preceding method embodiments, wherein the step of predicting at least one health condition includes using at least one fetal growth-related data, wherein at least one health condition hypothesis is based on at least one fetal growth-related data.

[0141] M62. A method according to the preceding embodiments and having the features of embodiment M32, wherein at least one fetal growth-related data is retrieved from at least one database.

[0142] M63. A method according to any of the preceding method embodiments, wherein the step of predicting at least one health condition includes using at least one PE-related data, wherein at least one health condition hypothesis is based on at least one PE-related data.

[0143] M64. A method according to the preceding embodiment and having the features of embodiment M32, wherein at least one PE-related data is retrieved from at least one database.

[0144] M65. A method according to any of the preceding embodiments, wherein the method includes determining at least one drug based on at least one health condition, wherein the at least one drug is suitable for preventing the occurrence of at least one medical condition and / or at least one health condition.

[0145] M66. A method according to any of the preceding embodiments, wherein the method comprises determining at least one medication based on at least one health condition, wherein the at least one medication is suitable for treating at least one medical condition and / or at least one health condition.

[0146] M67. A system according to any one of the two preceding embodiments, wherein the at least one drug comprises at least one of the following: aspirin; ibuprofen; at least one corticosteroid drug; at least one antihypertensive drug; and at least one cardiovascular-related drug.

[0147] M68. A method according to any one of the three preceding embodiments, wherein the method includes generating at least one drug administration route, wherein at least one drug administration route includes at least one of the following: intravenous injection; intramuscular injection; subcutaneous injection; inhalation; transdermal; percutaneous; oral; rectal; and sublingual.

[0148] M69. A method according to any of the preceding embodiments and having the features of embodiments M45 and M65 to M68, wherein the method comprises generating at least one dosing regimen for at least one drug.

[0149] M70. The method according to the preceding embodiment, wherein the method further comprises optimizing at least one dosing regimen, wherein at least one dosing regimen comprises at least one of the following:

[0150] At least one drug,

[0151] At least one route of drug administration;

[0152] at least one dosage regimen;

[0153] Duration of use of at least one medication; and

[0154] How often at least one medication is taken.

[0155] M71. A method according to the preceding embodiments, wherein the step of optimizing at least one dosing regimen is based on at least one health condition hypothesis.

[0156] M72. A method according to any one of the two preceding embodiments, wherein the method includes implementing at least one optimal control theory, wherein at least one optimal control theory is implemented by a computer.

[0157] M73. A method according to any of the preceding method embodiments, wherein the method is a computer-implemented method.

[0158] M74. A method according to any of the preceding method embodiments, wherein the method comprises optimizing at least one ongoing treatment for at least one medical condition.

[0159] M75. A method according to any of the preceding method embodiments, wherein the method comprises optimizing at least one ongoing treatment for at least one underlying medical condition.

[0160] M76. A method according to any one of the two preceding embodiments, wherein the step of optimizing is based on at least one health condition hypothesis and / or at least one health condition.

[0161] M77. A method according to any of the preceding method embodiments, wherein the method includes generating at least one treatment recommendation, wherein the at least one treatment recommendation is based on at least one health condition hypothesis and / or at least one health condition.

[0162] M78. A method according to the aforementioned embodiment, wherein the method includes optimizing at least one treatment recommendation, wherein the method includes performing an optimization step after executing at least one treatment recommendation.

[0163] M79. A method according to any of the preceding method embodiments, wherein the method comprises:

[0164] applying any of the foregoing method embodiments to a subject, and

[0165] At least one personalized treatment regimen is generated, wherein the at least one personalized treatment regimen is based on at least one health condition of the subject.

[0166] M80. A method according to the aforementioned embodiment, wherein the method includes optimizing at least one personalized treatment plan, wherein the method includes performing an optimization step after executing at least one personalized treatment plan.

[0167] M81. A method according to any of the preceding method embodiments, wherein the method comprises implementing any of the preceding optimization steps with the assistance of a quantitative pharmacology method implemented by a computer.

[0168] M82. A method according to any of the preceding embodiments, wherein the method includes performing any of the preceding method embodiments in the absence of the subject.

[0169] M83. A method according to any of the preceding embodiments, wherein the method includes executing any of the preceding method embodiments using at least one historical data.

[0170] M84. A method according to the preceding embodiment, wherein at least one historical data is historical data of the subject.

[0171] M85. A method according to any one of the two preceding embodiments, wherein the at least one historical data comprises data from at least one of the following:

[0172] Public Health Database,

[0173] A personal database of subjects,

[0174] Database of medical professionals,

[0175] a database of healthcare providers, and

[0176] Private database.

[0177] M86. A method according to any of the preceding method embodiments, wherein the method comprises at least one of the following:

[0178] capturing at least one image data of a subject; and

[0179] receiving at least one image data of a subject,

[0180] The at least one image data includes data related to at least one medical condition and / or at least one potential medical condition of the subject.

[0181] M87. A method according to any of the preceding embodiments, wherein the method is suitable for implementation in at least one medical device (e.g., an ultrasonic device).

[0182] M88. A method according to any of the foregoing method embodiments, wherein the method includes using a system according to any of the system embodiments to perform any of the steps described in any of the method embodiments.

[0183] The following will discuss system embodiments. These embodiments are indicated by the abbreviation "S" and a number. When system embodiments are mentioned herein, these embodiments are referred to.

[0184] S1. A system for predicting the health status of a subject, the system comprising:

[0185] At least one processing component, the at least one processing component configured to:

[0186] receiving at least one dynamic attribute data associated with a subject;

[0187] receiving at least one covariate associated with the subject;

[0188] processing at least one dynamic attribute data associated with the subject and at least one covariate data associated with the subject to generate a processed data set associated with the subject;

[0189] At least one analysis component, the at least one analysis component configured to:

[0190] Analyze the processed data set associated with the subject, and

[0191] generating at least one health condition hypothesis based on the processed data set associated with the subject,

[0192] Wherein the system is configured to predict at least one health condition based on at least one health condition hypothesis.

[0193] S2. The system according to the preceding embodiment, wherein the system comprises at least one storage component configured to store data related to at least one health condition of the subject.

[0194] S3. A system according to the preceding embodiment, wherein the system comprises at least one computing component configured to implement a dynamic model for predicting at least one health condition.

[0195] S3. A system according to any of the preceding system embodiments, wherein at least one health condition hypothesis includes an association with at least one medical condition of the subject.

[0196] S4. A system according to any of the preceding system embodiments, wherein the subject is a female subject.

[0197] S5. A system according to the preceding embodiment, wherein the female subject is a pregnant woman.

[0198] S6. A system according to any of the two preceding embodiments, wherein the female subject comprises a non-pregnant female.

[0199] S7. A system according to any of the preceding system embodiments, wherein the subject is a fetus.

[0200] S8. A method according to any of the preceding method embodiments, wherein the subject is a neonate.

[0201] S9. A system according to any of the preceding system embodiments, wherein the system is configured to predict dynamic behavior of at least one health condition of the subject.

[0202] S10. A system according to any of the aforementioned system embodiments, wherein the system is configured to implement at least one machine learning technology, wherein the system is configured to perform any of the steps described in any of the aforementioned method embodiments with the aid of at least one machine learning technology.

[0203] S11. A system according to any of the preceding system embodiments, wherein at least one subject-related covariate comprises at least one biomarker.

[0204] S12. The system according to the preceding embodiment, wherein at least one biomarker is associated with at least one medical condition.

[0205] S13. A system according to any one of the three preceding embodiments, wherein at least one biomarker comprises at least one of the following: soluble Fms-like tyrosine kinase-1 (sFlt1); placental growth factor (PlGF); neurofilament light chain (NfL); and peptide factor; placental biomarkers, such as placental RNA, placental protein; endothelial / cardiovascular biomarkers, such as endothelial RNA, endothelial protein; or any combination thereof.

[0206] S14. A system according to any of the foregoing system embodiments and having the features of embodiment S4, wherein at least one subject-related covariate includes at least one neonate-related covariate, and the at least one neonate-related covariate includes at least one of the following: gender; race; weight; birth weight; gestational age; mode of delivery, such as vaginal delivery, vacuum delivery, cesarean section; body temperature; heart rate; respiratory rate; pH value; umbilical cord pH value; respiratory assistance; oxygen demand; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); Apgar score; and at least one measurement value of at least one biomarker.

[0207] S15. A system according to any of the foregoing system embodiments and having the features of embodiment S5, wherein at least one subject-related covariate includes at least one mother-related covariate, and the at least one mother-related covariate includes at least one of the following: age; race; early rupture of membranes; body temperature; risk factors, such as diabetes, obesity, number of pregnancies, parity, white blood cells; and at least one measurement value of at least one biomarker.

[0208] S16. A system according to any of the foregoing system embodiments and having the features of embodiment S6, wherein at least one subject-related covariate includes at least one fetus-related covariate, and the at least one fetus-related covariate includes at least one of the following: gender; fetal weight during pregnancy; fetal biometric parameters, such as femur length, abdominal circumference, head circumference, mid-thigh circumference, and biparietal diameter; the rate of small for gestational age infants; gestational age; heart rate, heart rate variability; respiratory rate; uteroplacental perfusion parameters; and at least one measurement value of at least one biomarker.

[0209] S17. A system according to any of the preceding system embodiments, wherein at least one subject-related covariate includes at least one environmental covariate, wherein the at least one environmental covariate includes at least one of the following: country of residence, country of birth, date and time of birth, humidity conditions at birth, and ambient temperature at birth.

[0210] S18. A system according to any of the preceding system embodiments, wherein the system is configured to generate at least one threshold, wherein the at least one threshold represents an indication of at least one underlying medical condition.

[0211] S19. A system according to any of the preceding system embodiments, wherein the system is configured to output at least one potential medical condition, wherein the at least one potential medical condition includes at least one of the following: epileptic seizures; respiratory, cardiovascular, and blood dysfunction; endocrine, renal, hepatic, and placental dysfunction; fetal growth restriction; unexpected premature birth; placental abruption; elevated hepatolytic enzymes and low platelets (HELLP) syndrome; and eclampsia.

[0212] S20. The system according to any of the preceding system embodiments, wherein at least one analysis component is configured to:

[0213] determining a minimum threshold of at least one threshold, and

[0214] A maximum threshold value of at least one threshold value is determined.

[0215] S21. A system according to the preceding embodiment, wherein when at least one data related to the subject is below a minimum threshold, at least one analysis component outputs a monitoring recommendation.

[0216] S22. A system according to any one of the two preceding embodiments, wherein when at least one data related to the subject is above a maximum threshold, at least one analysis component outputs a treatment recommendation.

[0217] S23. A system according to any one of the three preceding embodiments, wherein at least one analysis component is configured to determine a baseline of at least one data associated with the subject.

[0218] S24. According to any one of the four aforementioned embodiments, the system, wherein at least one analysis component is configured to determine at least one intermediate threshold, wherein the at least one intermediate threshold comprises at least one value between a minimum threshold and a maximum threshold.

[0219] S25. The system according to the preceding embodiment, wherein at least one analysis component is configured to:

[0220] associating at least one range of at least one intermediate threshold value with at least one medical condition,

[0221] Generate an interpreted dataset based on the association step, and

[0222] An automated report is outputted indicating at least one underlying medical condition.

[0223] S26. The system according to any of the preceding system embodiments, wherein at least one analysis component is configured to:

[0224] Identify at least one indicator of a change in medical condition,

[0225] monitoring a change in at least one indicator of a change in medical condition,

[0226] generating a trend for at least one indicator of change in medical condition, and

[0227] The evolution of at least one medical condition is predicted based on a trend of at least one indicator of change in medical condition.

[0228] S27. The system according to any of the preceding system embodiments, wherein the system comprises at least one monitoring component configured to monitor at least one value change of at least one attribute associated with the subject, wherein the at least one monitoring component is further configured to:

[0229] record the initial value of at least one attribute associated with the subject,

[0230] recording at least one subsequent value of at least one attribute associated with the subject,

[0231] comparing the initial value to at least one of the at least one subsequent value,

[0232] Generate comparison value data, and

[0233] Output attribute hypotheses associated with the subject based on the comparison value data.

[0234] S28. A system according to the preceding embodiment, wherein at least one monitoring component is configured to record a current value of at least one attribute associated with the subject, wherein the current value is different from an initial value.

[0235] S29. A system according to any of the preceding system embodiments, wherein the system is a non-diagnostic system.

[0236] S30. A system according to any of the preceding system embodiments, wherein the system is a diagnostic system.

[0237] S31. A system according to any of the preceding system embodiments, wherein the system is configured to use data from at least one database to perform the method steps according to any of the preceding method embodiments.

[0238] S32. A system according to the aforementioned embodiment, wherein at least one database comprises at least one of the following: a public health database, a personal database of a subject, a database of medical professionals, a database of healthcare providers, and a private database.

[0239] S33. A system according to any of the preceding system embodiments, wherein the system is configured as follows:

[0240] feeding data to at least one server, and

[0241] training a computer-implemented dynamic model based on data fed to at least one server, and

[0242] Generate an adjustment function based on the training data,

[0243] The adjustment function is applicable to adjusting any configuration of the system according to any of the aforementioned system embodiments.

[0244] S34. A system according to any of the preceding system embodiments, wherein the system is configured to trigger at least one action recommendation based on at least one health condition hypothesis.

[0245] S35. A system according to the preceding embodiment, wherein the system is configured to display at least one action suggestion to the user.

[0246] S36. The system according to any one of the two preceding embodiments, wherein the system is configured to prompt the user to input at least one of the following:

[0247] acceptance of at least one proposed action, and

[0248] A rejection of at least one proposed action.

[0249] S37. A system according to the aforementioned embodiment, wherein when the user rejects at least one action suggestion, the system is configured to prompt the user to provide at least one annotation.

[0250] S38. A system according to any of the preceding system embodiments, wherein the dynamic model implemented by the computer is based on Bayesian statistical methods.

[0251] S39. A system according to any of the preceding system embodiments, wherein the dynamic model implemented by a computer is based on an ANN, CNN or RNN method.

[0252] S40. A system according to any of the preceding system embodiments, wherein the computer-implemented dynamic model is based on a quantitative pharmacology approach.

[0253] S41. A system according to any of the preceding system embodiments, wherein the dynamic model implemented by the computer is based on a supervised learning method.

[0254] S42. A system according to any of the preceding system embodiments, wherein the dynamic model implemented by a computer is based on deep learning and / or multi-layer neural network methods.

[0255] S43. A system according to any of the preceding system embodiments, wherein the dynamic model implemented by the computer is based on the concept of explainable AI (XAI).

[0256] S44. A system according to any of the preceding system embodiments, wherein at least one medical condition includes at least one of the following: fetal growth-related conditions; neonatal thyroid dysfunction; PE-related conditions; gestational diabetes-related conditions; pregnancy-induced hypertension-related conditions; and pregnancy-induced thyroid dysfunction.

[0257] S45. A system according to any of the preceding system embodiments and having the features of embodiment S13, wherein the system is configured to associate at least one biomarker with at least one medical condition, wherein the at least one medical condition comprises an underlying disease.

[0258] S46. A system according to any of the preceding system embodiments, wherein the system is configured to predict the occurrence of at least one hypothesis within a given time period, wherein the system is configured to identify multiple different time periods, the multiple different time periods including at least one of the following: prenatal period; pregnancy period; delivery period and postnatal period.

[0259] S47. A system according to the aforementioned embodiment, wherein the system is configured to output the probability of occurrence associated with each time period.

[0260] S48. A system according to any of the preceding system embodiments, wherein the system is configured to execute at least one machine learning algorithm.

[0261] S49. A system according to the aforementioned embodiments, wherein at least one machine learning algorithm comprises a supervised algorithm architecture, an unsupervised algorithm architecture, or any combination thereof.

[0262] S50. A system according to any of the preceding system embodiments, wherein at least one machine learning algorithm comprises at least one artificial deep learning (DL) architecture.

[0263] S51. A system according to the aforementioned embodiment, wherein at least one artificial deep learning architecture includes at least one of the following: ANN, CNN and RNN.

[0264] S52. A system according to any of the preceding system embodiments and having the features of embodiment S47, wherein the unsupervised algorithm architecture is configured to implement at least one clustering method for at least one clustering.

[0265] S53. A system according to any of the foregoing system embodiments, wherein the system is configured to perform at least one analysis method, wherein the at least one analysis method includes at least one of the following: pattern recognition, probabilistic modeling, Bayesian scheme, reinforcement learning, statistical analysis, statistical model, principal component analysis, independent component analysis, dynamic time warping, maximum likelihood estimation, modeling, estimation, neural network, convolutional network, recurrent network, deep convolutional network, deep learning, ultra-deep learning, genetic algorithm, Markov model and / or hidden Markov model.

[0266] S54. A system according to any of the preceding system embodiments, wherein the system is configured to implement at least one quantitative pharmacology model.

[0267] S55. The system according to the preceding embodiments, wherein at least one quantitative pharmacology comprises a PKPD model.

[0268] S56. A system according to any of the preceding system embodiments, wherein at least one health condition of the subject includes PE.

[0269] S57. A system according to any of the preceding system embodiments, wherein at least one health condition of the subject includes gestational diabetes.

[0270] S58. A system according to any of the preceding system embodiments, wherein at least one health condition of the subject includes issues related to fetal growth.

[0271] S59. A system according to any of the preceding system embodiments, wherein at least one health condition of the subject includes a condition related to pregnancy-induced hypertension.

[0272] S60. A system according to any of the preceding system embodiments, wherein the system is configured to predict at least one health condition based on at least one health condition hypothesis and use at least one fetal growth-related data.

[0273] S61. A system according to any of the preceding system embodiments, wherein the system is configured to use at least one fetal growth-related data to predict at least one health condition, wherein at least one health condition hypothesis is based on at least one fetal growth-related data.

[0274] S62. A system according to the preceding embodiments and having the features of embodiment S30, wherein at least one fetal growth related data is retrieved from at least one database.

[0275] S63. A system according to any of the preceding system embodiments, wherein the system is configured to use at least one PE-related data to predict at least one health condition, wherein at least one health condition hypothesis is based on at least one PE-related data.

[0276] S64. A system according to the preceding embodiment and having the features of embodiment S30, wherein at least one PE-related data is retrieved from at least one database.

[0277] S65. The system according to any of the preceding system embodiments, wherein the system comprises at least one imaging component configured to perform at least one of the following operations:

[0278] capturing at least one image data of the subject; and

[0279] receiving at least one image data of a subject,

[0280] The at least one image data includes data related to at least one medical condition and / or at least one potential medical condition of the subject.

[0281] S66. A system according to any of the preceding system embodiments, wherein the system is configured to perform any step according to any of the method embodiments.

[0282] S67. A system according to any of the foregoing system embodiments, wherein the system includes at least one implementation component, and the at least one implementation component is configured to connect the system to at least one medical device (e.g., an ultrasound device), wherein once the system is connected to the at least one medical device, it is configured to perform any step according to any of the foregoing method embodiments.

[0283] S68. A system according to any of the preceding system embodiments, wherein the system is configured to operate in the absence of a subject.

[0284] The following discussion will discuss the treatment method embodiments. These embodiments are indicated by the letter abbreviation "T" and a number. When the present invention refers to the treatment method embodiments, it refers to these embodiments.

[0285] T1. A therapeutic method for treating a medical condition in a subject, wherein the therapeutic method comprises generating a treatment regimen comprising at least one therapeutic drug and a treatment regimen, wherein the treatment regimen is based on at least one health condition hypothesis.

[0286] T2. The treatment according to the preceding embodiments, wherein at least one health condition hypothesis is provided by a method according to any preceding method embodiment.

[0287] T3. The treatment according to any one of the two preceding embodiments, wherein at least one drug is provided by a method according to any of the preceding method embodiments.

[0288] T4. The treatment according to any of the preceding method embodiments, wherein at least one health condition of the subject includes PE.

[0289] T5. The treatment according to any of the preceding treatment method embodiments, wherein at least one health condition of the subject includes gestational diabetes and / or pregnancy-induced hypertension.

[0290] T6. The treatment according to any of the preceding treatment embodiments, wherein at least one health condition of the subject includes fetal growth problems.

[0291] T7. The treatment according to any of the preceding method embodiments, wherein the treatment further comprises treating at least one underlying medical condition of the subject prior to the onset of the at least one medical condition.

[0292] T8. The treatment according to any of the preceding treatment embodiments, wherein the subject is at least one of: a pregnant woman and a non-pregnant woman.

[0293] T9. The method of treatment according to any of the preceding treatment embodiments, wherein the subject is a fetus.

[0294] T10. The method of treatment according to any preceding treatment embodiment, wherein the subject is a neonate.

[0295] The following will discuss the diagnostic method embodiments. These embodiments are indicated by the letter abbreviation "D" and a number. When the diagnostic embodiments are mentioned herein, these embodiments are meant.

[0296] D1. A diagnostic method for diagnosing a medical condition of a subject, wherein the diagnosis includes generating at least one diagnostic result including at least one medical condition of the subject, wherein the at least one diagnostic result is based on at least one health condition hypothesis.

[0297] D2. The diagnosis according to the preceding embodiment, wherein the diagnosis comprises generating at least one treatment method, wherein the at least one treatment method is used to treat at least one medical condition of the subject.

[0298] D3. A method according to any one of the two preceding embodiments, wherein the diagnosis comprises generating at least one diagnostic result, wherein the at least one diagnostic result comprises at least one medical condition of the subject before the onset of the at least one medical condition.

[0299] D4. The diagnosis according to the preceding embodiment, wherein the diagnosis comprises at least one prophylactic treatment method, wherein the at least one prophylactic treatment method is used to treat at least one medical condition of the subject before the onset of the at least one medical condition.

[0300] D5. The diagnosis according to the aforementioned diagnosis embodiment, wherein at least one health condition hypothesis is provided by a method according to any of the aforementioned method embodiments.

[0301] D6. The diagnosis according to any of the preceding diagnostic embodiments, wherein the diagnosis comprises providing at least one drug, wherein the at least one drug is provided by a method according to any of the preceding method embodiments.

[0302] D7. The diagnosis according to any of the preceding diagnostic embodiments, wherein at least one health condition of the subject includes PE.

[0303] D8. The diagnosis according to any of the preceding diagnostic embodiments, wherein at least one health condition of the subject includes gestational diabetes and / or pregnancy-induced hypertension.

[0304] D9. The diagnosis according to any of the preceding diagnostic embodiments, wherein at least one health condition of the subject includes a fetal growth problem.

[0305] D10. The diagnosis according to any of the preceding diagnostic embodiments, wherein the subject is at least one of the following: a pregnant woman and a non-pregnant woman.

[0306] D11. The diagnosis according to any preceding diagnostic embodiment, wherein the subject is a fetus.

[0307] D12. The diagnosis according to any of the preceding diagnostic embodiments, wherein the subject is a neonate.

[0308] D13. The diagnosis according to any of the preceding diagnosis embodiments, wherein the diagnosis includes recommending a treatment method according to any of the preceding treatment method embodiments.

[0309] The following will discuss the use embodiments. These embodiments are indicated by the letter abbreviation "U" and a number. When the system embodiments are mentioned herein, these embodiments are referred to.

[0310] U1. A use of a system according to any of the aforementioned system embodiments, wherein the system is used to execute a method according to any of the aforementioned method embodiments.

[0311] U2. A use of a method according to any of the foregoing method embodiments, wherein the method comprises causing a system according to any of the foregoing method embodiments to execute the steps of the method according to any of the foregoing method embodiments.

[0312] U3. A use of the method described in any of the foregoing method embodiments, the method being used to implement the treatment method described in any of the foregoing treatment method embodiments.

[0313] U4. A use of a method according to any of the foregoing method embodiments, the method being used to implement a diagnostic method according to any of the foregoing diagnostic method embodiments.

[0314] U5. A use of a method according to any of the aforementioned method embodiments, the method being used to implement a diagnostic method according to any of the aforementioned diagnostic method embodiments and a therapeutic method according to any of the aforementioned therapeutic method embodiments, wherein the diagnostic method is implemented prior to the therapeutic method. BRIEF DESCRIPTION OF THE DRAWINGS

[0315] Embodiments of the present invention will now be described with reference to the accompanying drawings. These embodiments are only used to illustrate the present invention and are not intended to limit the present invention.

[0316] Figure 1 A system for predicting the health status of a subject according to an embodiment of the present invention is schematically shown;

[0317] Figure 2 Schematically shows a layered representation of an implementation of the present invention according to an embodiment of the present invention;

[0318] Figure 3 Schematically shows a flow chart according to an embodiment of the present invention;

[0319] Figure 4 A comparison of the evolution of pregnancy in both categories of subjects is depicted. DETAILED DESCRIPTION

[0320] It should be noted that not all figures are marked with all reference numerals. On the contrary, in some figures, some reference numerals are omitted for brevity and simplified description. Embodiments of the present invention will now be described with reference to the accompanying drawings.

[0321] Figure 1 Schematically illustrated is a system 1000 for predicting a health condition of a subject. Briefly, the system 1000 includes a processing component 1100, an analysis component 1200, a calculation component 1300, a storage component 1400, and a monitoring component 1500. It should be understood that in some embodiments, the system 1000 may include one or more of these components.

[0322] In one embodiment, storage component 1400 may be an external component (e.g., a remote component). Figure 1 In the example of FIG. 1000 , this is indicated by a dotted line. However, it should be understood that any other component of the system 1000 may also be external, for example, the monitoring component 1500 may be a remote component. When a component of the system 1000 is an external component, it should be understood that the component may also be distributed on a server (remote or local) or even in the cloud.

[0323] The processing component 1100 can be configured to receive at least one dynamic attribute data associated with the subject, receive at least one covariate associated with the subject, and process at least one dynamic attribute data associated with the subject and at least one covariate data associated with the subject to generate a processed data set associated with the subject. That is, the processing component 1100 is responsible for receiving data, such as raw data or unprocessed data from different systems (e.g., databases), manual input from users, and automatic input performed by other devices or systems. Once the processing component 1100 receives the data, the processing component 1100 can autonomously or at least partially autonomously process the data to generate a processed data set associated with the subject.

[0324] The analysis component 1200 can be configured to analyze a processed data set associated with the subject and generate at least one health condition hypothesis based on the processed data set associated with the subject.

[0325] In one embodiment of system 1000, processing component 1100 and analysis component 1200 may represent integrated components.

[0326] The system 1000 is configured to utilize a plurality of different data as input. In particular, but not limited to, the system 1000 may receive, process and / or analyze the following: a plurality of biomarkers, such as maternal, fetal and / or neonatal biomarkers; a plurality of clinical parameters, such as maternal, fetal and / or neonatal clinical parameters; demographic, lifestyle and psychometric scores associated with a subject and / or a subject group; a plurality of environmental parameters; medication, such as current medication for a subject and / or medication recommended in current or effective guidelines; dosing regimen, medication history associated with a subject or a subject group; cardiogram data (CTG); electroencephalogram data (EEG); electrocardiogram data (ECG), pulse and / or oxygen measurements; data such as provided by ultrasound and Doppler, duplex, etc. variants; magnetic resonance imaging (MRI); X-ray.

[0327] In one embodiment, system 1000 may also include one or more imaging components (not shown) configured to capture images of a subject that may be associated with at least one health condition and / or medical condition.

[0328] Monitoring component 1500 is configured to monitor system 1000, i.e., to monitor components of system 1000. In addition, monitoring component 1500 can be configured to: monitor at least one value change of at least one attribute related to the subject, record at least one initial value of at least one attribute related to the subject, record at least one subsequent value of at least one attribute related to the subject, compare the initial value with at least one of the at least one subsequent value, generate comparative value data, and output a hypothesis of the attribute related to the subject based on the comparative value data.

[0329] Additionally or alternatively, at least one monitoring component 1500 may be configured to record a current value of at least one attribute associated with a subject, wherein the current value is different from the initial value. In other words, monitoring component 1500 is configured to monitor the change in the value of at least one attribute associated with a subject over time. It should be understood that for this purpose, monitoring component 1500 or system 1000 or the components of system 1000 can record and / or determine the initial value. However, it should also be understood that the initial value may have been included in the received data. In certain embodiments, the initial value may also be referred to as a baseline.

[0330] Additionally, system 1000 is configured to predict at least one health condition of the subject based on at least one condition hypothesis.

[0331] The computing component 1300 is configured to implement a dynamic model for predicting at least one health condition. In one embodiment, the computing component 1300 is further configured to implement multiple models to predict at least one health condition, improve outcomes, recommend, generate and / or improve medication for treating at least one health condition.

[0332] The storage component 1400 is also configured to store data related to at least one health condition of the subject. In one embodiment, the storage component 1400 may also include a server comprising a plurality of modules implemented by a computer. In another embodiment, the storage component 1400 may also include at least in part the processing component 1100, the analysis component 1200, the calculation component 1400 and / or the monitoring component 1500.

[0333] In one embodiment, the computing component 1300 may also include: Figure 3 A computing device further described in .

[0334] The system is also configured to output a plurality of data including information related to the subject (e.g., PE). Such information may include, but is not limited to, morbidity data, severity data scoring and prediction, morbidity dynamics analysis and interpretation, and risk assessment of the subject (e.g., mother, fetus, or neonate). The risk assessment may further include predictions and / or estimates of maternal, fetal, and / or neonatal complications, types of complications, and / or degrees of complications. In addition, the system 1000 is configured to output at least one treatment recommendation and / or treatment regimen and / or optimization of an ongoing treatment regimen.

[0335] In one embodiment, the system 1000 may also include a signal processing component (not shown) configured to process a plurality of signals provided by one or more devices external and / or independent of the system 1000. The signal processing component may also be included in the processing component 1100 and configured to process data received as signal data.

[0336] Figure 2 The hierarchical representation of the implementation of the method according to the embodiment of the present invention is schematically shown. The method is a method implemented by a computer. The method is performed by the system 1000. In simple terms, the hierarchical representation includes three layers L1, L2 and L3. Layer L1 can also be called an input layer, L2 can be called a model layer, a modeling layer, a processing layer and / or an analysis layer. L3 can be called an output layer and / or a result layer.

[0337] The input layer L1 can receive multiple inputs 210, 220, 230, which may include but are not limited to: biomarkers, such as maternal, fetal and / or neonatal biomarkers; multiple clinical parameters, such as maternal, fetal and / or neonatal clinical parameters; demographic, lifestyle and psychometric scores associated with the subject and / or subject group; multiple environmental parameters; drug therapy, such as the current drug therapy for the subject and / or the drug therapy recommended in the current or effective guidelines; dosing regimen, medication history associated with the subject or subject group; cardiogram data (CTG); electroencephalogram data (EEG); electrocardiogram data (ECG), pulse and / or oxygen measurements; data such as provided by ultrasound and Doppler, duplex and other variants; magnetic resonance imaging (MRI); X-ray.

[0338] These inputs may be processed within a modeling layer L2, wherein a plurality of computer-implemented dynamic models 310, 320, 330 may be applied to the input data to generate processed data, which may be further analyzed and interpreted to generate at least one result, which may be expressed as at least one hypothesis about at least one health condition of a subject or group of subjects through a computer-implemented prediction step. The multi-layer computer-implemented method may also utilize an output layer L3, wherein the interpreted data may be provided to a user (e.g., a physician). Such outputs may include, but are not limited to, PE-related predictions, assessments 410, risk assessments 420 for PE or any other medical condition of a subject or group of subjects, which may include, for example, a risk assessment S1 associated with the mother, a risk assessment S2 associated with the fetus, and / or a risk assessment S3 associated with the newborn. In addition, the output layer L3 may also include one or more treatment methods 430, such as treatment plans and / or treatment method recommendations, as well as optimization of current and / or future treatment methods.

[0339] This is particularly advantageous because the multi-layered computer-implemented method provides, via system 1000, at least one hypothesis regarding at least one health condition of a subject or group of subjects, wherein the hypothesis is based on discrete available data including current data and / or historical data. That is, the computer-implemented method can process, analyze, and interpret, via system 1000, data related to PE during pregnancy and its effects on fetal gestational development, such as Figure 4 As shown, the figure depicts the evolution of pregnancy of a healthy pregnant woman 100A and a pregnant woman with PE 100B.

[0340] Figure 3 A schematic diagram of a computing device 100 is provided. The computing device 100 may include a computing unit 35, a first data storage unit 30A, a second data storage unit 30B, and a third data storage unit 30C.

[0341] The computing device 100 may be a single computing device or a combination of computing devices. The computing device 100 may be arranged locally or remotely (eg, a cloud solution).

[0342] Different data may be stored on different data storage units 30. Additional data storage units may also be provided and / or the aforementioned data storage units may be at least partially combined.

[0343] The computing unit 35 may access the first data storage unit 30A, the second data storage unit 30B, and the third data storage unit 30C via an internal communication channel 160 , which may include a bus connection 160 .

[0344] The operation unit 30 may be a single processor or multiple processors, and may be, but not limited to, a CPU (central processing unit), a GPU (graphics processing unit), a DSP (digital signal processor), an APU (accelerator processing unit), an ASIC (application-specific integrated circuit), an ASIP (application-specific instruction set processor), or an FPGA (field programmable gate array). The first data storage unit 30A may be single or multiple, and may be, but not limited to, a volatile memory or a non-volatile memory, such as a random access memory (RAM), a dynamic RAM (DRAM), a synchronous dynamic RAM (SDRAM), a static RAM (SRAM), a flash memory, a magnetoresistive RAM (MRAM), a ferroelectric RAM (F-RAM), or a parameter RAM (P-RAM).

[0345] The second data storage unit 30B may be single or multiple, and may be but is not limited to a volatile memory or a non-volatile memory, such as a random access memory (RAM), a dynamic RAM (DRAM), a synchronous dynamic RAM (SDRAM), a static RAM (SRAM), a flash memory, a magnetoresistive RAM (MRAM), a ferroelectric RAM (F-RAM) or a parameter RAM (P-RAM).

[0346] The third data storage unit 30C may be single or multiple, and may be but is not limited to a volatile memory or a non-volatile memory, such as a random access memory (RAM), a dynamic RAM (DRAM), a synchronous dynamic RAM (SDRAM), a static RAM (SRAM), a flash memory, a magnetoresistive RAM (MRAM), a ferroelectric RAM (F-RAM) or a parameter RAM (P-RAM).

[0347] It should be understood that, in general, the first data storage unit 30A (also referred to as the encryption key storage unit 30A), the second data storage unit 30B (also referred to as the data sharing storage unit 30B) and the third data storage unit 30C (also referred to as the decryption key storage unit 30C) may also be part of the same memory. That is, each device may provide only one universal data storage unit 30, which may be configured to store respective encryption keys (so that the portion of the data storage unit 30 storing the encryption keys may be the encryption key storage unit 30A), respective data element sharing (so that the portion of the data storage unit 30 storing the data element sharing may be the data sharing storage unit 30B) and respective decryption keys (so that the portion of the data storage unit 30 storing the decryption keys may be the decryption key storage unit 30A).

[0348] In some embodiments, the third data storage unit 30C may be a secure memory device 30C, such as a self-encrypting memory, a hardware-based full disk encryption memory, etc., which may automatically encrypt all stored data. Data may be decrypted from the storage component only after successful authentication of a party that needs to access the third data storage unit 30C, which may be a user, a computing device, a processing unit, etc. In some embodiments, the third data storage unit 30C may only be connected to the computing unit 35, and the computing unit 35 may be configured to never output data received from the third data storage unit 30C. This may ensure secure storage and processing of the encryption key (i.e., private key) stored in the third data storage unit 30C.

[0349] In some embodiments, the second data storage unit 30B may not be provided, but the computing device 100 may be configured to receive the corresponding encrypted share from the database 60. In some embodiments, the computing device 100 may include the second data storage unit 30B and may be configured to receive the corresponding encrypted share from the database 60.

[0350] The computing device 100 may include another storage component 140 (which may be single or multiple), and may be, but is not limited to, a volatile memory or a non-volatile memory, such as a random access memory (RAM), a dynamic RAM (DRAM), a synchronous dynamic RAM (SDRAM), a static RAM (SRAM), a flash memory, a magnetoresistive RAM (MRAM), a ferroelectric RAM (F-RAM), or a parameter RAM (P-RAM). The storage component 140 may also be connected to other components of the computing device 100 (e.g., the computing component 35) via an internal communication channel 160.

[0351] In addition, the computing device 100 may include an external communication component 130. The external communication component 130 may be configured to facilitate sending data to and / or receiving data from an external device, which is a backup device, a recovery device, a database, etc. The external communication component 130 may include an antenna (e.g., a Wi-Fi antenna, an NFC antenna, a 2G / 3G / 4G / 5G antenna, etc.), a USB port / plug, a LAN port / plug, a contact pad providing an electrical connection, etc. The external communication component 130 may send and / or receive data based on a communication protocol, which may include instructions for sending and / or receiving data. The instructions may be stored in the storage component 140 and may be executed by the computing unit 35 and / or the external communication component 130. The external communication component 130 may be connected to the internal communication channel 160. Therefore, the data received by the external communication component 130 may be provided to the storage component 140, the computing unit 35, the first data storage unit 30A, and / or the second data storage unit 30B, and / or the third data storage unit 30C. Similarly, data stored on the storage component 140, the first data storage unit 30A and / or the second data storage unit 30B and / or the third data storage unit 30C and / or data generated by the computing unit 35 can be provided to the external communication component 130 for transmission to an external device.

[0352] In addition, the computing device 100 may include an input user interface 110, which may allow a user of the computing device 100 to provide at least one input (e.g., an instruction) to the computing device 100. For example, the input user interface 110 may include a button, a keyboard, a trackpad, a mouse, a touch screen, a joystick, etc.

[0353] In addition, the computing device 100 may also include an output user interface 120, which allows the computing device 100 to provide instructions to the user. For example, the output user interface 110 may be an LED, a display, a speaker, etc.

[0354] The output and input user interface 100 may also be connected to internal components of the device 100 via an internal communication component 160 .

[0355] The processor may be single or multiple, and may be, but not limited to, a CPU, a GPU, a DSP, an APU, or an FPGA. The memory may be single or multiple, and may be, but not limited to, a volatile memory or a non-volatile memory, such as SDRAM, DRAM, SRAM, flash memory, MRAM, F-RAM, P-RAM, etc.

[0356] The data processing device may include data processing means, such as a processor unit, a hardware accelerator and / or a microcontroller. The data processing device 20 may include storage components, such as a main memory (e.g., RAM), a cache memory (e.g., SRAM) and / or an auxiliary memory (e.g., HDD, SDD). The data processing device may include a bus configured to facilitate data exchange between components of the data processing device (e.g., communication between storage components and processing components). The data processing device may include a network interface card, which may be configured to connect the data processing device to a network (e.g., the Internet). The data processing device may include a user interface, such as:

[0357] (1) Output user interface, for example:

[0358] - a screen or display configured to display visual data (e.g. a graphical user interface for displaying a questionnaire to a user),

[0359] - a speaker configured to transmit audio data (e.g., to play audio data to a user),

[0360] (2) Input user interface, for example:

[0361] - a camera configured to capture visual data (e.g., capture an image and / or video of a user),

[0362] - a microphone configured to capture audio data (e.g., to record a user's audio),

[0363] - A keyboard configured to allow insertion of text and / or other keyboard commands (e.g., allowing a user to enter text data and / or other keyboard commands by typing on the keyboard), and / or a trackpad, mouse, touch screen, joystick configured to facilitate navigation in different graphical user interfaces of the questionnaire.

[0364] The data processing device may be a processing unit configured to execute program instructions. The data processing device may be a system-on-chip including a processing unit, a storage component, and a bus. The data processing device may be a personal computer, a laptop computer, a pocket computer, a smart phone, a tablet computer. The data processing device may be a local and / or remote server. The data processing device may be a processing unit or a system-on-chip that may be connected to a personal computer, a laptop computer, a pocket computer, a smart phone, a tablet computer, and / or a user interface (e.g., the user interface described above).

[0365] It should be noted that not all figures are marked with all reference numerals. On the contrary, in some figures, some reference numerals are omitted for brevity and simplified description. Embodiments of the present invention will now be described with reference to the accompanying drawings.

[0366] The reference numerals and letters that appear between brackets in the claims indicate the features described in the embodiments and illustrated in the drawings as examples of the claims to help readers understand. The addition of these reference numerals and letters should not be interpreted as imposing any limitation on the scope of the claims.

[0367] The term "at least one of a first option and a second option" is intended to mean the first option or the second option or the first option and the second option.

[0368] Although the preferred embodiment has been described above with reference to the accompanying drawings, those skilled in the art will appreciate that the embodiment is for illustrative purposes only and should not be construed to limit the scope of the present invention as defined by the claims.

[0369] When relative terms (such as "about", "substantially" or "approximately") are used in this specification, such terms should also be interpreted as including exact terms. That is, for example, "substantially straight" should be interpreted as also including "(precisely) straight".

[0370] Whenever steps are described above or in the appended claims, it should be noted that the order in which the steps are described herein may be accidental. That is, unless otherwise stated or unless it is clear to a person skilled in the art, the order in which the steps are described may be accidental. That is, when, for example, a method is stated herein to include steps (A) and (B), this does not necessarily mean that step (A) precedes step (B), and it is also possible that step (A) and step (B) are (at least partially) performed simultaneously or step (B) precedes step (A). In addition, when step (X) is stated to precede another step (Z), this does not mean that there are no steps between steps (X) and (Z). That is, step (X) precedes step (Z) not only includes the case where step (X) is performed directly before step (Z), but also includes the case where step (X) is performed before one or more steps (Y1), (Y2)... after step (Z). When terms such as "after" or "before" are used, corresponding considerations apply.

Claims

1. A method for predicting the health status of a subject, the method comprising: receiving at least one dynamic attribute data associated with a subject, receives at least one covariate associated with the subject, processing at least one dynamic attribute data associated with the subject and at least one covariate data associated with the subject to generate a processed data set associated with the subject, generating at least one health condition hypothesis based on the processed data set associated with the subject, and At least one health condition is predicted based on the at least one health condition hypothesis.

2. A method according to the preceding claim, wherein the step of predicting at least one health condition is based on a dynamic model implemented by a computer, and at least one health condition hypothesis includes an association with at least one medical condition of the subject, wherein the method also includes predicting the dynamic behavior of at least one health condition of the subject.

3. The method according to any one of the preceding claims, wherein at least one subject-related covariate comprises at least one of: At least one biomarker, wherein the at least one biomarker is associated with at least one medical condition, wherein the at least one biomarker comprises at least one of the following: soluble Fms-like tyrosine kinase (sFlt-1); placental growth factor (PlGF); neurofilament (NfL); C-terminal portion of arginine vasopressin (Copeptin); albumin; liver transaminases; urea; hemoglobin; platelets; creatinine; albuminuria; proteinuria; estimated glomerular filtration rate (eGFR); creatinine clearance (CrCl); at least one additional measure of renal function; placental biomarkers, such as placental RNA, placental protein; endothelial / cardiovascular biomarkers, such as endothelial RNA, endothelial protein; or any combination thereof; At least one covariate associated with the mother, the at least one covariate associated with the mother comprising at least one of the following: age; weight; height; body mass index (BMI); number of pregnancies; parity; number of fetuses in the current pregnancy; race; body temperature; Heart rate Heart rate variability; respiratory rate; early rupture of membranes; white blood cells; history of preeclampsia (familial and maternal); comorbidities such as gestational diabetes, obesity, cardiovascular / renal / kidney / thyroid disease, autoimmune disease, anemia, antiphospholipid syndrome, sexually transmitted diseases, headaches; smoking habits before and / or during pregnancy; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); uteroplacental perfusion parameters; Doppler measurements of the umbilical artery, middle cerebral artery, cerebroplacental ratio, uterine artery, fetal descending aorta, ductus venosus, umbilical vein, inferior vena cava, uterine artery pulsatility index; soft tissue parameters such as arm volume fraction and thigh volume fraction; and at least one measurement of at least one biomarker; at least one fetal-related covariate, the at least one fetal-related covariate comprising at least one of: sex; fetal weight during pregnancy; fetal biometric parameters, such as femur length, abdominal circumference, head circumference, mid-thigh circumference, and biparietal diameter; small for gestational age rate; gestational age; heart rate, heart rate variability; respiratory rate; uteroplacental perfusion parameters; and at least one measurement of at least one biomarker; At least one covariate associated with the newborn, the at least one covariate associated with the newborn comprising at least one of the following: sex; birth weight; weight; height; gestational age at birth; postnatal age; body temperature; heart rate; heart rate variability; respiratory rate; breastfeeding; duration of exclusive breastfeeding; pH; respiratory assistance; oxygen requirement; blood oxygen saturation (SpO2); blood pressure (systolic / diastolic); Apgar score; at least one additional neonatal biometric parameter; and at least one measurement of at least one biomarker; and At least one environmental covariate, the at least one environmental covariate comprising at least one of: country of residence, country of birth, date and time of birth, humidity conditions at birth, and ambient temperature at birth.

4. A method according to any one of the preceding claims, wherein the method comprises: generating at least one threshold, wherein the at least one threshold is indicative of at least one underlying medical condition; Output at least one potential medical condition, wherein the at least one potential medical condition includes at least one of the following: epileptic seizure; respiratory, cardiovascular, hematological dysfunction; endocrine, renal, hepatic, placental dysfunction; fetal growth restriction; unexpected premature birth; placental abruption; elevated hepatolytic enzymes, low platelets (HELLP) syndrome; and eclampsia; determining a minimum threshold of at least one threshold, and determining a maximum threshold of at least one threshold, Determine a baseline for at least one subject-related datum, and At least one intermediate threshold is determined, wherein the at least one intermediate threshold comprises at least one value between a minimum threshold and a maximum threshold.

5. The method according to the preceding claim, wherein the method comprises: associating at least one range of at least one intermediate threshold value with at least one medical condition, Generate an interpreted dataset based on the association step, and An automated report is outputted indicating at least one underlying medical condition.

6. A method according to any one of the preceding claims, wherein the method comprises: Identify at least one indicator of a change in medical condition, monitoring a change in at least one indicator of a change in medical condition, generating a trend for at least one indicator of change in medical condition, and predicting the evolution of at least one medical condition, wherein the prediction is based on a trend of at least one indicator of change in the medical condition, Wherein the method comprises monitoring at least one change in value of at least one attribute associated with the subject, the method comprising: record the initial value of at least one attribute associated with the subject, recording at least one subsequent value of at least one attribute associated with the subject, comparing the initial value to at least one of the at least one subsequent value, Generate comparison value data, and A hypothesis for a property associated with the subject is output based on the comparison value data, wherein the step of recording at least one subsequent value includes recording a current value of the at least one property associated with the subject, wherein the current value is different than the initial value.

7. A method according to any one of the preceding claims, wherein the method comprises: Feed data to at least one server, training a computer-implemented dynamic model based on data fed to at least one server, and generating an adjustment function based on the training data, wherein the adjustment function is suitable for adjusting any step of the method according to any of the preceding claims, triggering at least one action recommendation based on at least one health condition hypothesis, displaying at least one suggested action to the user, and The user is prompted to input at least one of: an acceptance of at least one action suggestion, and a rejection of at least one action suggestion.

8. A method according to any one of the preceding claims, wherein the method comprises: At least one medication is determined based on at least one health condition, where the at least one medication is indicated for at least one of the following: Prevent the occurrence of at least one medical condition and / or at least one health condition, and Treat at least one medical condition and / or at least one health condition; generating at least one dosing regimen for at least one drug; Optimize at least one dosing regimen, wherein the at least one dosing regimen comprises at least one of the following: at least one drug, at least one route of drug administration, at least one dosing regimen, at least one duration of drug administration, and at least one frequency of drug administration, wherein the step of optimizing the at least one dosing regimen is based on at least one health condition hypothesis.

9. A system for predicting the health status of a subject, the system comprising: At least one processing component, the at least one processing component configured to: receiving at least one dynamic attribute data associated with a subject; receiving at least one covariate associated with the subject; processing at least one dynamic attribute data associated with the subject and at least one covariate data associated with the subject to generate a processed data set associated with the subject; At least one analysis component, the at least one analysis component configured to: Analyze the processed data set associated with the subject, and generating at least one health condition hypothesis based on the processed data set associated with the subject, The system is configured to predict at least one health condition based on at least one health condition hypothesis and to perform the method according to any one of the preceding claims.

10. The system according to the preceding claim, wherein the system comprises: at least one storage component configured to store data related to at least one health condition of the subject; at least one computing component configured to implement a dynamic model for predicting at least one health condition, wherein the at least one health condition hypothesis includes a correlation with at least one medical condition of the subject, Therein, the system is configured to predict dynamic behavior of at least one health condition of the subject.

11. The system according to any one of claims 9 to 10, wherein the system is configured as follows: generating at least one threshold, wherein the at least one threshold is indicative of at least one underlying medical condition; and Output at least one potential medical condition, wherein the at least one potential medical condition includes at least one of the following: epileptic seizure; respiratory, cardiovascular, blood dysfunction; endocrine, renal, hepatic, placental dysfunction; fetal growth restriction; unexpected premature birth; placental abruption; elevated hepatolytic enzymes, low platelets (HELLP) syndrome; and eclampsia.

12. The system according to any one of claims 9 to 11, wherein at least one analysis component is configured to: determining a minimum threshold of at least one threshold, determining a maximum threshold of at least one threshold, associating at least one range of at least one intermediate threshold value with at least one medical condition, Generate an interpreted dataset based on the association step, outputting an automated report indicative of at least one underlying medical condition, Identify at least one indicator of a change in medical condition, monitoring a change in at least one indicator of a change in medical condition, generating a trend for at least one indicator of change in medical condition, and The evolution of at least one medical condition is predicted based on a trend of at least one indicator of change in medical condition.

13. The system according to any one of claims 9 to 12, wherein the system comprises at least one monitoring component configured to monitor at least one change in value of at least one attribute associated with the subject, wherein the at least one monitoring component is further configured to: record the initial value of at least one attribute associated with the subject, recording at least one subsequent value of at least one attribute associated with the subject, comparing the initial value to at least one of the at least one subsequent value, Generate comparison value data, Output the attribute hypothesis related to the subject based on the comparison value data, A current value of at least one attribute associated with the subject is recorded, wherein the current value is different from the initial value.

14. A system according to any one of claims 9 to 13, wherein the system is configured to feed data to at least one server, and training a computer-implemented dynamic model based on data fed to at least one server, and generating an adjustment function based on the training data, wherein the adjustment function is suitable for adjusting any configuration of the system according to any of the preceding claims; At least one action suggestion is triggered based on at least one health condition hypothesis, wherein the system is configured to display the at least one action suggestion to a user and prompt the user to input at least one of the following: acceptance of the at least one action suggestion, and rejection of the at least one action suggestion.

15. The system according to any one of claims 9 to 14, wherein the system comprises at least one imaging component configured to perform at least one of the following operations: capturing at least one image data of the subject; and receiving at least one image data of a subject, The at least one image data includes data related to at least one medical condition and / or at least one potential medical condition of the subject.

16. A therapeutic method for treating a medical condition in a subject, wherein the therapeutic method comprises generating a treatment regimen comprising at least one therapeutic drug and a treatment regimen, wherein the treatment regimen is based on at least one health condition hypothesis, wherein the at least one health condition hypothesis is provided by a method according to any one of claims 1 to 8.

17. A diagnostic method for diagnosing a medical condition of a subject, wherein the diagnosis includes generating at least one diagnostic result, the diagnostic result including at least one medical condition of the subject, wherein the at least one diagnostic result is based on at least one health condition hypothesis, wherein the at least one health condition hypothesis is provided by a method according to any one of claims 1 to 8.

Images