Method and system for determining gut microbiome maturation status in infants

Abstract

The present invention provides a method, system and computer program product for determining the maturity state of an infant between 0 and 120 months of age, comprising: measuring at least one microbial biomarker of a set of measurable microbial biomarkers of a sample of faeces of the infant; determining a predicted age of the infant based on the at least one microbial biomarker; wherein the at least one microbial biomarker is selected from the group of measurable microbial biomarkers based on analysis of the group of measurable microbial biomarkers as measured in faeces samples of breast-fed infants from a plurality of vaginal births of a plurality of ages, based on the evaluation of the at least one measured microbial biomarker, the predicted age is obtained using a function based on a plurality of respective at least one biomarker measured in a faeces sample of a breast-fed infant from a plurality of vaginal births of a plurality of ages.

Description

Technical Field

[0001] The present invention relates to a method, system and computer program product for determining the maturation state of an infant. In particular, the present invention relates to a method and system for determining the maturation state of the intestinal microbiome of an infant based on microbial biomarkers in a stool sample, wherein the infant is between 0 and 120 months of age. Background Art

[0002] Not all infants develop at the same rate in early life. Therefore, two infants of the same chronological age may be at different stages of development and therefore may, for example, have different nutritional needs. In this application, this difference is referred to as the infant's gut microbiome maturity state.

[0003] Furthermore, if there is a significant delay in the development of an infant compared to other infants of the same chronological age, this may, for example, indicate an underlying medical condition that should be diagnosed and treated as soon as possible.

[0004] Therefore, there is a need to be able to determine the state of gut microbiome maturation in infants and young children. Summary of the invention

[0005] The object of the present invention is to provide a method and system for determining the maturity state of the intestinal microbiome of infants and young children.

[0006] According to one aspect of the present disclosure, the present invention provides a method for determining the maturity status of an infant between 0 and 120 months of age, the method comprising measuring at least one microbial biomarker from a set of measurable microbial biomarkers in a stool sample of the infant, determining a predicted age of the infant based on the at least one microbial biomarker, wherein the at least one microbial biomarker is selected from the set of measurable microbial biomarkers based on analysis of the set of measurable microbial biomarkers as measured in stool samples of multiple vaginally born, breastfed infants of multiple ages, and based on an evaluation of the at least one measured microbial biomarker, the predicted age is obtained using a function based on a plurality of corresponding at least one biomarker measured in stool samples of multiple vaginally born, breastfed infants of multiple ages.

[0007] As an alternative or in addition to the maturity status, the present invention may provide an estimated microbial age.The present invention may provide the difference between the estimated microbial age and the actual age of an infant.

[0008] In an embodiment, the method is applicable to determining the microbial age of an infant between 0 and 120 months of age, or between 0 and 96 months of age, or between 0 and 72 months of age, or between 0 and 60 months of age, or between 0 and 48 months of age, or between 0 and 36 months of age. The method may be applicable to determining the microbial age at intervals of 1 week, 2 weeks, 3 weeks, 4 weeks, 1 month, 2 months, or 3 months. The method may be applicable to determining a reliability estimate of the determined microbial age.

[0009] When the present disclosure refers to microbial biomarkers, it is understood that they may include measurements related to any biological molecule and process. In addition, biomarkers may include, for example, measurements of stool consistency, stool color, or stool pH.

[0010] In an embodiment, linear regression is used for analysis.

[0011] In an embodiment, the function is based on a model, preferably a machine learning model, trained using a set of measurable microbial biomarkers as measured in stool samples from multiple vaginally born, breastfed infants of multiple ages.

[0012] In an embodiment, the at least one biomarker is selected based on a model, preferably a machine learning model, using a panel of measurable microbial biomarkers as measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages.

[0013] In an embodiment, at least three microbial biomarkers from a stool sample are used. In an embodiment, at least four, five, six, eight or ten biomarkers are used. In general, the more microbial biomarkers used, the more accurate the model (up to a certain number of microbial biomarkers).

[0014] In an embodiment, the at least one microbial biomarker is selected based on a stable parameter. In an embodiment, at least one microbial biomarker is selected to minimize the difference between the actual age and the estimated microbial age of a reference biomarker group (e.g., a group of vaginally born breastfed infants of multiple ages).

[0015] According to one aspect of the present disclosure, the present invention provides a system for determining the maturation status of an infant between 0 and 120 months of age, the system comprising: - a measuring device adapted to measure at least one microbial biomarker of a set of measurable microbial biomarkers of the infant stool sample, - a processing device for determining a predicted age of the infant based on the at least one microbial biomarker, wherein the at least one microbial biomarker is selected from a group of measurable microbial biomarkers based on analysis of the at least one microbial biomarker as measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages, the predicted age being obtained based on an evaluation of the at least one measured microbial biomarker using a function based on a plurality of corresponding at least one biomarker measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages.

[0016] In an embodiment, linear regression is used for analysis.

[0017] In an embodiment, the function is based on a model, preferably a machine learning model, trained using a set of measurable microbial biomarkers as measured in stool samples from multiple vaginally born, breastfed infants of multiple ages.

[0018] In an embodiment, the at least one biomarker is selected based on a model, preferably a machine learning model, using a panel of measurable microbial biomarkers as measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages.

[0019] In embodiments, the at least one microbial biomarker from a stool sample comprises at least three microbial biomarkers.

[0020] In embodiments, the at least one microbial biomarker is selected based on a stability parameter.

[0021] According to another aspect of the disclosure, the present invention provides a computer program product comprising machine-readable instructions which, when executed on a processing device, cause the device to operate according to the above method or system.

[0022] According to another aspect, a processing and storage system is provided, wherein the storage portion includes reference biomarker data for determining selected biomarkers and microbial age assessment functions. The processing portion may include means for accessing the data and / or performing statistical analysis on the data (as described elsewhere in this disclosure). The processing portion may include models (e.g., deep learning models) or other analysis instructions, as described elsewhere in this disclosure, particularly with reference to Figure 2 , used to determine selected biomarkers and / or microbial age assessment functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Embodiments of the present invention will be described below by way of example only with reference to the accompanying drawings, which are schematic in nature and are not necessarily drawn to scale. In addition, the same reference numerals in the drawings refer to the same elements.

[0024] In the attached picture: · Figure 1 A system for determining the maturational status of infants and young children is schematically shown; · Figure 2 Schematically depicts a method for obtaining reference microbial biomarkers and selecting biomarkers and microbial age determination functions according to an embodiment of the present invention; · Figure 3 Schematically depicts a method for determining the maturity status of an infant according to an embodiment of the present invention, and · Figure 4 Components that may be used in an electronic device embodying the present invention are schematically depicted. DETAILED DESCRIPTION

[0025] The human microbiome is the collection of human microorganisms and their genes that reside on or in human tissues and biofluids and the corresponding anatomical sites (including skin and organs) where they reside. The presence of certain microbial taxa and their genes may indicate the status of the specific part of the human body where the microbiome resides.

[0026] Furthermore, the development of the microbiome is important because it indicates the development of a part of the human body at a given age. If the development is lower than expected given the actual age of the person, nutrition can be adjusted (e.g., through food and beverages) to match the developmental stage of the microbiome. If the developmental stage deviates from the actual age given, nutrition can also be adjusted accordingly.

[0027] Since the development of the microbiome during infancy and childhood has an impact on the human body throughout life, it is recommended to determine the microbial age as early as possible, preferably already in infancy and childhood, especially if it deviates from the child’s actual age. For example, certain nutritional products for children of a certain age may or may not be suitable, depending on the microbial age.

[0028] A preferred method of assessing the microbial age of an infant (or young child) is to determine the intestinal microbiome maturity state of said infant. The intestinal microbiome maturity state of an infant is a comparison of the predicted microbial age obtained from the infant with the actual age.

[0029] like Figure 1As shown, this can be done by analyzing biomarkers in fecal matter (F) using a biomarker measurement device 10. Multiple measuring devices (not shown) can be used to measure multiple biomarkers. The biomarker data is then sent to an evaluation device 11 having a display 12 for displaying the results of the evaluation of the biomarker data. The display can include a predicted (microbial) age based on the evaluation of the biomarker data.

[0030] Displaying the results may include displaying the infant's microbial age and actual age, preferably in a manner that shows any differences between the two. For example, by plotting the infant's actual age on the X-axis and the determined microbial age on the Y-axis, where a diagonal line X=Y indicates that the microbial age matches the actual age, and any data points below the diagonal line (e.g. Figure 1 The data points above the diagonal line would indicate that the infant's microbial development was slightly delayed (compared to the reference), while the data points above the diagonal line would indicate that the infant's microbial development was slightly advanced, again compared to the reference ( Figure 2 discussed in the context of ).

[0031] The evaluation device 11 may be a mobile phone running a biomarker measurement and / or analysis application. In an embodiment, the biomarker measurement device 10 is integrated with the evaluation device 11 so that only a single device is required.

[0032] Hereinafter, it will be understood that, unless otherwise specified, "microbial biomarkers" may refer to the entire panel of microbial biomarkers or a selected subset of the entire panel of microbial markers that is determined, for example using statistical or machine learning analysis, to be indicative of the actual age of an infant in a reference group of microbial biomarker data from vaginally born, breastfed infants. Obtain reference microbial biomarkers, select biomarkers, and obtain age determination functions

[0033] The method for obtaining reference microbial biomarkers, analyzing and selecting biomarkers, and determining age determination functions is schematically shown in Figure 2 middle.

[0034] In step S200, fecal matter or other material of an infant with certain reference characteristics is measured. Microbial biomarkers are obtained from a reference infant through fecal matter discharged from the infant. The fecal matter is then processed to obtain a set of reference biomarkers. Although it is preferred to obtain microbial biomarker data from fecal matter, it can also be obtained from other excreta and / or secretions, such as saliva, mucus, tears, skin or body surface excreta. By analyzing these excreta and secretions, the microbial age of the infant can be determined in a non-invasive manner.

[0035] In an embodiment, the reference biomarker is a set of measurable microbial biomarkers, such as measured in stool samples of multiple vaginally born, breast-fed infants of multiple ages. The actual age of the reference infant is known, and by definition, the reference infant is considered to have a microbial age that matches its actual age. In step S201, a reference database can be compiled from the measured biomarkers of the reference infant and its actual age. It should be noted that other reference infant characteristics can be used, such as bottle-fed infants and infants born by caesarean section. Importantly, the reference biomarkers are measured in samples of a group with well-defined characteristics.

[0036] By compiling multiple microbial biomarkers based on the age of the (reference) infant, data for all infant ages (within a specific age range) can be generated that are comparable to each other. In particular, the nutritional requirements of vaginally born, breastfed infants as they develop are well known. By correlating the actual age of an average vaginally born, breastfed infant with the microbial age, a child's nutritional requirements can be better estimated than from the child's actual age alone.

[0037] In step S202, the set of reference biomarkers is then analyzed to determine a subset of biomarkers, perhaps only one, two or three biomarkers, that are considered most suitable for predicting the microbial age and chronological age of the reference infant. For example, biomarkers that remain nearly constant during the first 120 months of infancy are not sensitive to age and are therefore not suitable for predicting the microbial age of an infant. In contrast, biomarkers that show strong age dependence can be used to predict the microbial age of an infant.

[0038] The reference microbial biomarker model (hereinafter "reference model" or "model") is created by obtaining microbial biomarker information from fecal samples of vaginally born, breastfed infants sampled at different stages of infant development, for example, within the first 10 years after birth. The time sampling step is preferably in units of one day, however, the step can also be one week, or one month, two months, three months or any other constant or non-constant interval size.

[0039] Preferably, the reference model comprises data from infants at an age representative of the initial stage of infancy, preferably at least the first 10 years of life, more preferably at least the first (ie from zero to) 8, 6, 5, 4 or 3 years.

[0040] In an embodiment, linear regression is used as part of the analysis. In another or the same embodiment, a model is used as part of the analysis, particularly a machine learning model. For example, all available measured biomarkers can be provided to the machine learning model and then trained to determine the actual age. As part of the training, the machine learning model may be forced to select the most appropriate biomarkers so that the model learns which selected biomarkers in the entire set of biomarkers are most relevant to the determination of age.

[0041] The machine learning model can be a deep learning network. The machine learning model can be an artificial neural network (ANN). It can include a convolutional neural network (CNN) and / or a residual neural network (ResNet). The machine learning model can use an automatic encoder with a potential space restriction that is constrained to force the model to encode only the most important subset of biomarkers. The above combination can be used to form a model. In an embodiment, the trained model is analyzed to determine which biomarkers are the most important. For example, in a linear or nonlinear model, the training weights of a single biomarker input are analyzed to determine which biomarkers have the most influence on determining the age of the microorganisms in the trained model.

[0042] Since new reference data is still coming in, the analysis of the model can also be performed incrementally. This also allows the user to receive an alert when the reference microbial biomarker samples of some age ranges cannot generate a reference model. Then, the user can take action to fill in the missing age range (for example, by obtaining more data samples or even by extrapolation and other means). The age interval can be for each reference age (for example, between 0 and 3, 4, 5, 6, 8 or 10 years old, the interval is 1 day, 1 week, 1 month, 2 months, 3 months). For the interval, it may be finer at a younger age (for example, 1 week for infants aged 0-3 months) than at a higher age (for example, 1 month for infants over 1 year old).

[0043] To determine the predicted age of new infants (infants not included in the database), it is necessary to Figure 3 A match is found between the microbial biomarker group obtained in step S300 and the microbial biomarker reference database set of the corresponding reference age (using a certain metric, such as a metric generated by a machine learning model or a statistical method). Those skilled in the art will use other available statistical tools to achieve the goal of determining the predicted age in step S301 based on the microbial biomarkers obtained in step S300 and the data in the reference database.

[0044] As a way to determine the robustness of the reference model, the model can be subjected to a cross-validation check. Cross-validation is a resampling method that uses different parts of the data to test and train the model at different iterations. This allows the cross-validations to be combined (or averaged) to derive a more accurate estimate of the model's predictive performance.

[0045] As part of the analysis, the number of biomarkers selected can be weighed. Selecting fewer markers makes the method of determining the microbial age of infants and young children (such as reference Figure 1 and Figure 3 The above) is easier to apply, but at the expense of some precision. Selecting more markers usually makes the determination more precise, but in practice, measuring more biomarkers is more complicated.

[0046] After the analysis of the biomarkers obtained from the reference infant, whether using (human) statistical analysis, linear or nonlinear regression analysis or machine learning models, the following are determined: 1) as part of step S203, a subset of one or more biomarkers from the entire set of measurable biomarkers that are considered sufficient to determine the microbial age with the desired reliability, and 2) as part of step S204, an evaluation function (model, mathematical function, chart, etc.) for determining the microbial age of the infant based on the measurement of the selected biomarkers from the infant. It should be noted that step S203 can also occur in whole or in part after step S204. Step S203 can include manual (hand-picked) (pre) selection and / or machine (e.g., by a model) selection of biomarkers. This increases the flexibility of selecting the best subset for the necessary analysis.

[0047] In an embodiment, a subset of microbial biomarkers is selected based on one or more stability parameters. For example, the subset can be based on one or more hand-picked biomarkers known to predict microbial age. Then, for example, when predicting microbial age, such biomarkers can be given greater weight.

[0048] The evaluation function for determining the microbial age of an infant (hereinafter referred to as "function") is usually in digital form, for example, as a weight in a trained linear or nonlinear model, as a programmed mathematical function, etc. The digital form of the device can be implemented in many ways, for example, as Figure 1 The evaluation device (e.g. mobile phone) 11 may be Figure 3 or Figure 4 A function may be part of a device used in (see below), as a separate server accessible by said portable device over a network, or any other digital processing means available to the skilled person. A function may be a procedure implemented in a programming code running on a processor.

[0049] In an embodiment, different biomarkers or determination functions are selected at different ages. For example, on average, different biomarkers are better at predicting microbial age for infants aged 0 to 12 months than for infants aged 12 months and above.

[0050] In an embodiment, analysis of reference microbial biomarkers produces a set of reference profiles for selected biomarkers for age (e.g., age ranges in 1 month or 1 week intervals). The function used to determine microbial age may then involve searching for the most relevant match between biomarkers measured in infants with unknown microbial age and a set of reference profiles with relevant reference ages, or it may be a general (training) function that takes the selected biomarkers as input. Determining the maturity of the gut microbiome in infants and young children

[0051] The steps used to determine the predicted microbial age and intestinal microbiome maturity state of infants and young children are schematically shown in Figure 3 Predicted (microbial) age is the age determined by analyzing selected microbial biomarkers present in fecal material.

[0052] First, in step S300, a selected subset of biomarkers (e.g., one or more biomarkers considered most relevant based on a reference database for determining the microbial age of an infant) is measured. This can be done using a measuring device, such as Figure 1 The device 10 shown in FIG. 1 is configured to perform the task of identifying microbial biomarkers from fecal material. Any device can perform this task as long as the device includes means for receiving fecal material, identifying microbial biomarkers, and generating a data file suitable for use by an electronic device. For example, the fecal material can be analyzed by a dedicated stand-alone machine, or can even be transported to a laboratory for analysis, where the laboratory sends the data file to the electronic device.

[0053] The output in this step can be a data file comprising all microbial biomarkers present in the fecal material of the baby. Alternatively, it can only include selected biomarkers, as determined in the analysis of steps S202 and S203. In other words, it can be determined that only a subset of microbial biomarkers can be necessary for determining a reliable microbial age, so a data file can be generated based on partially selecting all microbial biomarkers from the original data file. This generation of new data files can be performed on portable mobile devices, personal computers (PCs), or performed by cloud computing or any other electronic and / or virtual devices.

[0054] Examples of microbial biomarkers are Bifidobacteriaceae species, butyrate and lactic acid producers.

[0055] In step S301, the determined function is used to determine the microbial age of the infant based on the measured biomarker subset. This can be done in the same device as step S301 or in a different assessment device (e.g. Figure 1 The analysis may be performed in a portable mobile device 11 as shown in FIG. If a different device is used, the data file with the measured biomarkers may be provided over a wired or wireless network or on a portable physical storage medium (for analysis on the portable electronic device). The output of the analysis may be a display screen that outputs a visualization of the predicted age and maturity status in the form of a graphical output.

[0056] According to an embodiment of the present invention, in step S301, the predicted microbial age is determined based on the multiple microbial biomarkers available in the stool sample F. This determination can be performed using Figure 2 Any function that is described in more detail in the context of .

[0057] Although it is usually preferred to use a pre-trained model as the microbial age determination function, it is also possible to Figure 2 This training is done dynamically using the reference database. Figure 2 Some of the options discussed do not use pre-trained models. For example, if as part of the analysis, the reference database is organized into a set of reference biomarker profiles for reference ages, then microbial age determination can include finding a reference age associated with the reference biomarker profile that most closely matches (using a suitable matching metric function to calculate the distance between biomarker groups) the measured biomarker subset. This is also a convenient approach in cases where some biomarkers are not always available. Matching metric functions can be designed to account for missing biomarker data in the measured subset.

[0058] In addition, in the determination step of S301, the input of the actual age can also narrow the range of possible ages, thereby predicting the age more accurately. Figure 2 As discussed in the context of , when selecting different biomarkers or determination functions at different ages, a rough indication of the infant's age can be used as an input to ensure that the correct biomarker subset and / or age determination function is used.

[0059] By comparing the actual age of the infant (e.g., requested by the analysis device as user input) with the determined microbial age, the intestinal microbiome maturity state of the infant is determined in step S302. The result can be output on a display screen of the electronic device. The output can also include a deviation of the predicted age from the actual age (i.e., the intestinal microbiome maturity state) displayed in graphical form, so that the user can more easily understand the information.

[0060] Preferably, three or more microbial biomarkers are used in the selected microbial biomarker subset. Application of the maturation status of the intestinal microbiome in infants and young children

[0061] Once the maturation state of an infant is determined, the system can be configured to provide recommendations to increase / decrease the abundance of certain microbial biomarkers for a particular infant. This can be done by suggesting certain diets or supplements. In an embodiment, these recommendations are automated, for example, in the evaluation device 11, for example as part of a programmed expert system or other recommendation system.

[0062] The maturity of the gut microbiome can be used to alert significant gaps between predicted age and actual age. Such gaps can indicate underlying medical conditions that cause the "microbial age" (predicted age) to be significantly lower (or higher) than actual age.

[0063] According to another aspect of the present invention, a system for determining the maturity state of the intestinal microbiome of an infant is described. The system can be a reference Figure 1 , 2 And / or computer implementation of the method described in 3.

[0064] Figure 4 A portable electronic device 40 according to an embodiment of the present invention is depicted. The system may be embodied as Figure 1 The portable electronic device may include a transceiver 41 for receiving microbial biomarker data and for transmitting / receiving information that can be used in determining a predicted age. The portable electronic device may have an optional measurement input 42 for analyzing fecal matter or for obtaining information obtained by another device ( Figure 4 The portable electronic device further includes a storage medium 44 and a processor 43, the storage medium is used to store microbial biomarker data and other data, such as data related to the evaluation function, and the processor is configured to perform the steps of predicting the age of the infant based on the microbial biomarker data in the received stool sample (microbial biomarker) data, and determine the maturity state of the infant. The processor can also be configured to process the machine learning algorithm described herein. The portable electronic device can also include a display unit 45, which is configured to output the maturity state and / or predicted age of the infant.

[0065] The displayed output can be in the form of text (alphanumeric) as well as visual output such as graphs and charts. Figure 1As shown, the maturity state can be displayed on a graph showing a comparison of the predicted age with the actual age. The display unit can also be configured with an interactive module so that the user can select information on the display for additional processing. For example, once the predicted age is displayed, the display unit can output the microbial biomarkers used for calculation. The user can then select a subset of the microbial biomarkers, or other microbial biomarkers not used in the prediction, and cause the portable electronic device to perform the prediction again (using the processor).

[0066] In the foregoing description of the drawings, the invention has been described with reference to specific embodiments thereof. However, it will be apparent that various modifications and changes may be made thereto without departing from the scope of the invention as outlined in the appended claims.

[0067] In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.

[0068] In particular, specific features of various aspects of the invention may be combined. One aspect of the invention may be further advantageously enhanced by adding features described in relation to another aspect of the invention.

[0069] It should be understood that the present invention is limited only by the appended claims and their technical equivalents. In this document and its claims, the verb "comprise" and its conjugation are used in its non-restrictive sense, meaning to include the items behind the word, but not excluding items not specifically mentioned. In addition, referring to an element by the indefinite article "a or an" does not exclude the possibility of more than one element, unless the context clearly requires one and only one element. Therefore, the indefinite article "a or an" usually means "at least one".

Claims

1. A method for determining the maturation status of an infant between 0 and 120 months of age, the method comprising - measuring at least one microbial biomarker from a panel of measurable microbial biomarkers in a stool sample of the infant, - determining the predicted age of the infant based on the at least one microbial biomarker, wherein - the at least one microbial biomarker is selected from the panel of measurable microbial biomarkers based on analysis of the panel of measurable microbial biomarkers as measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages, - based on the evaluation of the at least one measured microbial biomarker, obtaining the predicted age using a function based on a plurality of corresponding at least one biomarker measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages.

2. The method of claim 1, wherein the analysis is performed using linear regression.

3. The method of claim 1 or 2, wherein the function is based on a model, preferably a machine learning model, trained using the set of measurable microbial biomarkers as measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages.

4. The method of claim 3, wherein the at least one biomarker is selected based on the model.

5. The method according to any one of the preceding claims, wherein at least three microbial biomarkers from the stool sample are used.

6. The method of any of the preceding claims, wherein the at least one microbial biomarker is selected based on a stability parameter.

7. A system for determining the maturational status of an infant between 0 and 120 months of age, the system comprising: - a measuring device adapted to measure at least one microbial biomarker of a set of measurable microbial biomarkers of the infant stool sample, - processing means for determining the predicted age of the infant based on the at least one microbial biomarker, in - the at least one microbial biomarker is selected from the panel of measurable microbial biomarkers based on analysis of the panel of measurable microbial biomarkers as measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages, - based on the evaluation of the at least one measured microbial biomarker, obtaining the predicted age using a function based on a plurality of corresponding at least one biomarker measured in stool samples from a plurality of vaginally born, breastfed infants of a plurality of ages.

8. The system of claim 7, wherein the analysis is performed using linear regression.

9. The system of claim 7 or 8, wherein the function is based on a model, preferably a machine learning model, trained using the set of measurable microbial biomarkers as measured in stool samples from multiple vaginally born, breastfed infants of multiple ages.

10. The system of claim 9, wherein the at least one biomarker is selected based on the model.

11. The system of any of the preceding claims 7-10, wherein at least three microbial biomarkers from the stool sample are used.

12. The system of any of the preceding claims 7-11, wherein the at least one microbial biomarker is selected based on a stability parameter.

13. A computer program product comprising machine readable instructions which, when executed on a processing device, cause the device to operate according to any one of claims 1 to 6.

Images