Gestational weight gain prediction

Abstract

The invention relates to gestational weight gain prediction. The disclosed concepts are directed to providing protocols, solutions, concepts, designs, methods and systems related to improved prediction of gestational weight gain (GWG). Specifically, during the early stage of pregnancy (e.g., during the first 30 days of pregnancy, or during the first three months of pregnancy), a data sequence describing the weight of a pregnant subject at least twice a day (e.g., after waking up and before falling asleep) is used to determine the historical GWG curve of the subject. Since the energy balance in pregnancy is defined as energy intake equal to energy expenditure plus dynamic energy storage, a particular GWG prediction model is used to generate historical GWG curves, rather than a universal weight gain model. From the historical GWG curve, a future GWG value of the subject may be predicted. The future GWG value may be used to assess pregnancy risk scores, and / or to generate lifestyle recommendations for the subject.

Description

Technical Field

[0001] The present invention relates to the field of predicting gestational weight gain in a subject. Background Art

[0002] In modern society, it is difficult to maintain a specific weight, in part because high-calorie foods are readily available. Generally, when calorie intake exceeds calorie expenditure, weight increases. Over time, this can cause the person to be overweight or even obese. In addition, lack of proper nutrition and weight loss can be a serious problem in the elderly population, whose biological signals of hunger and satiety may be insufficient.

[0003] Another group of people who need to control their weight are those who are pregnant. To achieve optimal pregnancy outcomes, pregnant individuals need to accumulate an appropriate level of fat, which depends on the individual's body shape. In fact, underweight individuals require more fat deposition than overweight individuals. Given the high energy density of fat mass, these differences greatly affect energy intake requirements. In contrast, the energy stored in fetal and placental tissues (depending on the size of the fetus) is comparable among most individuals and has a relatively small impact on energy intake requirements.

[0004] Therefore, there is a need to assist pregnant individuals in controlling their gestational weight gain (GWG). In fact, prediction of GWG will enable the generation of predictions of pregnancy risk levels, which can be used to inform medical devices and (potentially) future medical interventions. In addition, such predictions can form the basis for improving adherence to recommended lifestyle behavior changes during pregnancy. Summary of the Invention

[0005] The present invention is defined by the claims.

[0006] According to an embodiment of one aspect of the present invention, there is provided a method for predicting a future gestational weight gain (GWG) of a subject, comprising:

[0007] obtaining a data series of weight values that describes the weight of the subject and the corresponding gestational age of the subject at least twice a day during an early stage of the subject's pregnancy;

[0008] processing the data series with a GWG prediction model to determine a historical GWG curve of the subject, the historical GWG curve describing the GWG of the subject during the early stage of pregnancy; and

[0009] predicting a future GWG value of the subject based on the historical GWG curve.

[0010] The disclosed invention aims to provide an improved GWG prediction. Specifically, during the early stages of pregnancy (e.g., during the first 30 days of pregnancy, or during the first trimester of pregnancy), a data series of the weight of a pregnant subject described at least twice a day (e.g., after waking up and before going to sleep) is used to determine the subject's historical GWG curve. Since the energy balance in pregnancy is defined as energy intake equals energy expenditure plus dynamic energy storage, a specific GWG prediction model is used to generate the historical GWG curve, rather than a general weight gain model. Based on the historical GWG curve, the future GWG value of the subject can be predicted. This future GWG value can be used to evaluate the pregnancy risk score, and / or generate lifestyle recommendations for the subject.

[0011] Repeated micro - weighing (i.e., measuring the subject's weight more than once a day) is a method to precisely track the weight gain of a subject. However, for an individual during pregnancy, predicting future weight gain based on historical weight gain is not straightforward because the fetus grows in a non - linear manner (i.e., the growth rate and thus the contribution to weight gain depends on the stage of pregnancy / gestational age). Therefore, in order to gather an accurate understanding of the subject's historical weight gain (i.e., what weight gain is attributable to the fetus's weight gain and what weight gain is attributable to fat storage), and to predict any future pregnancy weight, the corresponding gestational age of the subject at the time of weight measurement should be tracked.

[0012] In other words, it has been recognized that by measuring weight at least twice a day (preferably before and after sleep), daily calorie intake, expenditure, nutrient intake, and calorie storage can be determined. This has not been applied to pregnant subjects. For pregnant subjects, there is an additional layer of complexity because some energy is used for the developing baby (and thus needs to be added to the model as energy use that does not cause weight loss), which will depend on the gestational age of the subject.

[0013] Therefore, embodiments of the present invention determine the historical GWG curve from weight data obtained at least twice a day from early pregnancy (i.e., micro - weight tracking data). This GWG curve / data can then be extrapolated to predict the GWG in the later stages of pregnancy. Once this is known, recommendations can be generated based on the comparison of the predicted GWG with the recommended / ideal GWG. Additionally, specifically determined calorie intake, expenditure, nutrient intake, and calorie storage can be used for various aspects of recommendations, as well as to improve the historical GWG curve and predict future GWG values.

[0014] When using a GWG prediction model to process a data series of measured weights to generate an accurate GWG curve, embodiments disclosed in the present invention take into account the gestational age of the subject. Therefore, the resulting future GWG values obtained from the GWG curve can be more accurate, and thus more appropriate recommendations and actions can be taken.

[0015] For clarification, the gestational age of a subject describes the time of the subject's pregnancy. Technically, gestational age can be measured in different ways, such as the length of time since the subject's last menstrual period, or by another method. The data series includes a set of weight values for the subject, each weight value having an associated gestational age of the subject at the time of measurement.

[0016] The early stage of pregnancy can be considered the first 100 days of pregnancy, or it can be the first trimester of pregnancy. In some embodiments, the weight values can span only the first 30 days of pregnancy. During the early stage of pregnancy, the subject's weight changes little from day to day or even week to week, so normal fluctuations in weight can greatly affect the accuracy of the determined GWG curve. Therefore, the subject's weight must be measured at least twice a day to make the GWG curve accurate.

[0017] More specifically, the data series of weight values can describe the subject's weight at least before and after going to sleep each day.

[0018] It has recently been noted that weight loss during sleep is related to total energy intake. In addition, weight loss during sleep is also related to an individual's nutritional intake, such as carbohydrate intake, fat intake, and protein intake. In other words, a person who loses weight more rapidly during the night / sleep generally consumes more calories, carbohydrates, proteins, and fats than a person who loses weight more slowly. This can be explained by changes in the resting metabolic rate of individuals who consume large amounts of calories, fat, carbohydrates, or protein.

[0019] Therefore, by ensuring that the data series of weight values contains this information, a more accurate GWG curve can be determined. In turn, the resulting future GWG prediction can be more accurate. That is, weight values obtained shortly before and shortly after sleep each day can be used to improve the accuracy of the determined GWG curve.

[0020] Alternatively, the data series of weight values can describe the subject's weight at least once per hour.

[0021] The more frequently weight values are collected, the less susceptible the historical GWG curve is to random changes (e.g., changes in response to the subject's normal movements). This is because when a data sequence of weight values with sufficient resolution is given, these changes can be distinguished and interpreted by the GWG prediction model.

[0022] In addition, the data series of weight values can also describe the subject's weight at least twice a day during a period of time before pregnancy.

[0023] By also including the weight value for a period of time prior to pregnancy, lifestyle trends and changes in the subject (which may not be directly attributable to pregnancy) can be identified and evaluated. Thus, a more accurate GWG curve can be generated.

[0024] In some embodiments, the method may further include generating at least one of current calorie intake data, current calorie expenditure data, current calorie storage data, or current nutrient intake data based on the data series and the current gestational age of the subject.

[0025] As described above, weight loss associated with individual nutrient intake, such as carbohydrate intake, fat intake, and protein intake, is related to repeated micro-weightings (i.e., measuring the subject's weight more than once a day) between two time points spaced apart from each other within a day (e.g., one before sleep and one after sleep). Thus, this information can be generated from the data sequence.

[0026] In such a case, the subject's historical GWG curve may further include processing at least one of the current calorie uptake data, current calorie expenditure data, current calorie storage data, or current nutrient uptake data with a GWG prediction model.

[0027] Such information can be generated separately and then provided to the GWG prediction model. This can ensure that these factors are considered when generating the historical GWG curve, thereby improving the accuracy of the historical GWG curve.

[0028] In addition, the method may further include generating a recommendation that describes a recommended change to the subject's lifestyle based on a future GWG value and at least one of the current calorie uptake data, current calorie expenditure data, current calorie storage data, or current nutrient uptake data.

[0029] This information can be used to provide personalized and useful recommendations regarding changes to the subject's lifestyle, which can result in improved pregnancy outcomes (an increased chance).

[0030] The recommendation may include a calorie intake recommendation, a nutrient intake recommendation, or an exercise recommendation.

[0031] For example, the recommendation may encourage the subject to eat more or less food, and more or less of specific foods. In addition, the recommendation may encourage the subject to exercise more or less.

[0032] When the recommendation includes an exercise recommendation, the method may further include adjusting the exercise recommendation based on gait information that describes the subject's gait stability. Thus, the suitability of the recommendation can be improved.

[0033] In addition, the recommendation can be based on a target (growth) curve. The target curve can be set by a physician / medical professional. Of course, the target curve can also be adjusted as the pregnancy progresses.

[0034] In some embodiments, the method can further include modifying the data series based on subject background information describing at least one of movement, temperature, water loss, cardiovascular activity (i.e., photoplethysmography signal), or resting metabolic rate of the subject during an early stage of pregnancy.

[0035] In this way, variations caused by movement, temperature, water retention / loss, changes in cardiovascular activity (indicating stress), and changes in resting metabolic rate can be removed from the data sequence. As a result, the historical GWG curve obtained from the GWG prediction model in response to the input data sequence can be improved.

[0036] That is, it is not possible for the subject to repeat the conditions of accurate weight measurement every time. In fact, some factors can be completely out of the subject's control. Therefore, considering these factors can improve the accuracy of the data series. Subject background information can be measured, obtained from observations, or derived from information based on time and location context.

[0037] Additional embodiments can include an additional step of obtaining weight-related physiological data describing at least one physiological parameter of the subject; and adjusting the predicted future GWG value based on the obtained weight-related physiological data.

[0038] In particular, the at least one physiological parameter can include at least one of pre-pregnancy weight, pre-pregnancy BMI, age, height, race, stress value, pre-pregnancy lifestyle parameter value, or pregnancy lifestyle parameter value.

[0039] Each of these physiological parameters can affect the overall trend of the subject's GWG. Therefore, taking these into account when extrapolating the historical GWG curve to determine the predicted future GWG value can improve the accuracy of the value.

[0040] In some example embodiments, processing the data series to determine the historical GWG curve can include processing the data series with a regression analysis model, and wherein predicting the future GWG value of the subject includes extrapolating the historical GWG curve.

[0041] The method can further include generating a pregnancy risk score indicating the likelihood of complications during the subject's pregnancy based on a comparison between the future GWG value and the target GWG.

[0042] The pregnancy risk score can be used to inform clinical decisions and thus can be used to improve the pregnancy outcome of the subject. Specifically, such information can be used to appropriately allocate resources, inform procedures, and inform recommendations to the subject.

[0043] In addition, the method may further include processing the data series with a weight source prediction model to determine the weight of the fetus, the subject hydration value, and the fluid retention value.

[0044] In other words, a data series having weight values measured at least twice a day can be used to determine other relevant GWG metrics, such as the weight of the fetus, the subject hydration value, and the fluid retention value.

[0045] According to other embodiments of one aspect of the present invention, there is provided a computer program comprising computer program code means which, when the computer program is run on a computer, is adapted to implement any of the disclosed methods for predicting future gestational weight gain of a subject.

[0046] According to another example of another aspect of the present invention, there is provided a system for predicting future GWG of a subject, comprising:

[0047] An interface configured to obtain a data series of weight values that describe the weight of the subject at least twice a day during an early stage of the subject's pregnancy; and

[0048] A processor configured to:

[0049] Process the data series with a GWG prediction model to determine a historical GWG curve of the subject, the historical GWG curve describing the GWG of the subject during an early stage of pregnancy; and

[0050] Predict a future GWG value of the subject based on the historical GWG curve.

[0051] These and other aspects of the present invention will become apparent and be elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] To better understand the present invention and to more clearly show how it may be implemented, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0053] Figure 1 A flowchart of a method for predicting future gestational weight gain (GWG) of a subject according to an embodiment of the present invention is presented;

[0054] Figure 2 A block diagram of a system for predicting future GWG of a subject according to another aspect of the present invention is presented; and

[0055] Figure 3 Is a simplified block diagram of a computer within which one or more parts of the embodiment may be employed. Detailed implementation manners

[0056] The present invention will be described with reference to the accompanying drawings.

[0057] It should be understood that the detailed description and specific examples, although indicating exemplary embodiments of the apparatus, system and method, are for illustrative purposes only and are not intended to limit the scope of the present invention. These and other features, aspects and advantages of the apparatus, system and method of the present invention will become better understood from the following description, the appended claims and the drawings. The fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used advantageously.

[0058] It should be understood that the drawings are merely schematic and are not drawn to scale. It should also be understood that in all the drawings, the same reference numerals are used to indicate the same or similar components.

[0059] The disclosed concepts are intended to provide solutions, concepts, designs, methods and systems related to improved prediction of gestational weight gain (GWG). Specifically, during the early stages of pregnancy (e.g., during the first 30 days of pregnancy, or during the first trimester of pregnancy), a data sequence of the weight of a pregnant subject described at least twice a day (e.g., after waking up and before going to bed) is used to determine the subject's historical GWG curve. Since the energy balance in pregnancy is defined as energy intake being equal to energy expenditure plus dynamic energy storage, a specific GWG prediction model is used to generate the historical GWG curve, rather than a general weight gain model. Based on the historical GWG curve, the future GWG value of the subject can be predicted. This future GWG value can be used to evaluate the pregnancy risk score and / or generate lifestyle recommendations for the subject.

[0060] Generally speaking, it is difficult to maintain weight due to the easy availability of high-calorie foods and the growing trend of sedentary lifestyles. When a person consumes more calories than they burn, their weight increases. For certain populations, it can be even more difficult to maintain a target weight, such as the elderly (where the signals of hunger and satiety may be insufficient) and pregnant women (where it is unclear whether weight gain is due to fat accumulation or fetal and placental growth). The problem of maintaining a healthy weight is an urgent social challenge and an unmet consumer need.

[0061] Calorie intake is often intermittent rather than regular. Daily life can be characterized by food intake events such as breakfast, lunch, snacks, and dinner. Similarly, opportunities to expend calories occur according to the daily routine. Active commuting (e.g., walking, cycling, etc.), physical exercise, occupational tasks, household chores, and sedentary time tend to be highly repetitive on a daily and weekly basis. Calorie expenditure due to basal metabolic functions occurs continuously throughout the day and depends on muscle mass, homeostatic processes, and digestion. Due to such repetitive behaviors and predictable mechanisms, maintaining a balance between calorie intake and expenditure should be a viable goal for most healthy individuals. However, reversing the effects of any weight gain or loss can be particularly difficult and typically requires long-term effort.

[0062] As an additional layer of complexity, energy intake during pregnancy must be matched to the needs of resting metabolism, physical activity, and tissue growth to ensure a healthy and successful pregnancy. Energy balance during pregnancy is defined as energy intake being equal to energy expenditure plus energy storage. A detailed understanding of these components and their changes throughout pregnancy should inform energy intake recommendations to minimize the risk of adverse pregnancy outcomes.

[0063] For example, insufficient energy intake during pregnancy can cause complications such as poor fetal development, premature birth, etc. Excessive energy intake during pregnancy can cause other problems such as gestational diabetes and preeclampsia.

[0064] Energy expenditure is the sum of rest and physical activity-related expenditure. Due to weight gain, pregnancy-associated physiological changes (e.g., altered cardiac output), and fetal growth, the resting metabolic rate increases during pregnancy. Physical activity varies greatly among individuals during pregnancy and can change over the course of pregnancy. In fact, the activity of individuals during pregnancy can be hindered by pregnancy. The need for energy storage depends on the pre-pregnancy maternal body size.

[0065] The target level of fat accumulation during pregnancy depends on the pre-pregnancy body size / shape of the individual. Individuals with a low body weight require more fat deposition than those who are overweight. That is, those with a high body weight need to accumulate less fat mass or no fat mass at all. Considering the high energy density of fat mass, these differences greatly affect the energy intake required for a healthy pregnancy. In contrast, the energy stored in fetal and placental tissues is comparable among all individuals during pregnancy (but of course depends on the size of the fetus), and thus has a relatively small impact on the variability of energy intake requirements among women. Different predictive equations have been developed to quantify energy intake requirements.

[0066] Embodiments of the present invention address the above problems to achieve accurate and early prediction of future GWG, which can be used to generate a personalized risk level prediction during pregnancy. This enables early intervention and also forms the basis for improving adherence to recommended lifestyle and behavior changes during pregnancy.

[0067] The prediction model of GWG is mainly based on a regression model that uses historical weight measurements during the early stage of pregnancy (i.e., the first 100 days or the first trimester). However, within the first 100 days, the weight change of the subject is so small on a daily or even weekly basis that the model is very sensitive to minor errors in the measurements. These minor errors can be caused simply by normal fluctuations in weight.

[0068] As an explanation, it has been noted that weight loss during sleep is related to total energy intake. In addition, weight loss during sleep is also related to an individual's nutritional intake, such as carbohydrate intake, fat intake, and protein intake. In other words, a person who loses weight more rapidly during the night / sleep generally consumes more calories, carbohydrates, proteins, and fats than a person who loses weight more slowly. This can be explained by changes in the resting metabolic rate of individuals who consume large amounts of calories, fats, carbohydrates, or proteins.

[0069] That is to say, calorie / energy intake and calorie / energy expenditure can be obtained from cumulative weight data measured more than once a day, for example, at least once before going to bed and once after waking up. By measuring the weight of the subject more frequently, such as once an hour, or even continuously, the accuracy of intake and expenditure can be improved. The automatically collected weight information can be converted into a record of the user's activities and effectively guide the user to manage their weight. Of course, the energy balance during pregnancy is defined as energy intake equals energy expenditure plus energy storage. Since the energy storage requirements are dynamic during pregnancy (as well as due to fluctuations in resting metabolic rate, changes in exercise habits, etc. causing energy expenditure), this is a complex task for an individual during pregnancy. Therefore, the present invention provides a GWG prediction model that takes into account the gestational age of the subject when processing a data series of weight values, thus considering these possible changes during pregnancy. As a result, an accurate GWG curve can be obtained from data measured at least twice a day (preferably measured before going to bed and immediately after waking up).

[0070] In other words, the disclosed embodiments provide early GWG prediction based on the following combination: (i) a data series of weight values obtained by frequent measurements (especially at least twice a day) during the early stage of pregnancy (e.g., within the first 30 / 100 days, or even before pregnancy); and (ii) the gestational age of the subject related to the historical weight data.

[0071] In addition, weight loss between two measurements can be interpreted as providing information related to nutritional intake. Specifically, precise measurements before and after sleep are known to provide information on total calorie intake, as well as whether the calories ingested are based on fat, carbohydrates, or protein. Thus, this information can be used to improve the prediction of future GWG and to provide recommendations for improving pregnancy outcomes.

[0072] Embodiments of the proposed invention include some or all of the following steps:

[0073] (i) Measure the weight or (micro) weight change of a pregnant subject more than once a day. Typically, the weight (change) will be measured before and after sleep, or at least once an hour (possibly more frequently, even continuously). The measurements are taken in the early stages of pregnancy (although they can also be taken in the later stages of pregnancy);

[0074] (ii) Process the time-varying data series of weight values to remove noise and correct for movement, temperature, moisture loss, and resting metabolic rate;

[0075] (iii) Calculate the current dynamic calorie intake, nutritional intake, calorie expenditure, and calorie storage of the subject based on the measured data series, taking into account the gestational age / pregnancy status of the subject. For this step, it is important to distinguish between weight gain of the subject due to fetal growth and weight gain of the subject due to food and fluid intake, which indicates the weight change of the mother and thus indirectly indicates calorie intake;

[0076] (iv) Determine the GWG curve up to the current / latest weight measurement in the data series by processing the data series and the associated gestational age with a GWG prediction model;

[0077] (v) Use the GWG curve to predict the GWG at a later time point (e.g., in the second trimester and / or third trimester);

[0078] (vi) Compare and classify the predicted future GWG with the recommended GWG based on applicable guidelines (such as the IOM 2009 guidelines) to assess the risk or level of risk of the pregnancy. For example, this comparison can be used to determine the likelihood that the subject will develop preeclampsia, gestational diabetes, etc.; and

[0079] (vii) Calculate the recommended changes in dynamic calorie intake and calorie expenditure based on the current dynamic calorie and nutrient intake and calorie expenditure measured, the deviation of the predicted future GWG from the recommended / target GWG, and the dynamic energy requirements during pregnancy. For example, the recommended changes can be related to the amount and / or nature of the physical activity. Optionally, the gait stability of the subject is measured using a body-worn accelerometer, which can be used to adjust the recommended physical activity. Additionally, the body-worn accelerometer can be used to measure the activity behavior of the subject, thereby adjusting the recommendation for more or less physical activity.

[0080] In addition to the above, the method can also assist in predicting the growth of the fetus (e.g., the weight of the baby) from a data series of weight values. Similarly, body hydration and fluid retention can be determined from the data series of weight values. Optionally, other data, such as physical activity, heart rate, blood pressure, ultrasound, or impedance, can be obtained to determine the fluid content (i.e., to distinguish the baby's weight from the surrounding fluid and thus determine the fluid content). In some embodiments, an accelerometer at the subject's waist / abdomen can sense fetal growth by tilt increments.

[0081] Furthermore, the calculated recommended calorie intake can be associated with a nutritional recommendation unit that takes into account the target calories and the mother's preferred food types and recommends the amount of food.

[0082] Once again, the weight loss between two weight value measurements can be used to provide information related to the nutritional intake during pregnancy. Generally, the weight loss at night can be inferred that the weight is used to maintain the subject's body and appears in the form of water and heat loss. Therefore, all energy consumption will cause weight loss. If not all of the energy is consumed, it can be stored in the form of fat.

[0083] However, it has been recognized that for an individual during pregnancy, this mechanism is different. In addition to the usual energy consumption that causes weight loss and stores extra energy in fat, a pregnant subject also uses energy (and other nutrients) for fetal development. These proteins, fluids, minerals, and extra fat used for the baby's development are directly consumed through the baby's growth (and its own metabolic processes) or (temporarily) stored with the mother.

[0084] Thus, while precise measurements taken around sleep time in the early stages of pregnancy can provide information on total calorie intake and assess whether the intake is based on fat, carbohydrates, or protein, this becomes more complex as pregnancy progresses (i.e., as gestational age increases). Specifically, the nutritional intake of the subject may be underestimated. To account for this, additional terms related to the known energy usage of the developing baby at different stages of development are added to the model as energy usage that does not result in weight loss. Of course, this will be proportional to the gestational age of the subject. In other words, this type of energy usage will be proportional to the weight of the developing baby, and thus knowledge of the baby's weight (from, for example, ultrasound images) will improve the accuracy of the model.

[0085] Figure 1 A flowchart of a method for predicting a subject's future GWG according to an embodiment of the present invention is presented.

[0086] GWG is a natural response to accommodate fetal growth. The composition of GWG includes body components (fat, lean body mass), fetal weight, placenta, and amniotic fluid. However, both excessive and insufficient GWG can cause short-term and long-term health complications. Therefore, it is desirable to predict future GWG so that preventive or mitigating measures can be taken at an earlier stage (in response to a prediction of future GWG falling outside the recommended range).

[0087] This is achieved by using microweighting data or weight data measured at least twice a day during the early stages of pregnancy (e.g., the first 100 days or the first trimester of pregnancy) in the disclosed embodiments. By taking at least two weight readings per day, daily calorie intake and expenditure can be accounted for. Thus, an accurate understanding of the subject's historical GWG (i.e., the historical GWG curve) can be achieved. Additionally, by processing the data series with a GWG prediction model that also takes into account the gestational age of the subject (and thus the variability / dynamic nature of calorie consumption and storage during pregnancy), a GWG curve that accurately (i.e., close to the true value) describes the subject's historical GWG can be determined. Based on this determined GWG curve, future GWG value(s) can be generated.

[0088] In step 110, a data series of weight values is obtained. The data series of weight values describes the weight of the subject at least twice a day during the early stages of the subject's pregnancy and the corresponding gestational age of the subject. That is, the data series includes a plurality of weight values that describe the weight of the subject and the corresponding gestational age of the subject when those weight values were obtained.

[0089] Specifically, the data series of weight values can describe the weight of the subject before and after going to bed at least every day. If possible, the data series of weight values can describe the weight of the subject at least once per hour. These situations (i.e., when the weight of the subject is measured at least twice a day) can be described as micro - weighing of the subject, which enables the model to process the data sequence to account for the normal fluctuations in the subject's weight.

[0090] In addition, the data series of weight values can also describe the weight of the subject at least twice a day during a period before pregnancy. Thus, the weight changes attributable to pregnancy and those attributable to other sources can be more easily distinguished.

[0091] The data series can be obtained from a database or can be directly measured from a connected device, such as a dedicated set of scales.

[0092] In (optional) step 112, the data series is modified / augmented / corrected based on the subject background information. The subject background information can include any information related to the changes in the measured weight values of the subject such that the weight values can be standardized. For example, the subject background information can include at least one of the subject's movement, temperature, water loss, or resting metabolic rate during the early stages of pregnancy.

[0093] For example, if the subject has experienced a large amount of water loss, the weight value at this time can be adjusted to be larger.

[0094] In step 120, the data sequence is processed with a GWG prediction model. Thus, a historical GWG curve of the subject is determined / generated, which describes the GWG of the subject during the early stages of pregnancy.

[0095] The GWG prediction model can be a machine - learning model trained with a training algorithm using a training set. The training set can include the weight values of multiple subjects and a set of historical data series of the corresponding gestational ages, as well as the associated known GWG curves corresponding to each data series. Thus, the GWG prediction model can be trained to output a GWG curve in response to receiving a data sequence of weight values.

[0096] Alternatively, the GWG prediction model can be any model adapted to compensate for the dynamic calorie consumption and storage requirements during pregnancy, depending on the gestational age of the subject. Thus, the GWG prediction model is capable of generating a GWG curve that reflects the true GWG of the subject during the early stages of pregnancy. Specifically, the GWG prediction model can include a regression analysis model, such as a maximum a posteriori regression analysis model or a Gaussian process regression analysis model.

[0097] In step 130, the future GWG value of the subject is predicted based on the historical GWG curve. For example, a prediction of the GWG value of the subject at a certain moment in the second or third trimester of pregnancy is generated. The predicted future GWG value can be a numerical value (i.e., a specific weight), or it can be a categorical value (e.g., too high, too low, etc.).

[0098] The predicted future GWG value can then be adjusted based on weight-related physiological data. That is, weight-related physiological data describing at least one physiological parameter of the subject is obtained. Then, the predicted future GWG value is adjusted based on the obtained weight-related physiological data.

[0099] The at least one physiological parameter can include at least one of pre-pregnancy weight, pre-pregnancy BMI, age, height, race, stress value, pre-pregnancy lifestyle parameter value, or pregnancy lifestyle parameter value. However, any other physiological parameter related to the subject's weight and GWG can be considered.

[0100] Of course, the predicted future GWG value can be used for various purposes. The future GWG value can simply be output to the subject and / or medical expert for further analysis. In addition, based on the comparison between the future GWG value and the target GWG (i.e., the ideal GWG of the subject according to the IOM 2009 guidelines), a pregnancy risk score indicating the likelihood of pregnancy complications of the subject can be generated or increased / adjusted.

[0101] Other embodiments of the present invention can be based on additional steps, namely, generating at least one of current calorie intake data, current calorie consumption data, current calorie storage data, or current nutrition intake data based on the data series and the current gestational age of the subject. As described above, these parameters can be obtained from at least two daily weight measurements of the subject.

[0102] In this case, determining the historical GWG curve of the subject can also include processing at least one of the current calorie intake data, current calorie consumption data, current calorie storage data, or current nutrition intake data with a GWG prediction model. In fact, if calorie intake, consumption, and storage data as well as nutrition data are considered, the determined / generated historical GWG curve can be more accurate.

[0103] In addition, a recommendation describing a recommended change in the subject's lifestyle can be generated based on the future GWG value and at least one of the current calorie intake data, current calorie consumption data, current calorie storage data, or current nutrition intake data. In fact, these factors will directly affect the future GWG value. Therefore, adjusting one or more of these factors can make the adjustment of the true future GWG value closer to the target / ideal GWG value.

[0104] The recommendations can include calorie intake recommendations, nutritional intake recommendations, or exercise recommendations. When the recommendations include exercise recommendations, these can be adjusted based on gait information that describes the gait stability of the subject (such that the exercise recommendations are realistic and safe for the subject's capabilities).

[0105] Figure 2 A block diagram of a system 200 for predicting a subject's future GWG is presented. System 200 can implement any of the methods described above. Specifically, the system includes an interface 210 and a processor 220. System 200 can also include a weight measurement unit 230.

[0106] Specifically, interface 210 is configured to obtain a data series of weight values that describe the weight of the subject and the corresponding gestational age of the subject at least twice a day during the early stages of the subject's pregnancy.

[0107] Interface 210 can obtain the data series from a weight measurement unit 230 that is configured to measure the weight of the subject.

[0108] Processor 220 is configured to process the data sequence using a GWG prediction model to determine a historical GWG curve of the subject that describes the subject's GWG during the early stages of pregnancy.

[0109] In addition, processor 220 is configured to predict a future GWG value of the subject based on the historical GWG curve.

[0110] Figure 3 An example of a computer 1000 is illustrated, in which one or more portions of the embodiments can be employed. The various operations discussed above can utilize the capabilities of computer 1000. For example, one or more components of a system for obtaining input from a user to control an interface can be incorporated into any of the elements, modules, applications, and / or components discussed herein. In this regard, it should be understood that system functional blocks can operate on a single computer or can be distributed over several computers and locations (e.g., via an Internet connection). Additionally, computer 1000 can be implemented in a networked / distributed system, such as where computing occurs in the cloud.

[0111] Computer 1000 includes, but is not limited to, smart phones, PCs, workstations, laptops, PDAs, handheld devices, servers, memories, patient monitors, etc. In many cases, the disclosed systems and methods can be implemented in a patient monitor, such as a bedside monitor. Such monitors can be used, for example, in an intensive care unit (ICU), an operating room (OR), or a post-anesthesia care unit (PACU).

[0112] Generally speaking, in terms of the hardware architecture, the computer 1000 may include one or more processors 1010, a memory 1020, and one or more I / O devices 1030, which are communicatively coupled via a local interface (not shown). The local interface may be, for example but not limited to, one or more buses or other wired or wireless connections, as known in the art. The local interface may have additional elements, such as controllers, buffers (cache), drivers, repeaters, and receivers, to enable communication. In addition, the local interface may include address, control, and / or data connections to enable proper communication between the above components.

[0113] The processor 1010 is a hardware device for executing software that may be stored in the memory 1020. The processor 1010 may actually be any custom or commercially available processor, a central processing unit (CPU), a digital signal processor (DSP), a graphics processing unit (GPU), or an auxiliary processor among several processors associated with the computer 1000, and the processor 1010 may be a semiconductor-based microprocessor (in the form of a microchip) or a microprocessor.

[0114] The memory 1020 may include any one or combination of volatile memory elements (e.g., random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and non-volatile storage elements (e.g., ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic tape, compact disc read-only memory (CD-ROM), magnetic disk, floppy disk, cassette tape, cartridge tape, etc.). In addition, the memory 1020 may incorporate electronic, magnetic, optical, and / or other types of storage media. It should be noted that the memory 1020 may have a distributed architecture, where various components are located far from each other but can be accessed by the processor 1010.

[0115] The software in the memory 1020 may include one or more separate programs, each program including an ordered list of executable instructions for implementing logical functions. According to an exemplary embodiment, the software in the memory 1020 includes a suitable operating system (O / S) 1050, a compiler 1060, source code 1070, and one or more applications 1080. As shown, the application 1080 includes a plurality of functional components for implementing the features and operations of the exemplary embodiment. According to an exemplary embodiment, the application 1080 of the computer 1000 may represent various applications, computing units, logics, functional units, processes, operations, virtual entities, and / or modules, but the application 1080 is not intended to be limiting.

[0116] The operating system 1050 controls the execution of other computer programs and provides scheduling, input / output control, file and data management, memory management, communication control, and related services. The application 1080 for implementing the exemplary and comparative embodiments may be applicable to all (general-purpose) operating systems.

[0117] The application 1080 may be a source program, an executable program (object code), a script, or any other entity including a set of instructions to be executed. When it is a source program, the program is typically translated via a compiler (such as compiler 1060), an assembler, an interpreter, etc., and these programs may or may not be included in the memory 1020 to operate correctly in conjunction with the O / S 1050. Additionally, the application 1080 may be written in an object-oriented programming language having data and method classes, or a procedural programming language having routines, subroutines, and / or functions, such as but not limited to C, C++, C#, Pascal, Python, BASIC, API calls, HTML, XHTML, XML, ASP scripts, JavaScript, FORTRAN, COBOL, Perl, Java, ADA,.NET, functional programming, and so on.

[0118] The I / O device 1030 may include input devices such as but not limited to a mouse, a keyboard, a scanner, a microphone, a camera, a touch screen, etc. Additionally, the I / O device 1030 may also include output devices such as but not limited to a printer, a display, etc. Finally, the I / O device 1030 may also include devices that transfer input and output, such as but not limited to a NIC or a modem / demodulator (for accessing remote devices, other files, devices, systems, or networks), a radio frequency (RF) or other transceiver, a telephone interface, a bridge, a router, etc. The I / O device 1030 also includes components for communicating via various networks such as the Internet or an intranet.

[0119] If the computer 1000 is a PC, a workstation, a smart device, etc., the software in the memory 1020 may also include a basic input / output system (BIOS) (omitted for simplicity). The BIOS is a set of basic software routines that initialize and test the hardware at startup, start the O / S 1050, and support data transfer between hardware devices. The BIOS is stored in a type of read-only memory such as ROM, PROM, EPROM, EEPROM, etc., so that the BIOS can be executed when the computer 800 is activated.

[0120] When computer 1000 is running, processor 1010 is configured to execute software stored in memory 1020, transfer data to and from memory 1020, and generally control the operation of computer 1000 according to the software. Application 1080 and O / S 1050 are read in whole or in part by processor 1010, may be buffered in processor 1010, and then executed.

[0121] When application 1080 is implemented in software, it should be noted that application 1080 can be stored on almost any computer-readable medium for use by or in conjunction with any computer-related system or method. In the context of this document, a computer-readable medium can be an electronic, magnetic, optical, or other physical device or apparatus that can contain or store a computer program for use by or in conjunction with a computer-related system or method.

[0122] Application 1080 can be embodied in any computer-readable medium for use by or in conjunction with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can obtain instructions from and execute the instructions of an instruction execution system, apparatus, or device. In the context of this document, a "computer-readable medium" can be any device that can store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0123] Regarding Figure 1 the methods described and regarding Figure 2 the systems described can be implemented in hardware or software or a combination of both (e.g., as firmware running on a hardware device). To the extent that an embodiment is implemented in whole or in part in software, the functional steps shown in the process flow diagrams can be performed by a suitably programmed physical computing device, such as one or more central processing units (CPUs) or graphics processing units (GPUs). Each process and the individual component steps shown in its process flow diagram can be performed by the same or different computing devices. According to an embodiment, a computer-readable storage medium stores a computer program including computer program code that is configured to cause one or more physical computing devices to perform the encoding or decoding methods described above when the program runs on the one or more physical computing devices.

[0124] The storage medium may include volatile and non-volatile computer memories such as RAM, PROM, EPROM, EEPROM, and SSD, optical discs (such as CD, DVD, BD), and magnetic storage media (such as hard disks and magnetic tapes). The various storage media may be fixed within the computing device or may be transportable such that one or more programs stored thereon can be loaded into the processor.

[0125] To the extent that embodiments are implemented in whole or in part in hardware, Figure 2 the blocks shown in the block diagrams may be separate physical components, or logical subdivisions of a single physical component, or may all be implemented in an integrated manner in one physical component. The functionality of a single block shown in the drawings may be divided among multiple components in an implementation, or the functionality of multiple blocks shown in the drawings may be combined in a single component in an implementation. Hardware components suitable for embodiments of the present invention include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs). One or more blocks may be implemented as a combination of dedicated hardware performing some functions and one or more programmed microprocessors and associated circuitry performing other functions.

[0126] Upon study of the drawings, the disclosure, and the appended claims, those skilled in the art will be able to understand and implement variations of the disclosed embodiments when practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may implement the functions of several items recited in the claims. The fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. If a computer program is discussed above, it may be stored / distributed on a suitable medium, such as an optical storage medium or a solid state medium provided together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. If the term "adapted to" is used in the claims or the specification, it should be noted that the term "adapted to" is intended to be equivalent to the term "configured to". Any reference signs in the claims should not be construed as limiting the scope.

[0127] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of the possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of instructions that includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Claims

1. A method for predicting a subject's future gestational weight gain (GWG), comprising: obtaining (110) a data series of weight values ​​describing the subject's weight at least twice daily during an early stage of the subject's pregnancy and the subject's corresponding gestational age; Processing the data series with a GWG prediction model to determine (120) a historical GWG curve for the subject, the historical GWG curve describing the subject's GWG during the early stages of the pregnancy; and A future GWG value of the subject is predicted (130) based on the historical GWG curve.

2. The method according to claim 1, wherein the data series of weight values ​​describes the weight of the subject before and after sleeping at least every day.

3. The method according to claim 1 or 2, wherein the data series of weight values ​​describes the weight of the subject at least once every hour.

4. The method according to any one of claims 1 to 3, wherein the data series of weight values ​​further describes the weight of the subject at least twice a day during a period before pregnancy.

5. The method according to any one of claims 1 to 4 further comprises generating at least one of current calorie intake data, current calorie expenditure data, current calorie storage data or current nutritional intake data based on the data series and the current gestational age of the subject.

6. The method of claim 5, wherein determining (120) the historical GWG curve of the subject further comprises processing at least one of the current calorie intake data, the current calorie expenditure data, the current calorie storage data, or the current nutritional intake data with the GWG prediction model.

7. The method of claim 5 or 6, further comprising generating a recommendation describing a recommended change to the subject's lifestyle based on the future GWG value and at least one of the current calorie intake data, the current calorie expenditure data, the current calorie storage data, or the current nutritional intake data, and Optionally, wherein the recommendation comprises a calorie intake recommendation, a nutrient intake recommendation, or an exercise recommendation.

8. The method of claim 7, wherein the recommendation comprises an exercise recommendation, further comprising adjusting the exercise recommendation based on gait information describing the subject's gait stability.

9. The method according to any one of claims 1 to 8, further comprising modifying (112) the data series based on subject background information describing at least one of the subject's movement, temperature, water loss, cardiovascular activity, or resting metabolic rate during the early stages of the subject's pregnancy.

10. The method according to any one of claims 1 to 9, further comprising: obtaining weight-related physiological data describing at least one physiological parameter of the subject; as well as adjusting the predicted future GWG value based on the obtained physiological data related to body weight, and Optionally, the at least one physiological parameter comprises at least one of pre-pregnancy weight, pre-pregnancy BMI, age, height, race, stress value, pre-pregnancy lifestyle parameter value or pregnancy lifestyle parameter value.

11. A method according to any one of claims 1 to 10, wherein processing the data series to determine (120) the historical GWG curve includes processing the data series with a regression analysis model, and wherein predicting (130) the future GWG value of the subject includes extrapolating the historical GWG curve.

12. The method according to any one of claims 1 to 11, further comprising generating a pregnancy risk score indicative of the likelihood of complications during pregnancy of the subject based on a comparison between the future GWG value and a target GWG.

13. The method of any one of claims 1 to 12, further comprising processing the data series with a weight-derived prediction model to determine fetal weight, subject hydration values, and fluid retention values.

14. A computer program comprising computer program code means adapted to implement the method according to any one of claims 1 to 13 when said computer program is run on a computer.

15. A system for predicting a subject's future gestational weight gain (GWG), comprising: an interface (210) configured to obtain a data series of weight values ​​describing the subject's weight at least twice daily during an early stage of the subject's pregnancy and the subject's corresponding gestational age; as well as A processor (220), the processor being configured to: Processing the data series with a GWG prediction model to determine a historical GWG curve for the subject, the historical GWG curve describing the subject's GWG during the early stages of the pregnancy; and The future GWG value of the subject is predicted based on the historical GWG curve.

Images