Systems and methods for aggregating and presenting cohort information associated with a pregnancy

Abstract

The disclosed computer-implemented method can include receiving, from a user via a user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy. The method can also include generating, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key representative of the set of attributes. The method can further include using the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature, and identifying, based on the cohort of pregnancies, at least one consideration for the subject. The method can also include creating a pregnancy report that provides the at least one consideration for the subject. Various other methods, systems, and computer-readable media are also disclosed.

Description

SYSTEMS AND METHODS FOR AGGREGATING AND PRESENTING COHORT INFORMATION ASSOCIATED WITH A PREGNANCYCROSS REFERENCES TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Application No. 63 / 550,331, titled "Systems and Methods for Aggregating and Presenting Cohort Information Associated with a Pregnancy," filed February 6, 2024, and U.S. Application No. 63 / 735,672, titled "Systems and Methods for Aggregating and Presenting Cohort Information Associated with a Pregnancy," filed December 18, 2024, each of which is hereby incorporated in its entirety by this reference.BACKGROUND

[0002] Pregnancy management traditionally relies on generalized medical guidelines that apply broad strokes of healthcare practices to expectant mothers. Conventional resources provide a one-size-fits-all approach, averaging out the pregnancy experience. However, pregnancy is a deeply personal and complex journey that varies greatly from one individual to another, influenced by a myriad of factors including, but not limited to, genetic makeup, health history, lifestyle choices, and environmental conditions. Conventional systems often fall short in personalizing the pregnancy experience, leading to a gap in offering individualized information, care, and support.

[0003] Moreover, the utilization of pregnancy data for generating insights has been largely rudimentary, with conventional systems not taking full advantage of the vast amounts of data available. Individuals experiencing pregnancy often lack access to information that reflects their unique circumstances and are left with general advice that may not be applicable to their specific situation. Traditional methods have not adequately leveraged the potential of modern statistical and machine learning techniques to analyzepregnancy data, nor have they provided the tools necessary for healthcare providers and expectant mothers to understand and utilize this data in a meaningful way. There is a clear need for an advanced system that can analyze diverse pregnancy-related data sets to deliver customized guidance and support.SUMMARY

[0004] In some aspects, the techniques described herein relate to a computer- implemented method including: receiving, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; generating, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes; using the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; identifying, based on the cohort of pregnancies, at least one consideration for the subject; and creating a pregnancy report that provides the at least one consideration for the subject.

[0005] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy includes at least one of: a demographic characteristic; a health characteristic; a prior pregnancy characteristic; or a current pregnancy characteristic.

[0006] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy includes at least one of: an indication of whether a gestational parent is nulliparous; an age of at least one patient associated with the pregnancy; a bodymass index (BMI) of the at least one patient; a race of the at least one patient; a set of riskfactors associated with the at least one patient; or biomarker data associated with the at least one patient.

[0007] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy includes subject biomarker data associated with time to birth.

[0008] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy includes at least one of the attributes listed in Table 1.

[0009] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the at least one feature includes at least one of the features listed in Table 2.

[0010] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the pregnancy report includes at least one of: an indication of a degree of similarity of the pregnancy to other pregnancies in the cohort; educational information associated with at least one point of similarity of the pregnancy to other pregnancies in the cohort; educational information associated with at least one point of dissimilarity of the pregnancy to other pregnancies in the cohort; at least one suggested question regarding the pregnancy for a patient associated with the pregnancy to pose to a physician; an impact of an intervention on the at least one pregnancy feature; a rate of occurrence of at least one pregnancy feature; a qualitative measure of the at least one pregnancy feature within the cohort; a quantitative measure of the at least one pregnancy feature within the cohort; or an average magnitude of the at least one pregnancy feature.

[0011] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the pregnancy report includes data corresponding to at least one of the features listed in Table 3, Table 4, or Table 5.

[0012] In some aspects, the techniques described herein relate to a computer- implemented method, wherein creating the pregnancy report that provides the at least one consideration for the subject includes modifying the at least one consideration for the pregnancy report based on biomarkers associated with at least one patient associated with the pregnancy.

[0013] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the cohort of pregnancies having the at least one pregnancy feature includes data representative of at least one of: a risk profile for the cohort for the at least one pregnancy feature; a number of healthcare visits associated with the cohort; an incidence rate of infections among the cohort; a frequency of breech presentations within the cohort; a preeclampsia risk associated with the cohort; a surprise delivery risk associated with the cohort; a mean length of stay associated with the cohort; biomarker data that indicates biomarkers associated with pregnancy complications or time to birth.

[0014] In some aspects, the techniques described herein relate to a computer- implemented method, further including generating the pregnancy cohort data model based on at least one pregnancy data source.

[0015] In some aspects, the techniques described herein relate to a computer- implemented method, wherein generating the pregnancy cohort data model includes, for each data source included in the at least one pregnancy data source, generating a set of cohort aggregate features including at least clinical features and biomarker features.

[0016] In some aspects, the techniques described herein relate to a computer- implemented method, wherein using the key to identify, from the pregnancy cohort data model, data representative of the cohort of pregnancies similar to the subject includes associating the key with, for each data source included in the at least one pregnancy data source, a set of cohort aggregate features.

[0017] In some aspects, the techniques described herein relate to a computer- implemented method, wherein generating the key that is representative of the set of attributes includes determining, based on a set of predetermined relevance metrics, the relevance of the subset of the set of attributes to identifying cohorts of pregnancies similar to the subject.

[0018] In some aspects, the techniques described herein relate to a computer- implemented method, wherein creating the pregnancy report includes creating the pregnancy report via a computer-implemented generative artificial intelligence tool configured to generate pregnancy-related information based on pre-existing pregnancy data.

[0019] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the computer-implemented generative artificial intelligence tool is pre-trained using at least one pregnancy data source, the at least one pregnancy data source including at least one of: one or more public pregnancy data sources including governmentally compiled pregnancy data; and one or more private data sources including privately compiled pregnancy data different from data included in the one or more public pregnancy data sources.

[0020] In some aspects, the techniques described herein relate to a computer- implemented method, further including presenting the pregnancy report to a user via an output graphical user interface of an output computing device.

[0021] In some aspects, the techniques described herein relate to a system including: a receiving module, stored in memory, that receives, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; a generating module, stored in memory, that generates, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes; an identifying module, stored in memory, that: uses the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; and identifies, based on the cohort of pregnancies, at least one consideration for the subject; a reporting module, stored in memory, that creates a pregnancy report that provides the at least one consideration for the subject; and at least one physical processor that executes the receiving module, the generating module, the identifying module, and the reporting module.

[0022] In some aspects, the techniques described herein relate to a system, wherein the generating module further generates the pregnancy cohort data model based on at least one pregnancy data source.

[0023] In some aspects, the techniques described herein relate to a system, wherein the generating module generates the pregnancy cohort data model by, for each data source included in the at least one pregnancy data source, generating a set of cohort aggregate features including at least clinical features and biomarker features.

[0024] In some aspects, the techniques described herein relate to a system, wherein the identifying module uses the key to identify, from the pregnancy cohort data model, data representative of the cohort of pregnancies having the at least one pregnancy feature by associating the key with, for each data source included in the at least one pregnancy data source, a set of cohort aggregate features.

[0025] In some aspects, the techniques described herein relate to a system, wherein the generating module generates the key that is representative of the set of attributes by determining, based on a set of predetermined relevance metrics, the relevance of the subset of the set of attributes to identifying cohorts of pregnancies similar to the subject.

[0026] In some aspects, the techniques described herein relate to a system, wherein the reporting module creates the pregnancy report via a computer-implemented generative artificial intelligence tool configured to generate pregnancy-related information based on pre-existing pregnancy data.

[0027] In some aspects, the techniques described herein relate to a non- transitory, computer-readable medium including computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to: receive, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; generate, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes; use the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; identify, based on the cohort ofpregnancies, at least one consideration for the subject; and create a pregnancy report that provides the at least one consideration for the subject.

[0028] In some aspects, the techniques described herein relate to a computer- implemented method including: receiving, via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; obtaining subject biomarker data associated with time to birth (TTB); generating a classification of the subject by classifying the subject into one of three groups based on the subject biomarker data, wherein: the subject is classified as positive if the subject biomarker data associated with TTB indicates less than a median TTB minus a standard deviation of TTB, the subject is classified as negative if the subject biomarker data associated with TTB indicates greater than the median TTB plus the standard deviation of TTB, and the subject is classified as neutral otherwise; identifying, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature similar to the subject based on the set of attributes; generating a probability distribution of delivery weeks for the subject based on the identified cohort and the subject's classification; creating a pregnancy report including the probability distribution and at least one consideration for the subject, the at least one consideration tailored to the subject's classification; and presenting the pregnancy report to the user via the graphical user interface of the computing device.

[0029] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further includes at least one of: a demographic characteristic; a health characteristic; a prior pregnancy characteristic; or a current pregnancy characteristic.

[0030] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least onefeature of the pregnancy further includes at least one of: an indication of whether a gestational parent is nulliparous; an age of at least one patient associated with the pregnancy; a body-mass index (BMI) of the at least one patient; a race of the at least one patient; an education level of the at least one patient; a set of risk factors associated with the at least one patient; or an indication of chronic diabetes associated with the gestational parent.

[0031] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further includes at least one of, associated with the subject and in the pregnancy: an indication of hypertension; an indication of preeclampsia; or indication of gestational diabetes.

[0032] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further includes at least one of, associated with the subject and in a prior pregnancy: an indication of hypertension; an indication of preeclampsia; an indication of gestational diabetes; an indication of a caesarean section delivery; or an indication of preterm birth.

[0033] In some aspects, the techniques described herein relate to a computer- implemented method, further including dynamically adjusting a weight given to the subject biomarker data associated with TTB in generating the probability distribution as the pregnancy progresses.

[0034] In some aspects, the techniques described herein relate to a computer- implemented method, wherein the at least one consideration tailored to the subject's classification includes: for subjects classified as positive, considerations focused onpreparing for potentially earlier delivery; for subjects classified as negative, guidance on managing longer gestational periods; and for subjects classified as neutral, considerations based on average weekly probability of delivery.

[0035] In some aspects, the techniques described herein relate to a computer- implemented method, further including: obtaining the subject biomarker data associated with TTB from a first database; obtaining additional attributes from a second database; and integrating data from the first and second databases using Bayes Theorem to derive the probability distribution of delivery weeks.

[0036] In some aspects, the techniques described herein relate to a computer- implemented method, wherein generating the classification of the subject includes classifying the subject into at least two groups based on the subject biomarker data associated with TTB, wherein: the classification is determined using at least two different thresholds of a TTB data distribution; and each of the different thresholds are determined based on at least one of clinical relevance, statistical analysis, or machine learning algorithms that optimize predictive power of the classification.

[0037] In some aspects, the techniques described herein relate to a system including: a receiving module, stored in memory, that: receives, via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; obtains subject biomarker data associated with time to birth (TTB); generates a classification of the subject by classifying the subject into one of three groups based on the subject biomarker data associated with TTB, wherein: the subject is classified as positive if the subject biomarker data associated with TTB indicates less than a median TTB minus a standard deviation of TTB, the subject is classified as negative if the subject biomarker data associated with TTB indicates greater than the median TTB plus thestandard deviation of TTB, and the subject is classified as neutral otherwise; an identifying module, stored in memory, that identifies, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature similar to the subject based on the set of attributes; a probability module, stored in memory, that generates a probability distribution of delivery weeks for the subject based on the identified cohort and the subject's classification; a reporting module, stored in memory, that creates a pregnancy report including the probability distribution and at least one consideration for the subject, wherein the at least one consideration is tailored to the subject's classification; a presentation module, stored in memory, that presents the pregnancy report to the user via the graphical user interface of the computing device; and at least one physical processor that executes the receiving module, the classification module, the identifying module, the probability module, the reporting module, and the presentation module.

[0038] In some aspects, the techniques described herein relate to a system, wherein the probability module generates the probability distribution by dynamically adjusting a weight given to the subject biomarker data as the pregnancy progresses.

[0039] In some aspects, the techniques described herein relate to a system, wherein the at least one consideration tailored to the subject's classification includes: for subjects classified as positive, considerations focused on preparing for potentially earlier delivery; for subjects classified as negative, guidance on managing longer gestational periods; and for subjects classified as neutral, considerations based on average weekly probability of delivery.

[0040] In some aspects, the techniques described herein relate to a non- transitory, computer-readable medium including computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:receive, via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; obtain subject biomarker data associated with time to birth (TTB); generate a classification of the subject by classifying the subject into one of three groups based on the subject biomarker data associated with TTB , wherein: the subject is classified as positive if the subject biomarker data associated with TTB indicates less than a median TTB minus a standard deviation of TTB, the subject is classified as negative if the subject biomarker data associated with TTB indicates greater than the median TTB plus the standard deviation of TTB, and the subject is classified as neutral otherwise; identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature similar to the subject based on the set of attributes; generate a probability distribution of delivery weeks for the subject based on the identified cohort and the subject's classification; create a pregnancy report including the probability distribution and at least one consideration for the subject, wherein the at least one consideration is tailored to the subject's classification; and present the pregnancy report to the user via the graphical user interface of the computing device.BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings illustrate a number of example embodiments and are a part of the specification. Together with the following description, these drawings demonstrate and explain various principles of the instant disclosure.

[0042] FIG. 1 is a block diagram of an example system for aggregating and presenting information associated with a pregnancy.

[0043] FIG. 2 is a block diagram of an example implementation of a system for aggregating and presenting information associated with a pregnancy.

[0044] FIG. 3 is a flow diagram of an example method for aggregating and presenting information associated with a pregnancy.

[0045] FIG. 4 illustrates generation of a pregnancy cohort data model from a plurality of data sources in accordance with some examples described herein.

[0046] FIG. 5 through FIG. 11 show various examples of the types of data that can be incorporated into and / or analyzed in order to generate a pregnancy cohort data model.

[0047] FIG. 12 and FIG. 13 include scatter plots that illustrate identification of a pregnancy cohort from within a larger pregnancy cohort data model.

[0048] FIG. 14 shows a diagram that illustrates how a generated key can be used to identify relevant cohorts within multiple different data sources in accordance with some examples described herein.

[0049] FIG. 15 and FIG. 16 include considerations that can be included in a pregnancy report in accordance with some examples described herein.

[0050] FIG. 17 provides a bar graph from an exemplary test report, showing the birth week probability distribution for each week (weeks 36 to 43) for a pregnant subject with the following 11 clinical and demographic factors: 1. 32 (age), 2. 23.3 (BM I ), 3. White (race), 4. No (hypertension / preeclampsia in a prior pregnancy), 5. No (preterm birth in a prior pregnancy), 6. Yes (c-section delivery in a prior pregnancy), 7. High School (education level), 8. No (first time mother), 9. No (chronic diabetes), 10. No (gestational diabetes in the current pregnancy), and 11. No (hypertension or preeclampsia in the current pregnancy).

[0051] FIG. 18 shows a line graph of the distribution of "neutral", "positive", and "negative" groups of pregnant subjects and their probability to deliver for each week (weeks37 to 42). "Neutral" represents the average weekly probability whereas the "positive group" is skewed to the right of the "neutral" group, and the "negative" group is skewed to the left.

[0052] FIGS. 19A-19F show an example of a report as described herein, including as described in Example 1.

[0053] Throughout the drawings, identical reference characters and descriptions indicate similar, but not necessarily identical, elements. While the example embodiments described herein are susceptible to various modifications and alternative forms, specific embodiments have been shown by way of example in the drawings and will be described in detail herein. However, the example embodiments described herein are not intended to be limited to the particular forms disclosed. Rather, the instant disclosure covers all modifications, equivalents, and alternatives falling within the scope of the appended claims.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0054] The present disclosure is generally directed to systems and methods for aggregating and presenting cohort information associated with a pregnancy. Embodiments of this innovative approach can involve receiving a set of attributes linked to a pregnancy feature, inputted by a user through a graphical user interface on a computing device. Subsequently, embodiments can generate a unique key, which is representative of the set of attributes, while also considering the relevance of these attributes in identifying cohorts of pregnancies similar to that of the subject. Utilizing this key, embodiments can identify pertinent data from a pre-established pregnancy cohort data model. This model can be comprehensive, integrating data from a variety of sources to ensure a thorough analysis.

[0055] In some embodiments, the systems and methods described herein can also create a detailed pregnancy report, which can provide insights by comparing the subject's pregnancy with similar cohorts, but can also deliver personalized considerationsand recommendations. This method represents a significant progression in personalized pregnancy care, offering enhanced, individualized insights into pregnancy-related factors for both expectant mothers and healthcare professionals.

[0056] The following will provide, with reference to FIGS. 1-2 and 4-19, detailed descriptions of systems for aggregating and presenting cohort information associated with a pregnancy. Detailed descriptions of corresponding computer-implemented methods will also be provided in connection with FIG. 3.

[0057] As used herein, "pregnancy" generally refers to a period during which an individual is pregnant (including the features, events and experiences during such period), though in some contexts the term can be used to refer to a pregnant individual.

[0058] As used herein, when used in the context of a pregnancy, the terms "attribute" or "attribute of a pregnancy" refer to any specific characteristic, factor, or parameter that is associated with a pregnancy, an individual experiencing pregnancy, or an individual associated with a pregnancy. This can include, but is not limited to, measurable biological, physiological, demographic, or health-related factors that can influence, indicate, or predict aspects of a pregnancy. Attributes can encompass a wide range of data points, such as age, body mass index (BM I), genetic markers, health history, lifestyle choices, and any other relevant personal or medical information that can be used to assess, monitor, or manage the state and progress of a pregnancy.

[0059] In some examples, a set of attributes can include, without limitation, a demographic characteristic, a health characteristic, a prior pregnancy characteristic, and / or a current pregnancy characteristic. In additional or alternative examples, an attribute or set of attributes can include, without limitation, an indication of whether a gestational parent is nulliparous, an age of a patient associated with the pregnancy (e.g., a gestational parent, anon-gestational parent, etc.), a body-mass index (BMI) of the patient, a race of the patient, a set of risk factors associated with the patient, biomarker data associated with the patient, and so forth.

[0060] In some embodiments, the attributes may include the subject's age at the baby's predicted birth; the subject's height; the subject's race (e.g., white, black, Asian / pacific islander, Native American, etc.); whether the subject is of Hispanic origin (yes / no); the subject's highest level of education (e.g., no high school diploma, high school diploma, some college, bachelor's degree, advanced degree); the subject's number of previous live births; the subject's current weight; whether the subject used fertility treatments in the current pregnancy; the subject's pregnancy type (e.g., singleton, twins, etc.); whether the subject has been diagnosed with chronic diabetes; or whether the subject has been diagnosed with chronic hypertension. In additional or alternative examples, an attribute or set of attributes can include, without limitation, the attributes listed in Table 1.

[0061] As will be described in greater detail below, in some examples, these attributes are collected, processed, and utilized to generate personalized insights and recommendations, and to identify cohorts of pregnancies with similar characteristics for comparative analysis. Attributes can be integral to the functionality of some embodiments of the systems and methods described herein, as such attributes can provide some foundational data upon which personalized pregnancy reports and analyses may be based.

[0062] As used herein, the terms "pregnancy feature" or "feature of a pregnancy" refer to any distinct aspect, condition, or characteristic that is specifically related to or arises during the course of a pregnancy. This encompasses a broad spectrum of physiological, medical, or health-related elements that are indicative of, or have an impact on, the progression and status of a pregnancy.

[0063] In some examples, pregnancy features can relate to demographic information, which provides context about the physiological state of the pregnancy and can include factors such as the age of the expectant mother, socio-economic status (e.g., household income, highest level of education, private versus public health insurance), ethnicity, marital status, and geographic location. These demographic factors can influence access to healthcare resources, the likelihood of certain pregnancy-related health conditions, and overall pregnancy management strategies. Furthermore, pregnancy features can encompass significant events experienced during pregnancy, including but not limited to, instances of hospitalization, changes in medication, the necessity for medical interventions like induction or cesarean delivery, and notable shifts in maternal health. Additionally or alternatively, pregnancy features can also relate to the outcomes of the pregnancy, which can be measured in terms of the health and condition of both the mother and child post-delivery. This could include birth weight, the infant's Apgar score (which assesses the newborn's health immediately after birth), the necessity for neonatal intensive care, the duration of postnatal recovery, and so forth. Pregnancy features can include one or more of the features listed in Table 2. Each of these features, whether demographic, event-related, or outcome-focused, contributes to the multifaceted nature of pregnancy monitoring and can be helpful in developing comprehensive care plans and support systems for both the mother and baby.

[0064] Pregnancy features can form a basis for comparing individual pregnancies with cohorts of similar pregnancies, thereby enabling the generation of personalized pregnancy reports and guidance. Pregnancy features can provide essential information that aids in tailoring the healthcare and advice given to pregnant individuals based on specific features of their pregnancy.

[0065] As used herein, when used in the context of a pregnancy, the terms "consideration" or "consideration for the subject" refer to any advice, recommendation, insight, or information that is specifically tailored to the subject, who can be an individual experiencing pregnancy, based on the analysis of the pregnancy-related attributes and features. These considerations are derived from an evaluation of the subject's pregnancy profile, which includes personal attributes, pregnancy features, and comparative data from similar pregnancy cohorts. The considerations can provide guidance, support, and information to assist in decision-making, healthcare planning, and understanding of the pregnancy. In some embodiments, considerations can include the incidence of specific pregnancy features in a cohort (e.g., the cohort to which the subject has been matched as described herein). In some embodiments, considerations can include the comparison of such incidence(s) to the average incidence(s) of such pregnancy features in a reference group (e.g., U.S. national average incidences).

[0066] Examples of considerations for the subject can include, but are not limited to, lifestyle adjustments, dietary recommendations, medical interventions, or precautionary measures that are particularly relevant to the subject's pregnancy circumstances. They can also encompass suggestions for discussions with healthcare providers, addressing specific concerns or risks identified during the analysis. An objective of providing these considerations can be to enhance the personalized care and support for the subject during pregnancy, taking into account their unique situation as compared to general or average pregnancy cases. This feature can be helpful for delivering customized and informed healthcare experiences, thereby improving pregnancy outcomes and overall maternal and fetal health.

[0067] As used herein, the terms "pregnancy cohort" or "cohort of pregnancies" refer to a group of pregnancies (or patients who experienced pregnancy) that are aggregated and analyzed together based on sharing one or more common characteristics, features, or attributes. These shared elements can include, but are not limited to, demographic details, health conditions, lifestyle factors, genetic information, or any specific pregnancy-related features such as gestational age, risk factors, or outcomes. One purpose of grouping pregnancies into cohorts can be to facilitate comparative analysis, enabling the identification of patterns, risks, and outcomes that may be common to the cohort.

[0068] In some examples described herein, a pregnancy cohort can be used as a reference or comparative standard to assess and provide context to an individual's pregnancy. By comparing an individual's pregnancy attributes and features with those of a relevant cohort, the system can offer more personalized and meaningful insights, recommendations, and considerations. The creation and utilization of pregnancy cohorts can be central to some functionalities described herein as they can provide a foundation for generation of tailored reports and advice, enhancing the pregnancy management and monitoring process. The composition and criteria for defining a pregnancy cohort can be determined based on specific requirements of the analysis and the nature of the data available in the pregnancy cohort data model.

[0069] As used herein, the term "pregnancy cohort data model" can be characterized as a flexible and adaptive representation of data related to various pregnancy aspects, aimed at facilitating the analysis and comparison of different pregnancy scenarios. This model can integrate and systematically organize a diverse range of data, potentially including demographic details, health and medical histories, specific pregnancy-relatedmetrics, outcomes from past pregnancies, and other relevant data points that aid in comprehending and / or describing the nuances of pregnancy.

[0070] In its application within some embodiments of the systems and methods described herein, a pregnancy cohort data model can be utilized to identify groups or cohorts of pregnancies that share common attributes and features. It can serve as a tool in analyzing complex pregnancy-related data and generating personalized insights, particularly in the creation of individualized pregnancy reports. The model is typically pre-generated, crafted from a wide-ranging compilation of data sources, which might encompass publicly available data as well as proprietary research. However, in some embodiments, the pregnancy cohort data model may be dynamically updated to incorporate additional or updated data sources.

[0071] The flexibility of this data model may allow for effective discernment of trends, risks, and potential outcomes within various pregnancy cohorts, thus enhancing the precision and relevance of information and guidance provided to expectant mothers. The structure of the model, including its data integration techniques and analytical methods, can enhance its effectiveness in delivering accurate and customized pregnancy care insights.

[0072] As will be described in greater detail below, some embodiments of the systems and methods described herein can employ and / or access data included in various public and / or private pregnancy data sources. As used herein, the term "public pregnancy data source" refers to any collection of pregnancy-related data that is accessible to the public, often, though not necessarily, provided or maintained by government entities (e.g., the Centers for Disease Control and Prevention (CDC), state health departments, etc.), public health organizations, or academic institutions. Access to such public pregnancy data sources can be, but is not necessarily, without monetary charge. In some cases access maybe conditioned on agreement to certain terms, the provision of information, or the acceptance of certain obligations (e.g., privacy attestations or safeguards). Such conditions do not mean a data source is not accessible to the public. In some embodiments, this data source can include aggregated information derived from a wide population base and can cover various aspects of pregnancy, such as statistical data on birth rates, prenatal health metrics, demographic trends in pregnancy, and common pregnancy complications. In some embodiments, the data from these sources can be anonymized to protect individual privacy and used for public health research, policy-making, and general informational purposes. In some embodiments of the systems and methods described herein, this data can be utilized to inform and enhance the pregnancy cohort data model, contributing to the breadth and depth of the analysis provided by the system. Examples of such data sources are discussed in greater detail below, with FIG. 10 and FIG. 11 presenting examples of possible data source content and / or formats from data published by the CDC.

[0073] As used herein, the term "private pregnancy data source" refers to a collection of pregnancy-related data that is not publicly accessible and is typically held by private entities— e.g., healthcare providers, medical clinics, research organizations, or private health databases— for use by specific groups or individuals— e.g., employees, contractors, healthcare providers, researchers, paid subscribers. This data can include detailed medical records, individual patient histories, results of clinical studies, or proprietary research findings. Private data sources may contain more specific and individualized information compared to public sources and can offer deeper insights into various aspects of pregnancy and maternal health.

[0074] In some embodiments described herein, private data sources can allow for a more comprehensive and nuanced understanding of pregnancy, enabling thegeneration of highly personalized pregnancy reports and recommendations. Access to these private data sources is usually restricted and governed by privacy laws and regulations, ensuring the confidentiality and security of the information contained within.

[0075] Turning to the Figures, FIG. 1 is a block diagram of an example system 100 for aggregating and presenting information associated with a pregnancy. As illustrated in this figure, example system 100 can include one or more modules 102 for performing one or more tasks. As will be explained in greater detail below, modules 102 can include a receiving module 104 that receives, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy. Example system 100 can also include a generating module 106 that generates, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes. Additionally, example system 100 can also include an identifying module 108 that (1) uses the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature, and (2) identifies, based on the cohort of pregnancies, at least one consideration for the subject. Additionally, example system 100 can also include a reporting module 110 that creates a pregnancy report that provides the at least one consideration for the subject. In some examples, reporting module 110 can also provide the report to a user (e.g., the user or an additional user) via the user interface of the computing device.

[0076] As further illustrated in FIG. 1, example system 100 can also include one or more memory devices, such as memory 120. Memory 120 generally represents any type or form of volatile or non-volatile storage device or medium capable of storing data and / or computer-readable instructions. In one example, memory 120 can store, load, and / ormaintain one or more of modules 102. Examples of memory 120 include, without limitation,Random Access Memory (RAM), Read Only Memory (ROM), flash memory, Hard Disk Drives (HDDs), Solid-State Drives (SSDs), optical disk drives, caches, variations or combinations of one or more of the same, or any other suitable storage memory.

[0077] As further illustrated in FIG. 1, example system 100 can also include one or more physical processors, such as physical processor 130. Physical processor 130 generally represents any type or form of hardware-implemented processing unit capable of interpreting and / or executing computer-readable instructions. In one example, physical processor 130 can access and / or modify one or more of modules 102 stored in memory 120. Additionally or alternatively, physical processor 130 can execute one or more of modules 102 to facilitate aggregating and presenting information associated with a pregnancy. Examples of physical processor 130 include, without limitation, microprocessors, microcontrollers, central processing units (CPUs), Field-Programmable Gate Arrays (FPGAs) that implement softcore processors, Application-Specific Integrated Circuits (ASICs), portions of one or more of the same, variations or combinations of one or more of the same, or any other suitable physical processor.

[0078] As also illustrated in FIG. 1, example system 100 can also include one or more stores of data, such as data store 140. Data store 140 can represent portions of a single data store or computing device or a plurality of data stores or computing devices. In some embodiments, data store 140 can be a logical container for data and can be implemented in various forms (e.g., a database, a file, file system, a data structure, etc.). Examples of data store 140 can include, without limitation, one or more files, file systems, data stores, databases, and / or database management systems such as an operational datastore (ODS), a relational database, a NoSQL database, a NewSQL database, and / or any other suitable organized collection of data.

[0079] Data store 140 can include various data including, without limitation, a pregnancy cohort data model 142, attributes data 144, feature data 146, and consideration data 148. Each of these datasets and / or data objects can be maintained within data store 140 to ensure that each of the modules 102 has access to timely, accurate, and relevant information required to perform their functions. The data store is designed to interact with the various system modules to support the generation of personalized pregnancy reports and the delivery of individualized care recommendations.

[0080] Pregnancy cohort data model 142 can include and / or represent one or more comprehensive data structures or models that can represent, capture, and / or organize information about different cohorts of pregnancies. Pregnancy cohort data model 142 can include aggregated data points that reflect shared characteristics among groups of pregnancies, such as common health metrics, gestational timelines, and pregnancy outcomes. The model facilitates the identification of patterns and trends within specific cohorts and supports comparative analysis against an individual subject's pregnancy attributes.

[0081] Attributes data 144 can include or represent detailed records of individual pregnancy-related attributes collected from users and / or attributes that can be applied to users based on provided attribute data. Attributes data 144 can include any suitable data regarding any attribute which, as described above, may include measurable biological, physiological, demographic, or health-related factors that can influence, indicate, or predict aspects of a pregnancy. Hence, attributes data 144 can consist of both demographic and medical information, such as age, medical history, lifestyle factors, and genetic markers,which are pertinent to the pregnancy. Attributes data serves as part of the input for generating the key that is used to query the Pregnancy Cohort Data Model (e.g., pregnancy cohort data model 142) and align an individual subject's information with one or more relevant cohorts.

[0082] Feature data 146 can include or represent a detailed compilation of information regarding various pregnancy features as described above. Hence, it is an extensive collection of data points that pertain to the distinct aspects, conditions, or characteristics that emerge or are associated with the course of a pregnancy. This data encapsulates a broad spectrum of physiological, medical, or health-related elements that can be indicative of, or can have an influence on, progression and status of a pregnancy. This can include, but is not limited to, demographic information such as expectant mothers' age, socio-economic status (e.g., household income, highest level of education, private versus public health insurance), ethnicity, marital status, and geographic location, which provide context about the physiological state of the pregnancy. Feature data 146 can also include data on significant events experienced during pregnancies, such as instances of hospitalization, medication adjustments, medical interventions like induction or cesarean delivery, and notable shifts in maternal health. Furthermore, it can also include outcomes of the pregnancy, measurable in terms of health parameters such as birth weight, the infant's Apgar score, the requirement for neonatal intensive care, and the duration of postnatal recovery, among others.

[0083] Consideration data 148 can include a set of advice, recommendations, insights, and / or information that can be customized for subjects (e.g., individuals undergoing a pregnancy). One or more of the systems described herein can draw from consideration data 148 in creating and / or providing a pregnancy report. For example,consideration data 148 may comprise recommendations tailored to a subject's TTB classification, such as suggestions for preparing for potentially earlier delivery, guidance on managing longer gestational periods, or considerations based on average weekly probability of delivery. Consideration data 148 can include, but is not limited to, suggestions for lifestyle modifications, dietary changes, potential medical interventions, or precautionary steps, all of which are directly pertinent to the individual circumstances of the subject's pregnancy. Additionally, this data can offer specific questions or topics for discussion with healthcare providers, particularly addressing identified concerns or risks that emerged from the analysis, including those related to the subject's TTB classification. The ultimate goal of providing these considerations can be to amplify the level of personalized information, care, and support offered to subjects throughout their pregnancies, reflecting their distinct circumstances as opposed to relying on generic pregnancy data. By doing so, the systems and methods disclosed herein can provide healthcare experiences that are both customized and informative, potentially leading to enhanced outcomes for both maternal and fetal health.

[0084] Example system 100 in FIG. 1 can be implemented in a variety of ways. For example, all or a portion of example system 100 can represent portions of an example system 200 ("system 200") in FIG. 2. As shown in FIG. 2, system 200 can include a server 202 in communication with a user device 206 via a network 204. In at least one example, server 202 can be programmed with one or more of modules 102. Additionally or alternatively, user device 206 can be programmed with one or more of modules 102.

[0085] In at least one embodiment, one or more modules 102 from FIG 1 may, when executed by server 202 and / or user device 206, enable server 202 and / or user device206 to perform one or more operations to aggregate and present information associatedwith a pregnancy. For example, as will be described in greater detail below, receiving module 104 can cause server 202 and / or user device 206 to receive, from a user (e.g., user 208) via a graphical user interface of a computing device (e.g., user interface 210), a set of attributes of a subject linked to at least one feature of a pregnancy (e.g., set of attributes 212). Additionally, generating module 106 can cause server 202 and / or user device 206 to generate, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject (e.g., relevance data included in attributes data 144), a key (e.g., key 216) that is representative of the set of attributes.

[0086] Furthermore, identifying module 108 can cause server 202 and / or user device 206 to use the key to identify, from a pregnancy cohort data model (e.g., pregnancy cohort data model 142), a cohort of pregnancies having at least one pregnancy feature (e.g., identified cohort 218) and to identify, based on the cohort of pregnancies, at least one consideration for the subject (e.g., consideration 220). Moreover, reporting module 110 can cause server 202 and / or computing device 206 to create a pregnancy report that provides the at least one consideration for the subject. In some examples, reporting module 110 can additionally cause server 202 and / or user device 206 to present the pregnancy report to a user (e.g., user 208 and / or a different user) via a graphical user interface of a computing device (e.g., user interface 210 and / or a different user interface).

[0087] Server 202 generally represents any type or form of computing device capable of reading and / or executing computer-executable instructions and / or hosting executables. Examples of user device 206 include, without limitation, application servers, storage servers, database servers, web servers, cloud computing platforms, virtual servers,and / or any other suitable computing device configured to run certain software applications and / or provide various application, storage, and / or database services.

[0088] Network 204 generally represents any medium or architecture capable of facilitating communication and / or data transfer between server 202, user device 206. Examples of network 204 include, without limitation, an intranet, a WAN, a LAN, a Personal Area Network (PAN), the Internet, Power Line Communications (PLC), a cellular network (e.g., a Global System for Mobile Communications (GSM) network, a code-division multiple access (CDMA) network, a Long-Term Evolution (LTE) network, etc.), universal serial bus (USB) connections, APPLE LIGHTNING connections, virtual network connections, and the like. Network 204 can facilitate communication or data transfer using wireless or wired connections. In one embodiment, network 204 can facilitate communication between server 202 and user device 206.

[0089] User device 206 generally represents any type or form of computing device capable of reading and / or executing computer-executable instructions. In at least one embodiment, server 202 can accept one or more directions from user device 206, and / or vice versa. Examples of user device 206 include, without limitation, servers, desktops, laptops, tablets, cellular phones, (e.g., smartphones), personal digital assistants (PDAs), multimedia players, embedded systems, wearable devices (e.g., smart watches, smart glasses, etc.), gaming consoles combinations of one or more of the same, or any other suitable mobile computing device.

[0090] In at least one example, server 202 and / or user device 206 can be computing devices programmed with one or more of modules 102. All or a portion of the functionality of modules 102 can be performed by server 202, user device 206, and / or any other suitable computing system. As will be described in greater detail below, one or moreof modules 102 from FIG. 1 may, when executed by at least one processor of server 202 and / or user device 206, can enable server 202 and / or user device 206 to aggregate and present information associated with a pregnancy.

[0091] Many other devices or subsystems can be connected to system 100 in FIG. 1 and / or system 200 in FIG. 2. Conversely, all of the components and devices illustrated in FIGS. 1 and 2 need not be present to practice the embodiments described and / or illustrated herein. The devices and subsystems referenced above can also be interconnected in different ways from those shown in FIG. 2. Systems 100 and 200 can also employ any number of software, firmware, and / or hardware configurations. For example, one or more of the example embodiments disclosed herein can be encoded as a computer program (also referred to as computer software, software applications, computer-readable instructions, and / or computer control logic) on a computer-readable medium.

[0092] FIG. 3 is a flow diagram of an example computer-implemented method 300 for aggregating and presenting information associated with a pregnancy. The steps shown in FIG. 3 can be performed by any suitable computer-executable code and / or computing system, including system 100 in FIG. 1, system 200 in FIG. 2, and / or variations or combinations of one or more of the same. In one example, each of the steps shown in FIG. 3 can represent an algorithm whose structure includes and / or is represented by multiple substeps, examples of which will be provided in greater detail below.

[0093] As illustrated in FIG. 3, at step 310, one or more of the systems described herein can receive, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy. For example, receiving module 104 may, as part of server 202 and / or user device 206 in FIG. 2, cause server 202and / or user device 206 to receive, via user interface 210 of user device 206, set of attributes 212.

[0094] Receiving module 104 can cause server 202 and / or user device 206 to receive a set of attributes 212 in any suitable way and in a variety of contexts. This can involve prompting the user through the user interface 210 to enter specific details regarding their pregnancy, which can include, but are not limited to, the expected due date, past medical history, current health conditions, and any known genetic factors. The user interface 210 can be designed to be intuitive and can include forms, questionnaires, or interactive elements that can guide the user in providing comprehensive and accurate information.

[0095] Receiving module 104 can further process the input data for consistency and completeness. It can validate the received attributes against predefined criteria to ensure data integrity and can also transform the input into a standardized format suitable for further analysis. In some cases, receiving module 104 can also interact with other modules or databases to enrich the received data. For example, it can cross-reference entered medical conditions with a medical database to gather additional details or to confirm the information provided by the user.

[0096] Additionally, receiving module 104 can facilitate the secure transmission of the received attributes to server 202 for processing. It can employ anonymization, encryption, and / or secure communication protocols to maintain the confidentiality of the user's sensitive information. Once the data is received and processed by receiving module 104, it can then be stored in a local or remote data storage medium associated with the server 202 (e.g., memory 120 and / or data store 140), making it available for subsequent steps in the method 300.

[0097] Returning to FIG. 3, at step 320, one or more of the systems described herein can generate, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes. For example, generating module 106 may, as part of server 202 and / or user device 206, cause server 202 and / or user device 206 to generate, based on at least a subset of set of attributes 212 and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, key 216.

[0098] Generating module 106 can cause server 202 and / or user device 206 to generate key 216 in a variety of contexts. In some examples, generating module 106 can initiate its operation by selecting a subset of set of attributes 212 that are deemed most relevant for identifying a cohort of pregnancies that are similar to the subject's situation. This selection can be guided by a set of predetermined relevance metrics, which can include predefined criteria and / or selection methodologies designed to weigh the importance of each attribute in the context of pregnancy analysis.

[0099] These relevance metrics, which can be included as part of attributes data 144 in data store 140, can include factors such as a statistical frequency of certain attributes within the general population, a strength of association between attributes and pregnancy outcomes, and / or other evidence-based measures. Generating module 106 can utilize these metrics to evaluate which attributes from the set are most indicative of the subject's pregnancy experience and can thereby serve as reliable indicators for cohort comparison.

[0100] Upon determining the relevance of each attribute in the subset, generating module 106 can generate a unique key, key 216. This key can include a representative code or identifier that can encapsulate, represent, or otherwise indicate the selected attributes in a form that can be efficiently used to query the pregnancy cohort datamodel. The design of this key can be such that it can capture an essence of the subject's unique pregnancy profile while also conforming to a structure of the pregnancy cohort data model, allowing for a seamless interaction between the two.

[0101] The generation of the key 216 by generating module 106 is not a mere compilation of data; it is an analytical process that transforms raw user input into a distilled representation of the subject's pregnancy context. This key serves as a cornerstone for the subsequent identification process, enabling the system to retrieve the most relevant cohort data and, consequently, the most applicable considerations for the subject.

[0102] In some examples, generating module 106 can generate the pregnancy cohort data model based on at least one pregnancy data source. As described above, the at least one pregnancy data source can include a diverse array of data from at least one pregnancy data source, and can encompass a variety of information repositories, including electronic health records, clinical databases, public health surveys, proprietary research compilations, and so forth.

[0103] For each data source included within the scope of the at least one pregnancy data source, generating module 106 can process the data source to extract a set of cohort aggregate features. These features are carefully chosen to represent key clinical and biomarker characteristics of pregnancy, which can include but are not limited to, gestational age, maternal health indicators, fetal development markers, and genetic or proteomic data linked to pregnancy outcomes.

[0104] Generating module 106 can employ sophisticated algorithms to analyze each data source and distill the information into a structured format, creating a comprehensive framework that encapsulates the nuanced aspects of pregnancy cohorts.This process of generating the pregnancy cohort data model can be iterative and dynamic,ensuring the model remains reflective of the most current medical understanding and data availability.

[0105] Generating module 106 can generate the pregnancy cohort data model with layered complexity, allowing for each set of cohort aggregate features to be indexed and cross-referenced based on a per-source key generated by the system. When generating module 106 processes the attributes data received from the user, it aligns the key (e.g., key 214) with the corresponding cohort aggregate features within the model. This alignment can enable other modules (e.g., identifying module 108) to effectively match the user's provided set of attributes against the pregnancy cohort data model, facilitating the identification of a relevant cohort of pregnancies that share similarities with the subject's pregnancy.

[0106] The granularity with which generating module 106 builds the pregnancy cohort data model ensures that the subsequent identification of cohorts is both accurate and highly personalized. By associating the key with specific cohort aggregate features for each data source, the system is endowed with the capability to draw from a rich tapestry of data, yielding insights and considerations deeply tailored to the user's unique pregnancy journey.

[0107] By way of illustration, FIG. 4 shows an operational flow diagram of a source data map that can show how various data sources can be incorporated into a pregnancy cohort data model. FIG. 4 shows incorporation of three data sources into a pregnancy cohort data model, each data source via a respective data path. Data path 402 represents incorporation of a public data source including CDC data, data path 404 represents incorporation of a private data source including data from a study, and data path406 represents incorporation of consumer data.

[0108] The types of data that can be incorporated into and / or analyzed in order to generate a pregnancy cohort data model can be varied and multifaceted. FIGS 5-11 show various examples of the types of data that can be incorporated into and / or analyzed in order to generate a pregnancy cohort data model. For example, FIG. 5 shows a chart 500 generated from data provided by the CDC that compares various pregnancy features for two cohorts of patients. The first cohort includes gestational parents 20-25 years of age with BMI less than or equal to 25 who have attended no college and received fewer than six doctor's visits. The second cohort includes gestational parents 32-37 years of age with BMI greater than 30 who attended college and received greater than or equal to 13 doctor's visits.

[0109] FIG. 6 shows a map 600 that illustrates different levels or types of access to maternity care depending on the gestational parent's geographic location. This data can be useful for identifying pregnancy features or outcomes related to access to maternity care of the gestational parent based on location information provided by the user (e.g., a zip code, an address, a political subdivision, a positional coordinate, etc.). Moreover, the systems and methods described herein may benefit patients who live in geographic locations having less access to maternity care in that embodiments thereof may provide patients with access to information that may inform their choices about seeking out maternity care.

[0110] FIG. 7A depicts a histogram 700 representing a frequency distribution of maternal age for pregnancies recorded in the year 2017. The X-axis of the histogram categorizes maternal age into discrete intervals, typically in years, while the Y-axis quantifies the frequency of occurrences within each age group. The distribution is displayed as a seriesof vertically aligned bars, with each bar's height corresponding to the number of pregnancies observed for a given maternal age range.

[0111] This frequency distribution is indicative of the maternal age demographic for the year in question, highlighting the most common age ranges in which pregnancies occur, as well as less common age ranges. Such a distribution can be valuable in identifying prevalent trends in maternal age for pregnancies, which may be a helpful factor in the analysis of pregnancy-related risks, healthcare resource allocation, and policy-making in maternal health services.

[0112] FIG. 7B displays a histogram 710 that visualizes a distribution of timing for a first prenatal physician visit across different months for pregnancies in the year 2017. The X-axis categorizes the months, while the Y-axis measures the frequency of first visits. The height of each bar corresponds to the number of first physician visits that occurred during a particular month. This distribution provides insights into when expectant parents typically begin seeking prenatal care, which is crucial for healthcare planning and resource allocation.

[0113] FIG. 8A shows a histogram 800 that visualizes a frequency distribution of maternal BMI for pregnancies in the year 2017. The X-axis represents the BMI values categorized into ranges, and the Y-axis indicates the number of occurrences within each BMI category. Taller bars reflect a higher frequency of pregnancies within a specific BMI range. This visual representation can be helpful for understanding the distribution of maternal BMI across the population and can assist healthcare providers in identifying prevalent BMI categories for targeted prenatal care strategies.

[0114] FIG. 8B shows a histogram 810 that illustrates a distribution of childbirths by day of the week for the year 2017. The X-axis enumerates the days of the week, starting with 1 for Sunday and ending with 7 for Saturday, while the Y-axis quantifies the frequencyof deliveries on each day. The pattern revealed by the bars may suggest trends in delivery scheduling or natural birth rates on specific days, offering insights that could be valuable for healthcare staffing and resource planning in maternity services.

[0115] FIG. 9A displays a histogram 900 that charts a frequency distribution of gestational age at birth (GAB) for pregnancies recorded in 2017. The bars represent categorized gestational ages, with the X-axis delineating these categories numerically from 1 to 10. These numbers correspond to gestational age ranges as follows: '1' represents under 20 weeks of gestation; '2' codes for 20-27 weeks; '3' for 28-31 weeks; '4' for 32-33 weeks; '5' for 34-36 weeks; '6' for 37-38 weeks; '7' for 39 weeks; '8' for 40 weeks; '9' for 41 weeks; and '10' for 42 weeks and over. The Y-axis measures the frequency of births within each of these gestational periods. The histogram provides insights into the timing of births, highlighting prevalence of various gestational periods from preterm to post -term deliveries. This data can inform healthcare providers about common gestation durations and potentially guide interventions to support at-risk pregnancies.

[0116] FIG. 9B includes a histogram 910 that depicts the frequency distribution of the number of prenatal physician visits for pregnancies in 2017. The X-axis is segmented numerically from 0 to 11, with each segment representing a range of prenatal visits: '0' for no visits, '1' for 1-2 visits, '2' for 3-4 visits, '3' for 5-6 visits, '4' for 7-8 visits, '5' for 9-10 visits, '6' for 11-12 visits, '7' for 13-14 visits, '8' for 15-16 visits, '9' for 17-18 visits, and '10' for 19 or more visits. The Y-axis indicates the count of pregnancies corresponding to each visit range. The histogram can provide insight into prenatal care engagement patterns among expectant mothers, which may be helpful for understanding healthcare utilization during pregnancy.

[0117] FIG. 10 includes a partial listing 1000 of some pregnancy features tracked and / or reported by the CDC that can provide cohort information and / or pregnancy feature information which can be utilized by the systems and methods disclosed herein. The "Feature" column indicates various pregnancy features. The "Type" column indicates a type associated with each pregnancy feature (e.g., "Demographic", "Experience", or "Outcome"). The "CDC Variable" column indicates a corresponding label within the CDC's database for variables in the CDC database representative of each pregnancy feature. As provided in the "User Guide to the 2022 Natality Public Use File" published by the CDC, the entries in the "CDC Variable" column indicate, from top to bottom, Mother's Single Years of Age (AGER), Mother's Race Recode 6 (MRACE6), Marital Status (DMAR), Mother's Education (MEDUC), Prior Births Now Living (PRIORLIVE), Prior Births Now Dead (PRIORDEAD), Interval Since Last Live Birth Recode (ILLB_R), Month Prenatal Care Began Recode (PRECARE5), Number of Prenatal Visits (PREVIS), Cigarettes Before Pregnancy (CIG_0), Cigarettes 1st Trimester (CIG_1), Cigarettes 2nd Trimester (CIG_2), Cigarettes 3rd Trimester (CIG_3), Body Mass Index (BMI), Pre-pregnancy Diabetes (RF_PDIAB), Gestational Diabetes (RF_GDIAB), Prepregnancy Hypertension (RF_PHYPE), Gestational Hypertension (RF_GHYPE), Previous Preterm Birth (RF_PPTERM), Infertility Treatment Used (RFJNFTR), Previous Cesarean (RF_CESAR), Infection Gonorrhea (IP_GON), Infection Syphilis (IP_SYPH), Infection Chlamydia (IP_CHLAM), Infection Hepatitis B (IP_HEPB), Infection Hepatitis C (IP_HEPC), No Infections Reported (NOJNFEC), Induction of Labor (LDJNDL), Augmentation of Labor (LD_AUGM), Steroids (LD_STER), Antibiotics (LD_ANTB), Chorioamnionitis (LD_CHOR), and Anesthesia (LD_ANES). Finally, the "Values" column indicates possible values for the respective variables.

[0118] FIG. 11 includes a partial listing 1100 of a portion of a raw spreadsheet that includes some pregnancy data reported by and / or made public by the CDC. As provided in the "User Guide to the 2022 Natality Public Use File" published by the CDC, the columns shown in this figure indicate, from left to right, Birth Year (dob_yy), Birth Month (dob_mm), Time of Birth (dob_tt), Birth Day of Week (dob_wk), Birth Place (bfacil), Reporting Flag for Birth Place (f_bfacil), and Birth Place Recode (bfacil3).

[0119] Returning to FIG. 4, in each data path, generating module 106 causes the respective data source to undergo a similar process. First, a data engineering operation is executed, which can involve collecting and preparing raw data for analysis. This could involve cleaning the data, handling missing values, normalizing data formats, and / or ensuring that the data is in a usable state for further processing.

[0120] Next, for each data source, generating module 106 executes a data engineering and data modeling operation. The prepared data is used to build models that can capture relationships and patterns within the data. This can be a proprietary process that can use statistical methods, machine learning algorithms, or other data science techniques to construct a model that represents the various cohorts of interest— such as different groups of pregnancies characterized by specific attributes. In some examples, generating module 106 can, for each data source, generate a set of cohort aggregate features. These are characteristics or patterns that are common within a defined group or cohort. Each set of cohort aggregate features may be included within the grouping indicated by cohort aggregate features 408 in FIG. 4.

[0121] Generating module 106 can then, for each data source, integrate the modeled data into the pregnancy cohort data model (indicated as "PCDM 142" in FIG. 4)This step involves combining data from different sources or streams into a single, unifiedmodel. This can include combining the cohort aggregate features included in cohort aggregate features 408 in FIG. 4 into pregnancy cohort data model 142.

[0122] Returning to FIG. 3, at step 330, one or more of the systems described herein can use the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature. For example, identifying module 108 may, as part of server 202 or user device 206 in FIG. 2, cause server 202 or user device 206 to use key 216 to identify, from pregnancy cohort data model 142, identified cohort 218.

[0123] Identified cohort 218 can include data representative of or associated with any suitable pregnancy feature including, without limitation, a risk profile for the cohort for the at least one pregnancy feature, a number of healthcare visits associated with the cohort, an incidence rate of infections among the cohort, a frequency of breech presentations within the cohort, a preeclampsia risk associated with the cohort, a surprise delivery risk associated with the cohort, a mean length of stay associated with the cohort, and / or biomarker data that indicates biomarkers associated with pregnancy complications.

[0124] By way of illustration, FIG. 12 presents a scatter plot 1200 illustrating a comprehensive distribution of data points, where each point represents a unique pregnancy case. The axes of the scatter plot may denote various pregnancy attributes, features, and / or outcomes, such as gestational age, birth weight, maternal age, or other clinical parameters. The spread of the data points across the plot reflects the diversity and range of these attributes within the population studied. This visualization aids in the initial assessment of the data's overall distribution, identifying clusters, outliers, and trends that are inherent to the collective pregnancy data.

[0125] FIG. 13 depicts a refined scatter plot 1300, building upon the data presented in FIG. 12. In this iteration of the plot, a circle encompasses a subset of the datapoints, delineating a specific cohort of pregnancies 1302. This cohort is characterized by having similar attributes, as indicated by their proximity within the plot. The circle serves as a visual identifier for this group, highlighting the cohort for further analysis. This cohort identification is crucial for the system's ability to provide personalized healthcare insights, as it isolates the data subset most relevant to the user's query or pregnancy attributes.

[0126] Identifying module 108 can identify identified cohort 218 in a variety of contexts. Identifying module 108 can efficiently sift or search through an extensive data repository included in pregnancy cohort data model 142 to locate a specific cohort of pregnancies that shares common pregnancy features with the subject's profile. The process can involve one or more matching algorithms where the key 216, representative of the subject's attributes, guides the search and identification within the model. This ensures that the cohort selected is closely aligned with the subject's pregnancy characteristics, thereby ensuring relevancy and precision in the cohort identification process.

[0127] In some examples, as described above, generating module 106 may, as part of generating pregnancy cohort data model 142, extract a set of cohort aggregate features. Hence, identifying module 108 may, using key 214, identify cohorts having similarity with the set of attributes based on one or more cohort aggregate features extracted and / or generated from each data source during generation of pregnancy cohort data model 142.

[0128] By way of illustration, FIG. 14 shows a diagram 1400 that illustrates how a generated key (e.g., key 214) can be used to identify relevant cohorts within multiple different data sources. As described above, key 214 is a result of the processing of a user- provided set of attributes, which encapsulates information linked to features of a pregnancy.

[0129] Three primary data sources are shown in FIG. 14, each linked to key 214 by directional arrows that signify the flow of data retrieval. The first data source 1402 is labeled 'CDC' and may represent data from the CDC indicating the system's capacity to incorporate national or governmental health data into its analysis. The second data source 1404 is denoted as 'STUDIES,' which suggests a collection of various academic and clinical research studies that the system can draw upon for detailed pregnancy-related statistics and findings. The third data source 1406 is identified as 'PRAMS,' referring to the Pregnancy Risk Assessment Monitoring System's database, which provides nuanced insights into maternal and infant health before, during, and after pregnancy.

[0130] Diagram 1400 in FIG. 14 emphasizes the centralized role of the key in interfacing with these diverse data sources, underlining the functionality of embodiments of the systems and methods described herein in harnessing a wide range of data to inform personalized pregnancy care. Each data source contributes a unique set of data points that, when combined, offer a rich, multidimensional perspective on pregnancy features and outcomes. The generated key (e.g., key 214) is integral to unlocking this wealth of information, enabling the system to identify relevant data that aligns with the user's specific attributes and to deliver comprehensive insights into their pregnancy experience.

[0131] Returning to FIG. 3, at step 340, one or more of the systems described herein can identify, based on the cohort of pregnancies, at least one consideration for the subject. For example, identifying module 108 may, as part of server 202 and / or user device 206 in FIG. 2, cause server 202 and / or user device 206 to identify, based on identified cohort 218, consideration 220.

[0132] Identifying module 108 can identify consideration 220 in any suitable way.For example, identifying module 108 can analyze pregnancy features, characteristics,patterns, and outcomes prevalent within the identified cohort 218 and can extrapolate pertinent considerations by comparing the subject's pregnancy attributes with those of the identified cohort, ensuring that the advice is both personalized and contextually relevant.

[0133] Identifying module 108 can examine various pregnancy features within the cohort, such as gestational age, maternal health indicators, and the incidence of pregnancy complications or outcomes like birth weight and delivery type. Additionally, identifying module 108 can employ advanced data analytics techniques to discern patterns and correlations within the cohort data that are relevant to the subject's pregnancy attributes. For instance, if the subject has certain risk factors, the module can prioritize identifying considerations related to managing these risks based on the outcomes observed in the cohort.

[0134] The considerations are formulated by synthesizing the comparative analysis results into actionable insights. This synthesis might involve using decision trees, statistical models, or machine learning algorithms to predict the most relevant considerations for the subject's unique circumstances. The module might also take into account the latest medical guidelines and research to ensure the advice provided is up-to- date and evidence-based.

[0135] Identifying module 108 can identify a variety of considerations. For example, identifying module 108 can suggest, without limitation, lifestyle changes, medical screenings, or specific discussions to have with healthcare providers. These suggestions can be specially tailored to align with the subject's profile and the aggregated experiences and outcomes of the identified cohort, thus providing personalized and clinically relevant recommendations.

[0136] To ensure the pertinence and accuracy of the considerations, identifying module 108 can also incorporate feedback mechanisms. These could involve user feedback on the relevance of previous considerations or the outcomes of following certain recommendations, which the module can use to refine future advice.

[0137] Returning to FIG. 3, at step 350, one or more of the systems described herein can create a pregnancy report that provides the at least one consideration for the subject. For example, reporting module 110 can create a pregnancy report 222 that provides consideration 220.

[0138] Reporting module 110 can create pregnancy report 222 in a variety of ways. For example, reporting module 110 can generate pregnancy report 222 by collating all pertinent considerations identified by identifying module 108 and, in some examples, selecting one or more considerations based on any suitable criteria such as maximum benefit to pregnancy outcomes, lowest patient cost to implement, least intrusive to the gestational parent, and so forth. Reporting module 110 can also structure the report to include a summary of the similarities and differences between the subject's pregnancy and the identified cohort, providing context and relevance to the provided considerations.

[0139] Reporting module 110 can incorporate various elements into the report, such as educational information that elucidates points and / or degrees of similarity or dissimilarity of the subject to identified cohorts, suggested questions to pose (e.g., to physicians) for healthcare provider discussions, and potential impacts of interventions on specific pregnancy features. The report can also present statistical information, such as the rate of occurrence of certain pregnancy features within the cohort, along with qualitative and quantitative measures. This could include visual representations like graphs or charts to convey the average magnitude of these features.

[0140] To illustrate, FIG. 15 and FIG. 16 include information that could be included in a pregnancy report (e.g., pregnancy report 222). FIG. 15 shows a chart 1500 that illustrates various pregnancy factors and that indicates similarity or dissimilarity of pregnancy features in different cohorts (e.g., a first cohort that includes gestational parents 20-25 years of age with BMI less than or equal to 25 who have attended no college and received fewer than six doctor's visits, a second cohort that includes gestational parents 32- 37 years of age with BMI greater than 30 who attended college and received greater than or equal to 13 doctor's visits, and all 2017 pregnancies reported by the CDC). Likewise, FIG. 16 shows a chart 1600 that illustrates a variability of experiences among a particular cohort within data provided by the CDC for the year 2017.

[0141] In some embodiments, reporting module 110 can be equipped to tailor the considerations in the report based on biomarker data associated with the patient. This ensures that the report is not only personalized but also medically precise, reflecting the unique physiological profile of the subject.

[0142] In some embodiments, reporting module 110 can employ one or more generative artificial intelligence (Al) tools to produce pregnancy report 222. A generative Al tool can be an advanced system that has undergone extensive pre-training using diverse and rich pre-existing data sets. These data sets can include publicly available information such as governmentally compiled statistics on birth rates, maternal and fetal health metrics, and epidemiological studies. They can also encompass private data sources that can include detailed and individualized health records, research data, and proprietary information from healthcare providers and research institutions.

[0143] The pre-training of the one or more generative Al tools can involve processing and learning from these data sources to recognize patterns, understandcorrelations, and generate predictive models that can intelligently extrapolate insights relevant to pregnancy care. This learning can enable a suitably trained Al to dynamically create content within pregnancy report 222 that is personalized and directly pertinent to the user's specific circumstances. For example, based on the provided set of attributes, the Al may be capable of generating sections of the report that discuss risk factors, forecast potential outcomes, or provide bespoke health and wellness advice.

[0144] Furthermore, some generative Al tools can be capable of updating their content generation capabilities in real-time, assimilating new data as it becomes available. This can ensure that pregnancy report 222 is not only personalized but also reflects current research and data, providing the user with relevant and timely information. The dynamic nature of such an Al tool can allow reporting module 110 to create a report that is both comprehensive and adaptable, accommodating the evolving nature of the user's pregnancy and any new developments in maternity care research.

[0145] In some examples, once the pregnancy report is created, reporting module 110 can present the pregnancy report to a user (e.g., user 208 or another user). Reporting module 110 can therefore interface with an output graphical user interface of a computing device (e.g., user interface 210 or another user interface), ensuring that the presentation of the report is user-friendly and conducive to a positive user experience.

[0146] The output interface can be designed to be intuitive, allowing users to navigate through the report easily and understand the provided information without requiring specialized medical knowledge. Interactive elements can be included to allow users to delve deeper into specific sections of the report for more detailed information.

[0147] Other embodiments of the present disclosure relate to using various methods, systems, and biomarkers described herein, and integrating or combining the samewith clinical or demographic variables, to generate test reports or models to estimate the probability of a pregnant female delivering, in each week, e.g., from week 37 to 41 (see, e.g., FIG. 17) and / or the most likely week of delivery. In some embodiments, such test reports or models herein use data from a cohort of subjects that have similar term deliveries and factors as the pregnant female, such as age, BMI, race, hypertension / preeclampsia in a prior pregnancy, preterm birth in a prior pregnancy, c-section delivery in a prior pregnancy, education level, being a first-time mother, chronic diabetes, gestational diabetes in the current pregnancy, and hypertension or preeclampsia in the current pregnancy.

[0148] Some embodiments utilize a combination of clinical, demographic, and / or biomarker data, and the method can produce a result that is both qualitative (e.g., the most likely week to deliver) and quantitative (e.g., the probability of each week to deliver). In some embodiments, the method is intended to predict term births (i.e., 37 weeks or later).

[0149] In some embodiments, the method utilizes the pregnant subject's (denoted as "S") cohort (denoted as "C(S)"), which can be characterized as women who have similar biomarker results, demographics, and clinical factors as the subject S. The weekly delivery estimates can be derived from their cohort C(S).

[0150] In some embodiments, a database from the Centers for Disease Control and Prevention (CDC) can be used for clinical and demographic factors integrated into the estimation of probability of delivery in each week and prediction of most likely week of delivery. Women similar to S in the CDC database, denoted as "CDC(S)", can be formed into a cohort defined as those with term deliveries and similarities on the following clinical or demographic factors: Age; BMI; Race; Hypertension / preeclampsia in a prior pregnancy; Preterm birth in a prior pregnancy; C-section delivery in a prior pregnancy; Education level;First time mother; Chronic diabetes; Gestational diabetes in the current pregnancy;Hypertension or preeclampsia in the current pregnancy. For non-categorical factors such as age, a window can be used, e.g., women whose age is within 2 years of the subject's age.

[0151] Once the CDC(S) cohort is formed, the probability of delivering for each week, 37 to 41, can be determined by taking the average across subjects in CDC(S) to produce a probability distribution over these weeks.

[0152] Thus, an exemplary method yields a probability distribution across birth weeks 37 to 41, where: Week 41 includes week 41 and 42; the probability distribution sums to 1; and the most likely delivery week will be the week with the highest probability.

[0153] As one example of these embodiments, FIG. 17 provides an exemplary bar graph of the birth week probability distribution where the factors above, in order, are: 1. 32 (age), 2. 23.3 (BM I), 3. White (race), 4. No (hypertension / preeclampsia in a prior pregnancy), 5. No (preterm birth in a prior pregnancy), 6. Yes (c-section delivery in a prior pregnancy), 7. High School (education level), 8. No (first time mother), 9. No (chronic diabetes), 10. No (gestational diabetes in the current pregnancy), and 11. No (hypertension or preeclampsia in the current pregnancy).

[0154] For biomarker data used in these embodiments, the biomarker assay (TTB) results for subject S, denoted as "TTB(S)", can be used. The biomarker assay (TTB) can be any of the assay methods known in the art. Subjects can be binned using three classifications, denoted "T(S)" using the measurement TTB(S):If TTB(S) < median(TTB) - std(TTB) then T(S) is positive ('skewed right'). If TTB(S) > median(TTB) + std(TTB) then T(S) is negative ('skewed left'). Otherwise, T(S) is neutral ('no skew').

[0155] TTB can be the distribution of assay values over the database used for clinical and demographic factors, in which case the database (e.g., CDC(S)) is restricted tothose women with the same assay result T(S) as subject S (or assay results within some variance of subject S's result, e.g., within 20%, 15%, 10%, 9%, 8%, 7%, 6%, 5%, 4%, 3%, 2%, 1%, 0.5%, 0.2%, or 0.1%). In some embodiments the biomarker assay method distribution comes from a different set of subjects from the clinical / demographic factor distribution.

[0156] In some embodiments, pregnancies can be assigned to one of the three groups: "positive", "neutral", and "negative", as shown in FIG. 18. As described above, FIG. 18 shows a line graph of the distribution of such "neutral", "positive", and "negative" groups and their probability to deliver for each week shown (37 to 42). Neutral represents the average weekly probability whereas the "positive group" is skewed to the right of the "neutral" group, and the "negative" group is skewed to the left. With this classification of pregnancies based on the biomarker assay methods of the present disclosure, each subject S can be assigned to one of three groups T(S).

[0157] In some embodiments where the clinical, demographic, and biomarker factors are all derived from the same database of subjects (as in the examples described above), there generally is no need to integrate. In some embodiments, disparate databases (or data from them) can be integrated to derive a delivery week probability distribution that incorporates information from each database (e.g., using Bayes Theorem).

[0158] In some such embodiments, the weekly probability distribution from one database (e.g., CDC database) can be used as the base distribution (i.e., the prior) and can then be adjusted using the weekly probability distribution from another database. For example, the weekly probability distribution from the CDC database, based on clinical and / or demographic factors (e.g., Age; BMI; Race; Hypertension / preeclampsia in a prior pregnancy; Preterm birth in a prior pregnancy; C-section delivery in a prior pregnancy;Education level; First time mother; Chronic diabetes; Gestational diabetes in the currentpregnancy; Hypertension or preeclampsia in the current pregnancy), can be used as the base distribution and can then be adjusted using the weekly probability distribution from a database of biomarker assay results, all to yield a refined estimation of the probability of delivery in each of weeks, e.g., 37-41, and the week with the highest probability of delivery.

[0159] In some aspects, the classification of the subject based on biomarker data associated with time to birth may be performed using two or more percentiles or thresholds. This approach can allow for a more granular classification that adapts to various data distributions and clinical needs. For example, the classification can use quartiles, quintiles, or any other suitable number of divisions based on the time to birth data distribution. The number and placement of these thresholds can be determined based on clinical relevance, statistical analysis, or machine learning algorithms that optimize the predictive power of the classification.

[0160] Thus, in some embodiments the disclosure provides a method of predicting the week of gestation in which a pregnant female is most likely to deliver, the method comprising: (a) obtaining a biological sample obtained from said pregnant female; (b) detecting the presence or amount of one or more isolated biomarkers in said biological sample (e.g., a pair of biomarkers); (c) comparing clinical factors for said pregnant female (e.g., age, BMI, race, hypertension / preeclampsia in a prior pregnancy, preterm birth in a prior pregnancy, c-section delivery in a prior pregnancy, education level, being a first-time mother, chronic diabetes, gestational diabetes in the current pregnancy, and hypertension or preeclampsia in the current pregnancy) to the same clinical factors in a cohort of reference pregnant females (e.g., in a proprietary or public database, e.g., in a CDC database); and (d) deriving from (b) and (c) the probability said pregnant female will deliver in each of certain specific weeks of gestation (e.g., each of weeks 37 through 41). In someembodiments, step (c) of the method is performed before steps (a) and (b). In some embodiments, step (a), (b), and (c) are performed in this order. In some embodiments, step (b) comprises detecting the presence or amount of a pair of isolated biomarkers. In some such embodiments the probability in step (d) is derived by (dl) deriving the probability said pregnant female will deliver in each of certain specific weeks of gestation (e.g., each of weeks 37 through 41) based at least in part on the comparison in (c) and (d2) adjusting the probability in (dl) by the probability derived from comparing the amount of biomarker(s) detected in (b) with the amount of biomarkers detected in a reference cohort of pregnant females. In some embodiments the adjustment is made using Bayes Theorem.

[0161] The following example further illustrates the methods and systems described above by providing a detailed implementation, including clinical, demographic, and biomarker factors. The following example demonstrates the generation of an exemplary "test report" or "model" that can be used to estimate the probability of a pregnant subject delivering in each week from weeks 37 to 41, i.e., term births. Such a test utilizes a combination of clinical, demographic, and / or biomarker factors. The test report is both qualitative (e.g., the most likely week to deliver) and quantitative (e.g., the probability of each week to deliver).

[0162] The test herein consists of a blood test along with demographic and clinical factors that are used to estimate the probability of a mother delivering in each week from weeks 37 to 41. The most likely week of delivery is the one with highest probability. The test is intended to predict term births (i.e., 37 weeks or later).

[0163] The test utilizes the pregnant subject's (denoted as "S") cohort. As used herein, the cohort (denoted as "C(S)") is characterized as women who have similar blood test results, demographics, and clinical factors as the subject, "S". It is from this cohort (C(S))that the weekly delivery estimates are derived. It has been demonstrated that probability of delivery in each week for pregnancy cohorts is highly reproducible.

[0164] For clinical and demographic factors, a database from the Centers for Disease Control and Prevention (CDC) is used. Women similar to S in the CDC database, denoted as "CDC(S)", are defined as those with term deliveries and similarities on the following factors: (a) BMI; (b) Race; (c) Hypertension or preeclampsia in a prior pregnancy; (d) Preterm birth in a prior pregnancy; (e) C-section delivery in a prior pregnancy; (f) Education level; (g) First-time mother; (h) Chronic diabetes; (i) Gestational diabetes in the current pregnancy; and (j) Hypertension or preeclampsia in the current pregnancy.

[0165] For non-categorical factors such as age, a window is used, e.g., women whose age is within 2 years of the subject's age.

[0166] Once CDC(S) is formed, the probability of delivering for each week, 37 to 41, is determined by taking the average across subjects in CDC(S). This produces a probability distribution over these weeks.

[0167] Thus, an exemplary test report, for instance, comprises or consists of a probability distribution across birth weeks 37 to 41, where:Week 41 includes week 41 and 42;The probability distribution sums to 1; andThe most likely delivery week will be the week with the highest probability.

[0168] Such a test report is both qualitative (e.g., most likely week to deliver) and quantitative (e.g., probability of each week to deliver).

[0169] To further illustrate, FIG. 17 provides an exemplary bar graph of the birth week probability distribution where the factors above, in order, are: 1. 32 (age), 2. 23.3(BMI), 3. White (race), 4. No (hypertension / preeclampsia in a prior pregnancy), 5. No (preterm birth in a prior pregnancy), 6. Yes (c-section delivery in a prior pregnancy), 7. High School (education level), 8. No (first time mother), 9. No (chronic diabetes), 10. No (gestational diabetes in the current pregnancy), and 11. No (hypertension or preeclampsia in the current pregnancy).

[0170] For biomarker factors, the biomarker assay time to birth (TTB) results for subject S, denoted as "TTB(S)", is used. Subjects have three classifications, denoted "T(S)" using the measurement TTB(S):If TTB(S) < median(TTB) - std(TTB) then T(S) is positive ('skewed right'). If TTB(S) > median(TTB) + std(TTB) then T(S) is negative ('skewed left'). Otherwise, T(S) is neutral ('no skew').

[0171] TTB, as used in this example, is the distribution of all assay values over the database used above for clinical and demographic factors in which case CDC(S) is restricted to those women with the same assay result T(S) as subject S. This study illustrates the case where the TTB distribution comes from a different set of subjects such as the PAPR study subjects (NCT01371019).

[0172] Thus, using the PAPR study, restricted to term deliveries, all pregnancies are assigned to one of the three groups: "positive", "neutral", and "negative", as shown in FIG. 18. Specifically, FIG. 18 shows a line graph of the distribution of such "neutral", "positive", and "negative" groups and their probability to deliver for each week shown (37 to 42). Neutral represents the average weekly probability whereas the "positive group" is skewed to the right of the "neutral" group, and the "negative" group is skewed to the left.The Wilcoxon Rank-Sum Test demonstrates that there are highly significant shifts (p < 0.001)between positive and non-positive subjects as well as between negative and non-negative subjects.

[0173] In summary, with this classification of pregnancies based on the TTB assay, each subject S is assigned to one of three groups T(S).

[0174] If the clinical, demographic, and biomarker factors are all derived from the same database of subjects, then there is no need to integrate, as described above. If not, disparate databases (or data from them) can be integrated to derive a delivery week probability distribution that incorporates information from each database using Bayes Theorem.

[0175] The approach is to use the weekly probability distribution from one database as the base distribution (i.e., the prior) and adjust it using the weekly probability distribution from another database.

[0176] In some aspects, the systems and methods described herein may utilize the biomarker data associated with time to birth to enhance the personalization and accuracy of the pregnancy report. For example, one or more of modules 102 (e.g., receiving module 104) may obtain subject biomarker data associated with time to birth. This subject biomarker data may be obtained via one or more suitable assays, such as those described above. This data may be integrated with other attributes and features to provide more precise predictions about the timing of birth and related considerations. For example, the pregnancy report may include recommendations tailored to the subject's time to birth classification, such as suggested timing for additional prenatal visits, specific nutritional advice, or preparatory steps for labor and delivery.

[0177] The time to birth data may also influence the identification of relevant pregnancy cohorts, potentially leading to more nuanced considerations in the report. Forinstance, subjects classified as "positive" (skewed right) based on their time to birth biomarker data may receive considerations focused on preparing for potentially earlier delivery, while those classified as "negative" (skewed left) may receive guidance on managing longer gestational periods.

[0178] Furthermore, the systems and methods may dynamically adjust the weight given to time to birth data in generating considerations as the pregnancy progresses. This approach may allow for the incorporation of changing biomarker data throughout the gestational period, potentially improving the accuracy and relevance of the pregnancy report over time.

[0179] By incorporating time to birth data into the cohort identification and report generation processes, the systems and methods described herein may provide users with a more comprehensive and personalized set of considerations, enhancing their ability to make informed decisions throughout their pregnancy journey.

[0180] In conclusion, the examples herein demonstrate the generation of an exemplary "test report" or "model" that can be used to estimate the probability of a pregnant subject delivering in each week from weeks 37 to 41 (i.e., term births) using, e.g., clinical, demographic, and biomarker factors and variables. The test report is both qualitative (e.g., the most likely week to deliver) and quantitative (e.g., the probability of each week to deliver).

[0181] As may be clear from the foregoing examples and explanations, the systems and methods described herein provide many benefits over conventional approaches to propagation of pregnancy information and advice. Embodiments of the systems and methods described herein can provide a nuanced approach to pregnancy care by tailoring information to individual experiences. Embodiments can receive a set ofattributes from users and, with a focus on relevance, can generate a unique key that encapsulates these attributes. This key can then be used to query a comprehensive pregnancy cohort data model to identify a cohort of pregnancies sharing similar features.

[0182] Once a relevant cohort is identified, embodiments can discern personalized considerations for the user. These considerations can be drawn from an in- depth analysis of the cohort's data, ensuring they are highly pertinent and actionable. Embodiments can adaptively modify these considerations (e.g., based on evolving biomarker data) to provide advice that is both current and contextually significant. The result can be a dynamic, user-centric report that offers insights into the pregnancy, from risk profiles and healthcare visit frequencies to potential complications and outcomes.

[0183] Moreover, some embodiments can leverage generative artificial intelligence, pre-trained on a diverse array of pregnancy data, to create content within the pregnancy report that is both personalized and evidence-based. This Al tool can enable the systems and methods described herein to present users with information that not only informs their healthcare decisions but also empowers them with knowledge tailored to their unique pregnancy journey. It can be designed to bridge the gap between general pregnancy guidelines and individual needs, thus enhancing the overall experience and outcomes of pregnancy care.

[0184] By integrating data from varied sources, including public health records and private studies, embodiments of this disclosure may enable a multi-dimensional view of pregnancy, providing users with a level of insight and personalization previously unattainable, ultimately leading to better care, informed decision-making, and improved health outcomes for both the gestational parent and the developing fetus.

[0185] In some embodiments, the disclosure provides a computer-implemented method comprising: (a) receiving, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; (b) generating, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes; (c) using the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; (d) identifying, based on the cohort of pregnancies, at least one consideration forthe subject; and (e) creating a pregnancy report that provides the at least one consideration for the subject. In some embodiments, the set of attributes comprises one or more of the attributes listed in Table 1.Table 1

[0186] In some such embodiments, the at least one feature comprises one or more of those shown in Table 2.Table 2

[0187] In some such embodiments, the considerations for the cohort (e.g., incidences of one or more features) are compared to the considerations for a reference population (e.g., average incidence of such features in the U.S. population of pregnant females (e.g., from one or more years of Natality Public Use File published by the CDC)). Insome such embodiments, the incidence of certain specific features in the subject's locale (e.g., U.S. state) can be compared to the national average incidence of such features. An example report showing such a set of attributes, features and considerations is shown in FIGS. 19A- 19F.EXAMPLESEXAMPLE 1

[0188] The following set of attributes of a subject, linked to at least one feature of a pregnancy, were received via a graphical user interface of a computing device: age at baby's birth: 20; height: 5'4"; Hispanic origin: no; previous live births: 1; preterm births: 1; current weight: 200 lbs.; fertility treatments used: no; pregnancy type: one baby (singleton); chronic diabetes: yes; chronic hypertension: no.

[0189] Based on this set of attributes and the relevance of the set to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes was generated. This key was then used to identify, from a pregnancy cohort data model comprising the CDC's Natality Public Use File for the years 2019-2022, a cohort of 1,925 pregnancies having a plurality of pregnancy features. This cohort had the following attributes, in common with the subject: age at baby's birth: 34 or below; BMI: 30 or above; pregnancy type: one baby (singleton); fertility treatments: no; previous live births: yes; preterm births: yes; previous c-sections: no; chronic diabetes: yes; chronic hypertension: no.

[0190] Based on this cohort of pregnancies, a set of features for the subject was identified (Table 3), and the incidence of each feature in the subject's cohort (each a consideration) was compared to the national average incidence (Table 4). National average was defined as the percentage of each outcome for all women who had recorded births inthe U.S. during the relevant years, and excluded women who had multiple pregnancies (such as twins or triplets) or used fertility treatments to get pregnant.Table 3Table 4

[0191] The subject's location was also used to compare the incidence of certain pregnancy features in her state to the national average incidence (Table 5).Table 5

[0192] An example pregnancy report that provided this set of considerations (and attributes and features) for the subject was created and is included herein as FIGS. 19A-19F.

[0193] As detailed above, the computing devices and systems described and / or illustrated herein broadly represent any type or form of computing device or system capable of executing computer-readable instructions, such as those contained within the modules described herein. In their most basic configuration, these computing device(s) can each include at least one memory device and at least one physical processor.

[0194] Although illustrated as separate elements, the modules described and / or illustrated herein can represent portions of a single module or application. In addition, in certain embodiments one or more of these modules can represent one or more software applications or programs that, when executed by a computing device, can cause the computing device to perform one or more tasks. For example, one or more of the modules described and / or illustrated herein can represent modules stored and configured to run on one or more of the computing devices or systems described and / or illustrated herein. One or more of these modules can also represent all or portions of one or more special-purpose computers configured to perform one or more tasks.

[0195] In addition, one or more of the modules described herein can transform data, physical devices, and / or representations of physical devices from one form to another. For example, one or more of the modules recited herein can receive attribute data to be transformed, transform the attribute data, output a result of the transformation to identify one or more pregnancy cohorts, use the result of the transformation to generate a pregnancy report, and store the result of the transformation to update one or more pregnancy cohort data models. Additionally or alternatively, one or more of the modules recited herein can transform a processor, volatile memory, non-volatile memory, and / or any other portion of a physical computing device from one form to another by executing on the computing device, storing data on the computing device, and / or otherwise interacting with the computing device.

[0196] The term "computer-readable medium," as used herein, generally refers to any form of device, carrier, or medium capable of storing or carrying computer-readable instructions. Examples of computer-readable media include, without limitation, transmission-type media, such as carrier waves, and non-transitory-type media, such asmagnetic-storage media (e.g., hard disk drives, tape drives, and floppy disks), optical-storage media (e.g., Compact Disks (CDs), Digital Video Disks (DVDs), and BLU-RAY disks), electronic- storage media (e.g., solid-state drives and flash media), and other distribution systems.

[0197] The process parameters and sequence of the steps described and / or illustrated herein are given by way of example only and can be varied as desired. For example, while the steps illustrated and / or described herein may be shown or discussed in a particular order, these steps do not necessarily need to be performed in the order illustrated or discussed. The various exemplary methods described and / or illustrated herein can also omit one or more of the steps described or illustrated herein or include additional steps in addition to those disclosed.

[0198] The preceding description has been provided to enable others skilled in the art to best utilize various aspects of the exemplary embodiments disclosed herein. This exemplary description is not intended to be exhaustive or to be limited to any precise form disclosed. Many modifications and variations are possible without departing from the spirit and scope of the instant disclosure. The embodiments disclosed herein should be considered in all respects illustrative and not restrictive. Reference should be made to the appended claims and their equivalents in determining the scope of the instant disclosure.

[0199] Unless otherwise noted, the terms "connected to" and "coupled to" (and their derivatives), as used in the specification and claims, are to be construed as permitting both direct and indirect (i.e., via other elements or components) connection. In addition, the terms "a" or "an," as used in the specification and claims, are to be construed as meaning "at least one of." Finally, for ease of use, the terms "including" and "having" (and their derivatives), as used in the specification and claims, are interchangeable with and have the same meaning as the word "comprising.

Claims

CLAIMSWhat is claimed is:

1. A computer-implemented method comprising: receiving, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; generating, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes; using the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; identifying, based on the cohort of pregnancies, at least one consideration for the subject; and creating a pregnancy report that provides the at least one consideration for the subject.

2. The computer-implemented method of claim 1, wherein the set of attributes of the subject linked to at least one feature of the pregnancy comprises at least one of: a demographic characteristic; a health characteristic; a prior pregnancy characteristic; or a current pregnancy characteristic.

3. The computer-implemented method of any one of claims 1-2, wherein the set of attributes of the subject linked to at least one feature of the pregnancy comprises at least one of: an indication of whether a gestational parent is nulliparous; an age of at least one patient associated with the pregnancy; a body-mass index (BMI) of the at least one patient; a race of the at least one patient; a set of risk factors associated with the at least one patient; or biomarker data associated with the at least one patient.

4. The computer-implemented method of claim 3, wherein the set of attributes of the subject linked to at least one feature of the pregnancy comprises subject biomarker data associated with time to birth.

5. The computer-implemented method of any one of claims 1-4, wherein the set of attributes of the subject linked to at least one feature of the pregnancy comprises at least one of the attributes listed in Table 1.

6. The computer-implemented method of any one of claims 1-5, wherein the at least one feature comprises at least one of the features listed in Table 2.

7. The computer-implemented method of any one of claims 1-6, wherein the pregnancy report comprises at least one of: an indication of a degree of similarity of the pregnancy to other pregnancies in the cohort;educational information associated with at least one point of similarity of the pregnancy to other pregnancies in the cohort; educational information associated with at least one point of dissimilarity of the pregnancy to other pregnancies in the cohort; at least one suggested question regarding the pregnancy for a patient associated with the pregnancy to pose to a physician; an impact of an intervention on the at least one pregnancy feature; a rate of occurrence of at least one pregnancy feature; a qualitative measure of the at least one pregnancy feature within the cohort; a quantitative measure of the at least one pregnancy feature within the cohort; or an average magnitude of the at least one pregnancy feature.

8. The computer-implemented method of any one of claims 1-7, wherein the pregnancy report comprises data corresponding to at least one of the features listed in Table 3, Table 4, or Table 5.

9. The computer-implemented method of any one of claims 1-8, wherein creating the pregnancy report that provides the at least one consideration for the subject comprises modifying the at least one consideration for the pregnancy report based on biomarkers associated with at least one patient associated with the pregnancy.

10. The computer-implemented method of any one of claims 1-9, wherein the cohort of pregnancies having the at least one pregnancy feature comprises data representative of at least one of:a risk profile for the cohort for the at least one pregnancy feature; a number of healthcare visits associated with the cohort; an incidence rate of infections among the cohort; a frequency of breech presentations within the cohort; a preeclampsia risk associated with the cohort; a surprise delivery risk associated with the cohort; a mean length of stay associated with the cohort; biomarker data that indicates biomarkers associated with pregnancy complications or time to birth.

11. The computer-implemented method of any one of claims 1-10, further comprising generating the pregnancy cohort data model based on at least one pregnancy data source.

12. The computer-implemented method of claim 11, wherein generating the pregnancy cohort data model comprises, for each data source included in the at least one pregnancy data source, generating a set of cohort aggregate features comprising at least clinical features and biomarker features.

13. The computer-implemented method of claim 12, wherein using the key to identify, from the pregnancy cohort data model, data representative of the cohort of pregnancies similar to the subject comprises associating the key with, for each data source included in the at least one pregnancy data source, a set of cohort aggregate features.

14. The computer-implemented method of any one of claims 1-13, wherein generating the key that is representative of the set of attributes comprises determining, based on a set of predetermined relevance metrics, the relevance of the subset of the set of attributes to identifying cohorts of pregnancies similar to the subject.

15. The computer-implemented method of any one of claims 1-14, wherein creating the pregnancy report comprises creating the pregnancy report via a computer- implemented generative artificial intelligence tool configured to generate pregnancy-related information based on pre-existing pregnancy data.

16. The computer-implemented method of claim 15, wherein the computer- implemented generative artificial intelligence tool is pre-trained using at least one pregnancy data source, the at least one pregnancy data source comprising at least one of: one or more public pregnancy data sources comprising governmentally compiled pregnancy data; and one or more private data sources comprising privately compiled pregnancy data different from data included in the one or more public pregnancy data sources.

17. The computer-implemented method of any one of claims 1-16, further comprising presenting the pregnancy report to a user via an output graphical user interface of an output computing device.

18. A system comprising: a receiving module, stored in memory, that receives, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; a generating module, stored in memory, that generates, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes; an identifying module, stored in memory, that: uses the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; and identifies, based on the cohort of pregnancies, at least one consideration for the subject; a reporting module, stored in memory, that creates a pregnancy report that provides the at least one consideration for the subject; and at least one physical processor that executes the receiving module, the generating module, the identifying module, and the reporting module.

19. The system of claim 18, wherein the generating module further generates the pregnancy cohort data model based on at least one pregnancy data source.

20. The system of claim 19, wherein the generating module generates the pregnancy cohort data model by, for each data source included in the at least one pregnancy data source, generating a set of cohort aggregate features comprising at least clinical features and biomarker features.

21. The system of claim 20, wherein the identifying module uses the key to identify, from the pregnancy cohort data model, data representative of the cohort of pregnancies having the at least one pregnancy feature by associating the key with, for each data source included in the at least one pregnancy data source, a set of cohort aggregate features.

22. The system of any one of claims 18-21, wherein the generating module generates the key that is representative of the set of attributes by determining, based on a set of predetermined relevance metrics, the relevance of the subset of the set of attributes to identifying cohorts of pregnancies similar to the subject.

23. The system of any one of claims 18-22, wherein the reporting module creates the pregnancy report via a computer-implemented generative artificial intelligence tool configured to generate pregnancy-related information based on pre-existing pregnancy data.

24. A non-transitory, computer-readable medium comprising computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to: receive, from a user via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; generate, based on at least a subset of the set of attributes and a relevance of the subset to identifying at least one cohort of pregnancies similar to the subject, a key that is representative of the set of attributes;use the key to identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature; identify, based on the cohort of pregnancies, at least one consideration for the subject; and create a pregnancy report that provides the at least one consideration for the subject.

25. A computer-implemented method comprising: receiving, via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; obtaining subject biomarker data associated with time to birth (TTB); generating a classification of the subject by classifying the subject into one of three groups based on the subject biomarker data, wherein: the subject is classified as positive if the subject biomarker data associated with TTB indicates less than a median TTB minus a standard deviation of TTB, the subject is classified as negative if the subject biomarker data associated with TTB indicates greater than the median TTB plus the standard deviation of TTB, and the subject is classified as neutral otherwise; identifying, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature similar to the subject based on the set of attributes; generating a probability distribution of delivery weeks for the subject based on the identified cohort and the subject's classification;creating a pregnancy report comprising the probability distribution and at least one consideration for the subject, the at least one consideration tailored to the subject's classification; and presenting the pregnancy report to the user via the graphical user interface of the computing device.

26. The computer-implemented method of claim 25, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further comprises at least one of: a demographic characteristic; a health characteristic; a prior pregnancy characteristic; or a current pregnancy characteristic.

27. The computer-implemented method of claim 25, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further comprises at least one of: an indication of whether a gestational parent is nulliparous; an age of at least one patient associated with the pregnancy; a body-mass index (BMI) of the at least one patient; a race of the at least one patient; an education level of the at least one patient; a set of risk factors associated with the at least one patient; or an indication of chronic diabetes associated with the gestational parent.

28. The computer-implemented method of claim 25, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further comprises at least one of, associated with the subject and in the pregnancy: an indication of hypertension; an indication of preeclampsia; or indication of gestational diabetes.

29. The computer-implemented method of claim 25, wherein the set of attributes of the subject linked to at least one feature of the pregnancy further comprises at least one of, associated with the subject and in a prior pregnancy: an indication of hypertension; an indication of preeclampsia; an indication of gestational diabetes; an indication of a caesarean section delivery; or an indication of preterm birth.

30. The computer-implemented method of claim 25, further comprising dynamically adjusting a weight given to the subject biomarker data associated with TTB in generating the probability distribution as the pregnancy progresses.

31. The computer-implemented method of claim 25, wherein the at least one consideration tailored to the subject's classification comprises: for subjects classified as positive, considerations focused on preparing for potentially earlier delivery;for subjects classified as negative, guidance on managing longer gestational periods; and for subjects classified as neutral, considerations based on average weekly probability of delivery.

32. The computer-implemented method of claim 25, further comprising: obtaining the subject biomarker data associated with TTB from a first database; obtaining additional attributes from a second database; and integrating data from the first and second databases using Bayes Theorem to derive the probability distribution of delivery weeks.

33. The computer-implemented method of claim 25, wherein generating the classification of the subject comprises classifying the subject into at least two groups based on the subject biomarker data associated with TTB, wherein: the classification is determined using at least two different thresholds of a TTB data distribution; and each of the different thresholds are determined based on at least one of clinical relevance, statistical analysis, or machine learning algorithms that optimize predictive power of the classification.

34. A system comprising: a receiving module, stored in memory, that: receives, via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy;obtains subject biomarker data associated with time to birth (TTB); generates a classification of the subject by classifying the subject into one of three groups based on the subject biomarker data associated with TTB, wherein: the subject is classified as positive if the subject biomarker data associated with TTB indicates less than a median TTB minus a standard deviation of TTB, the subject is classified as negative if the subject biomarker data associated with TTB indicates greater than the median TTB plus the standard deviation of TTB, and the subject is classified as neutral otherwise; an identifying module, stored in memory, that identifies, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature similar to the subject based on the set of attributes; a probability module, stored in memory, that generates a probability distribution of delivery weeks for the subject based on the identified cohort and the subject's classification; a reporting module, stored in memory, that creates a pregnancy report comprising the probability distribution and at least one consideration for the subject, wherein the at least one consideration is tailored to the subject's classification; a presentation module, stored in memory, that presents the pregnancy report to the user via the graphical user interface of the computing device; and at least one physical processor that executes the receiving module, the classification module, the identifying module, the probability module, the reporting module, and the presentation module.

35. The system of claim 34, wherein the probability module generates the probability distribution by dynamically adjusting a weight given to the subject biomarker data as the pregnancy progresses.

36. The system of any one of claims 34-35, wherein the at least one consideration tailored to the subject's classification comprises: for subjects classified as positive, considerations focused on preparing for potentially earlier delivery; for subjects classified as negative, guidance on managing longer gestational periods; and for subjects classified as neutral, considerations based on average weekly probability of delivery.

37. A non-transitory, computer-readable medium comprising computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to: receive, via a graphical user interface of a computing device, a set of attributes of a subject linked to at least one feature of a pregnancy; obtain subject biomarker data associated with time to birth (TTB); generate a classification of the subject by classifying the subject into one of three groups based on the subject biomarker data associated with TTB , wherein: the subject is classified as positive if the subject biomarker data associated with TTB indicates less than a median TTB minus a standard deviation of TTB,the subject is classified as negative if the subject biomarker data associated with TTB indicates greater than the median TTB plus the standard deviation of TTB, and the subject is classified as neutral otherwise; identify, from a pregnancy cohort data model, a cohort of pregnancies having at least one pregnancy feature similar to the subject based on the set of attributes; generate a probability distribution of delivery weeks for the subject based on the identified cohort and the subject's classification; create a pregnancy report comprising the probability distribution and at least one consideration for the subject, wherein the at least one consideration is tailored to the subject's classification; and present the pregnancy report to the user via the graphical user interface of the computing device.

Images