Application of artificial intelligence in screening of birth defects a scoping review

MINISTRY OF EDUCATION MINISTRY OF HEALTHHANOI MEDICAL INIVERSITY HVY DO DEC APPLICATION OF ARTIFICIAL INTELLIGENCE IN SCREENING OF BIRTH DEFECTS: A SCOPING REVIEW GRADUATION THESIS DOCTO

MINISTRY OF EDUCATION MINISTRY OF HEALTH

HANOI MEDICAL INIVERSITY

HVY DO DEC

APPLICATION OF ARTIFICIAL INTELLIGENCE IN SCREENING OF BIRTH DEFECTS: A SCOPING REVIEW

GRADUATION THESIS DOCTOR OFPREVENTn E MEDICINE

2015 2021

SUPERVISOR:

LE MINH GUNG, MD, PhD

HA NOI 2021

1 would like to offer my thanks to the stall's of Hanoi Medical University School of Preventive Medicine and Public Health, as well as teachers from the Department of Epidemiology' for your guidance and support.

1 would like to express my great appreciation to all the individuals and teams below, that without them I would not be able to accomplish my graduation thesis

Firstly I would like to express my deepest gratitude to my supervisor Assoc.Prof Le Minh Giang for his guidance Even though he lias always been busy, he still willing to give me some of his precious time This has always been very much appreciated

The second and third person that I want to say thanks to is A/Prof Nguyen Thi Trang and Ms Le Thi Minh Phuong from Department of Biomedical Genetics for your help in birth defects, especially Ms Le Till Minh Phuong lor the time you spent screening articles with me

In addition, because I can always ask you about scoping review thank you Ms Nguyen Thi Hue from Center for Research and Training on Substance Abuse- HIV

Last but not least I would like to give thanks to my family and close friends, for their support and encouragement throughout my study

Hanoi May 2021

Do Due Iluy

Respectfully addressed to:

Board of Hanoi Medical University

Board of Preventive Medicine and Public Health School

Department of Epidemiology

Board of Di ssertalion Assessment

My name is Do Due Huy - Student of Hanoi Medical University, course

2015 - 2021 majoring in Preventive Medicine Doctor, hereby declare that:This is a research that I conducted under the scientific guidance of Assoc.Prof Le Minh Giang Tire data and results presented in tire research are completely truthful In addition, the thesis also uses a number of comments, assessments as well as results from other authors, agencies and organizations, all with source annotations clearly stated in the references

I will take full responsibility if tlrere was any fraud in the contents of my research

Hanoi May 2021

Do Due Huy

Al Artificial Intelligence

2.2.2 Classification of birth defects

2.23 Cause of birth defects in human

2.23 Screening methods for some common birth defects

2.3.1 Al application in health care

2.3.2 Definition -

15162.3.3 Machine learning • •••••••••••••• M •••• M ••••••••••«••••••••••••••••• M •••• M M •••• M •••••• M 172.33 Evaluate the effectiveness of artificial intelligence software 19

3.1 Protocol and registration - 213.2 Studs subjects -

3.2.1 Inclusion criteria.—

21213.2.2 Exclusion critei 13 M WW «W.W.WW.W.W.W M M.W W.H.WW W.W.< 213.3 Information sources

3.4 Search

22

3.5 Selection of sources of evidence • •••••••••••••••••• 9 999 99 9 99• M •••••• •••••••••• ••••••••••• 233.6 Data charting 233.7 Data Items - - -233.8 Synthesis of results 99 99 9 99 9 99 9 99 99 9 99 9 99 9 99 9 99 99 9 99 9 99 9 99 99 9 99 9 99 9 99 9 99 99 9 99 9 99 9 99 9 99 99 9 99 9 99 9 99 99 24

LIST OF TABLES

Table 2.1 The risk of Down, Edward and Patau Syndrome according to maternal age. • •••••••••••••••a •• • ••••••••■••■■• • •■•••• • • ■

Table 2.2 Diagnosis of abnormalities using AFP uE3 and HCG 13

Table 2.3 Confusion matrix 20

Table 4.1: General characteristics of eligible studies 26

Table 4.2 Methodological characteristics of eligible studies 27

Table 4.3: Methodological characteristics of eligible studies 30

Table 5.4 Limitation in eligible studies 39

Figure 2.1 Maternal age-related risk for trisomy 21 at 12 weeks gestation and

maternal serum b-hCG levels (left) and PAPP-A (right f 12

Figure 2.2 Example of an supervised learning system 19

Figure 4.1: Literature search and study identification sưategy 25

Figure 5 J An example of support vector machine 34

Figure Ỉ.2 An illustration of neural network 35

&AỊK <€

Result: There were 11 eligible studies All Al models built in these studies archieved encouraging results However there are still key evidence gaps that need to be addressed before Al can be rendered more transferable to large- scale screening evaluations.

Conclusion: We found that the published evidence on Al application for birth defects detection was concentrated around model (algorithmic) development, generally independently of real-world clinical or screening evaluation, and overall the evidence does not indicate readiness of Al systems for real-world birth delects screening trials

Keywords: Artificial Intelligence; Birth Defects; Screening

There are about 303.000 newborns who died within 4 weeks of birth every year, worldwidẹ due to congenital abnonialies1 In the US for every 33 babies bom there is I with a birth defect2 Birth defects can have lasting effects, with devastating consequences not only for the child, but also for the familỵ the health system, and society as a whole*' Early screening methods for intervention and treatment can be implemented to limit the complications

of birth defects in order to improve quality of life for children and families as well as reducing infant mortality due to birth defects5 Therefore, we need to have effective methods to screen, diagnose and predict birth defects so that

we can have early interventions

In recent years, artificial intelligence (Al) has become an important part

of our daily lifẹ Some applications of artificial intelligence in everyday life include Google Translate" Google Map3 Youtube video proposal softwarệ In healthcare, artificial intelligence lias many important applications such

as screening for cancer or building predictive models in disease prevention Application of artificial intelligence to build clinical decision support system

is of interested to many scientists around lire globe5 The advantages of Al includes promoting evidence-based diagnostics, improving diagnostic efficiency, individualizing treatment as well as bringing high economic efficiency*.10

With these advantages, the application of artificial intelligence ill prenatal screening can be an effective tool to help central hospitals to make more accurate diagnosis of prenatal birth defects as well as replacing doctors

in lower level hospitals where there are no trained specialists Therefore, it is

necessaiy 10 assess the ability of artificial intelligence systems to screen for birth defects based on existing literatures and identify- gaps in these studies However, there are not many studies mentioned this issue Thus, we conducted this study with 2 objectives:

Objective 1: To describe characteristics of current studies in the 2010 -

2020 period on the application of artificial intelligence in screening of birth defects in pregnant women

Objective 2: To assess Al’s readiness in large scale screening of birth defects

LITERATURE REVIEW

2.1 Scoping review

Since The 1970s the term systematic review has begun to appear in researches as a way of accessing, analyzing and interpreting the results or implications of multiple studies at the same time-1 However in many cases, systematic review is not able to provide necessary' informations to readers Tlien scoping review with a different approach Iras become a more relevant direction11 For example, researchers may choose a scoping review when they need to find out about knowledge gaps in a particular field, something that systematic review cannot provide

The term “scoping review" is an ideal means of determining the coverage of a document on a particular issue and giving clear indication of the number of studies available as well as generalizing the concentration of studies to that problem :Although similar to systematic review that scoping review follow a pre-built process, they are done for different purposes'5 It can be used to synthesize concepts about a particular area of study, along with clarifying the definitions or conceptual boundaries of a topic16 Along with that, the scoping overview can be file foundation for a systematic review study, especially in file case when we need to learn about a new topic but there are still a lot of unanswered questions' We can distinguish between scoping reviews and systematic reviews based on research questions If the authors have a question regarding the feasibility, appropriateness, meaningfulness or effectiveness of a certain problem, then systematic review is likely the most valid approach13 However, if they don't ask such precise question, and want to explore the certain characteristics/

on their purposes but they all agree on the following points:

- All are abnormalities that have a prenatal cause

- These abnormalities may manifest at the bodily, cellular or molecular level

• These abnormalities manifest at birth or in later stages

Thus, birth defects are all abnormalities at the bodily, cellular or molecular lex el which can manifest at birth or at a later stages but have a prenatal cause.19

2.22 Classification of birth defects

There are many ways to classify birth defects, but we introduce a classification system based on 1CD - 10:

- Q0O-QO7 Congenital malformations of the nervous system

- Q10 QI 8 Congenital malformations of eye ear face, and neck

- Q20-Q28 Congenital malformations of the circulatory system

• Q30-Q34 Congenital malformations of the respiratory system

• Q35-Q37 Cleft lip and cleft palate

• Q38-Q45 Other congenital malformations ofthe digestive system

- Ọ50-Ọ56 Congenital malformations of genital organs

- QÓO Q64 Congenital malformations of the urinary system

- Ọ65-Ọ79 Congenital malformations and deformations of the musculoskeletal system

• Q80-Q89 Other congenital malformations

- Ọ90-Ọ99 Chromosomal abnormalities not elsewhere classified

2.23 Cause of birth defects In human

Causes of birth defects are divided into 3 groups by many authors, including: (1) caused by genetic factors (2) caused by envữonmental factors (3) caused by multiple genetic factors In addition, there are many birth defects with unknown causes

a Birth defects caused by genetic factors

Birth defects caused by genetic factors are divided into two groups

which are birth defects caused by chromosome disorders and birth defects caused by single gene mutations

- Birth defects caused by chromosome disorders:

Chromosomal disorders are changes in chromosome number, structure,

or mosaic, resulting in tire addition or loss of genetic material In this group, aneuploidy of chromosome 21 (trisomy 21X also known as Down's syndrome, was the most common In addition, there are some other common birth defects such as Patau syndrome Edwards Turner Klinefelter

- Birth defects caused by single gen mutations:

There are many single gene mutations that cause thegenetic birth defects and its expression obeys the genetic laws of Menden Single-geire diseases

have 3 types of genetic mechanisms, which are autosomal dominant, recessive and sex-linked There are more than 6.000 types of single-gene mutations that have been described'5, of which brittle X chromosome syndrome is tire most common genetic cause of mental retretness In addition, there are also defects such as skeletal dysplasia, cartilage dysplasia, cartilage hypoplasia, microcephaly, color blindness, hemophilia A

b Birth defects caused by environmental factors

- Maternal age

The risk of having a chromosomal abnormality increases with maternal age mainly due to events in the fecal process, resulting in the fetus having a trisomy*'1:

- Poverty:

According to World Health Organization (WHO), weak socioeconomic status is associated with an increased in the proportion of birth defects Pregnant women in these countries are more likely to suffer from malnutrition before and during pregnancy, and are at high risk of environmental exposures which are harmful to the fetus such as tobacco, alcohol, etc In addition, there are still may limitations in reproductive health care sen-ices, family planning

or prevention of congenital syphi lis sy ndrome, congenital rubella in the health care system which leads to high proportion of birth defects*”

- Nutrition deficiencies:

A nutrition deficiency diet during pregnancy can affect the risk of haring

a child with birth defects Lack of Phosphoius Magnesium and otlier trace elements can lead to a deformation of the skeleton, causing congenital rickets2-'

An iodine deficient diet during pregnancy- can also give birth to a baby uiwth birth defects UNICEF believes that iodine deficiency causes brain dannge and intellectual disability20 However this is also the leading cause of mental retardation which can easily be prevented2025 Iodine Deficiency Disorder causes spontaneous abortion, perinatal death mental retardation, hearing impairment etc Severe iodine deficiency disorder can lead to cretinism

Folic acid is a vitamine (vitamin B9) required for biosynthesis and methylation of DNA and RNA Il is very- important for cell division especially at the time of rapid cell division such as in an etnbiyo Folic acid is essential for the development of tire brain and spinal cord during the first 4

weeks of pregnancy24 Repons indicate that 95% of babies with neural tube defects occur in mothers with no family history of the disease There are extensive scientific evidences linking birth defects with folate deficiency and the use of folic acid before conception with prevention of neural tube defects24

- Physical and chemical agents:

Chemical agents such as pesticides, plant protectors, heavy metals such

as mercury, lead can cause bitth defects such as eye defects, limb deformities, facial and mouth defects Dioxin can cause birth defects at 2 times higher rate than other agents*5

Physical agents such as radioactive substances can influence embryogenesis while radiation, gamma rays, and ultraviolet rays can also disrupt polymorphic process of muscle and other organs of tire embryo

- Microbiological agents:

Mother infected with viruses during pregnancy such as cytomegalovirus, herpes-zoster virus, chickenpox, flu especially rubella can give birth with birth defects such as defects of the nervous system, cardiovascular system, calcification in the brain microcephaly, mental retardation

Some bacteria such as toxoplasma, chlaminvdia trachomatis, syphilis can also cause birth defects such as fetal death, cleft lip calcification in the brain, hydrocephalus, encephalitis - meningitis, retinitis if the mother has been previously infected without treatment or infected during pregnancy*

- Drinking alcohol during pregnancy:

Fetal Alcohol Syndrome (FAS) is a syndrome of birth defects in children whose mothers drink alcohol during pregnancy This syndrome includes growth retardation, heart defects, physical, mental and behavioral disorders that can include low IQ or mental retardation Fetal alcohol syndrome is not a simple birth defect Il is a group or pattern of related disorders The severity

of symptoms varies, with some children having worse symptoms than others Alcohol can affect the fetal brain at any time during pregnancy Hence there is

no safe alcohol dosage, no safe drinking time or no right kind of wine to drink during pregnancy2'

- Some other factors:

Some other factors such as obesity mother, insulin-dependent diabetes, usage of stimulants such as cocaine, smoking, sedatives (Thalidomide ), antiepileptic drugs are also risk factors that increases die rate of childbirth with birth defects

2.25 Screening methods for some common birth defects

a Ultrasound

Ultrasound is a non-invasive procedure that does not harm both the mother and the fetus, which allows clinicians gather some information about the pregnancy that cannot be provided by any5 examination such as: gestational age, number of fetuses, fetal development, mother-to-child metabolism quality (based on Doppler) and fetal morphology Although there have been many technical improvements but ultrasound is still not tire perfect method, it can only detect some fetal malformations when the fetus is in a favorable position with the right amount of amniotic fluid Unclear

motphological abnormalities are also difficult to detect on ultrasound For example, in Down Syndrome, ultrasound can only detect indirect images such

as nuchal translucency

Ultrasound for the measurement of nuchal translucency is usually done

at 11-13 weeks of pregnancy which will give the most accurate results The majority of cases with nuchal translucency < 3 mm were classified as low-risk (less likely to develop chromosomal abnormalities) In the case when nuchal translucency is ranged from 3.5 to 4.4 mm there is a chromosomal abnormality rale of 21.1% and in the case which It is > 6.5 mm the risk of chromosomal abnormality can be increased up to 64.5% In cases where nuchal translucency is > 3 mm the pregnant woman will be ordered to perform an additional triple test at 16-18 weeks

b Doubk* test Triple test

The first Down syndrome screening method was introduced in the 19"0s based on maternal age women over 40 years old will be given an amniocentesis test to determine the risk of fetus with chromosomal abnormalities Later, when amniocentesis becomes safer than before with the guidance of ultrasound, the cost is also reduced, amniocentesis is widely indicated in high-risk pregnant women, ie older than or equal to 35 years old.Test of biochemical indices in maternal blood

- Maternal serum alplia-fetoprotein (AFP)

A developing fetus has 2 maứi types of blood protein Albumin and alpha fetoprotein (AFP) while an adult has only albumin, so an AFP test in the maternal serum is used to indirectly determine the amount of AFP in the fetal blood

Normally only a small amount of AFP in the amniotic fluid can cross the placenta to enter the mother's bloodsfream However, when there is a neural tube abnormality, because pail of the embryonic neural tube is not closed, AFP will escape into the amniotic fluid Neural tube abnormalities include anencephaly (due to the neural tube that does not close the head) and spina bifida (due to the inability of the tail of the neural tube) In the US the rate of these diseases is 1-2/1000 births Likewise, in gastroschisis or omphalocele AFP from the fetus enters mother's bloodsưeam in a larger amount than usual.AFP tends to be lower than normal in fetuses with Down syndrome or some chromosomal abnormalities, so AFP is usefiil in screening for Down syndrome and a number of other infections A combination of AFP screening and ultrasound can detect almost all anencephaly and most cases of spina bifida.

• Maternal serum free Beta-HCG

This is the most commonly used test during pregnanes’ About 1 week after the embryo implants in the uterus, the amount of beta HCG secreted by the culturing cells is sufficient to diagnose pregnancy In the early stages of pregnancy, beta HCG helps in early diagnosis and prognosis of miscarriage, ectopic piegnancy because in these cases, beta HCG is lower than normal.Later in pregnancy, at the end of the second trimester, HCG may be used

in combination with AFP to screen for specific chromosomal abnormalities in Down syndrome Increased HCG in association with decreased AFP IS an implication of Down syndrome Meanwhile, abnormally high hCG suggests pseudocyesis

Figure 2.1 Maternal age-related risk for trisonn 21 al 12 weeks gestation and

maternal serum b-hCG levels (left/ and PAPP-A (KightỈ

• Maternal serum Estriol

Estriol is derived from dehydroepiandrosterone (DHEA) which is produced from the adrenal glands and tlren converted to estriol by the placenta Esttiol enters the mother s bloodstream and is excreted in the urinary’ tract or excreted by the liver into the bile Continuous testing of estriol in the third trimester is performed to monitor fetal health staius If the concenttaiion

of estriol is reduced, the fetus is at risk and may indicate an end to pregnancy Estriol is also reduced in fetuses with Down syndrome or adrenal insufficiency or anencephaly

- Pregnancy-associated plasma protein A (PAPP-A)

In the first trimester, low serum PaPP-A is an indication of trisomies 13,

18 and 21 Furthermore, low PAPP-A levels in the first trimester predict a low

binh weight pregnancy or stillbirth A higher than ttormal PAPP-A suggests a larger than normal fetus.

Combination of serological tests can potentially increase rhe sensitivity and specificity of detecting fetal abnormalities The classic 3 screening tests includes alpha-fetoprotein (MSAFP) beta-HCG and estriol (uE3) Some facilities use fourth tests, which is inhibin-A

Table 2.2 Diagnosis of abnormalities using AFP uEJ aiưỉHCG

(The values of these indicators depend on gestational age)

c Amniocentesis

Amniocentesis is the most widely used method today because of its technical simplicity as well as low rate of complications It is considered the mam method of obtaining fetal specimens

Amniocentesis is done at 3 periods: Early amniocentesis (13 to 16 weeks gestation), classic amniocentesis (from 17 to 20 weeks gestation), late amniocentesis (after 20 weeks )

The best gestational age for this procedure is 17 to 18 weeks because at this time the chance to successfully draw out amniotic fluid is highest while the rate of complications for both mother and fetus is lowest The procedure is performed under ultrasound guidance

Amniocentesis takes about 20 nil of amniotic fluid for testing The whole procedure takes 5 to 10 minutes Then maternal need to stay in place for 3 hours, she doesn't have to use antibiotics Risk of amniotic fluid leakage, miscarriage is < 0.5% Test results will be available in 2 to 3 weeks

- Chorionic Villus Sampling

Chorionic villus sampling (CVS), or chorionic villus biopsy, is a prenatal test that involves taking a sample of tissue from the placenta to rest for chromosomal abnormalities and certain other genetic problems This method causes high rate of miscarriage (about 9%), so it is only used mainly in cases

of fetus with severe abnormalities detected in the fust trimester Tins method

is performed under ultrasound guidance Results will be available after 5 to 7 days

- Non-invasive prenatal screening (NIPT)

This is considered to be the most effective and safest testing method available today The method is perform'd early from the 10th week of pregnancy through the mother’s blood sample (only 7-10 ml) Chromosome abnormalities can be screened include chromosome 6 9 13 (Palau’s syndrome), chromosome 18 (Edwards), chromosome 21 (Down), chromosome X Y and segmental mutations, etc In addition, this method is also applicable for single pregnancy, twins, surrogacy with high accuracy, up

to 99.98%

Prenatal screening not only helps detect birth defects for the fetus, but it also enhances and improves the quality of future generations Therefore, prenatal screening and diagnosis is an essential job to help mothers detect diseases, have healthy babies which develop normally

AĨ the present, modern molecular biology techniques such as NGS microanav BoBs can screen and identify many genetic mutations Especially the NGS technique can decodes the entire human genome to identify genetic abnormalities related to birth defects This technology help US detect 4500 different genetic diseases Therefore, it is necessary to have machine learning and deep learning technology in order to promote the effectiveness of these systems.

2.3 Artificial Intelligence (Al)

2.3.1 Al application in health care

In clinical setting Al is often used to build clinical decision support system Clinical decision support systems haw the responsibility of assisting physicians or healthcare professionals in making clinical decisions These systems can improve the quality of healthcare by providing references to doctors based on data from the past

Clinical decision support systems haw been developed since the 1970s such as the MYCIN, INTERNIST-1 andCASNET Decision support systems have been developed and applied in many fields of healthcare such as diagnosing diseases, developing treatment regimens, making drugs, monitoring and taking care of patients, These systems have been applied in many facilities around the world Al algorithms in healthcare have been developed by many companies, including large companies such as IBM, Microsoft Google Intel Facebook and even startups Ill recent years, the development and application of clinical decision support systems have been increasingly sưengthened There are mam- reasons for this development, that

is the development of hardware leading to increased computing power

Artificial Intelligence (Al), also known as Al is the intelligence expressed by machines, different from the natural intelligence expressed by humans or animals, which are related to consciousness and emotions.

In other words, artificial intelligence is a branch of computer science whose purpose is to give software the ability to analyze information, then make decisions based on results

The artificial intelligence concept is built based on 2 different ideas The first idea is aritificial narrow intelligence (also known as ANT) These are Al softwares that can do a specific job like voice recognition or self­driving cars or sorting spam messages Tire second idea is about artificial general intelligence (artificial general intelligence), also known as AGI This

is the purpose of building artificial intelligence, which is to create software that can do eventhing humans can or even more Today, almost all new Al inventions belong to ANT

2.3.3 Machine learning

Machine learning is the most important part of Al it gives computer systems the ability to learn automatically Machine teaming can be understood as the process by which a system "learns" itself from past experiences and converts those "lessons" into its knowledges, instead of using knowledges obtained by human

Currently, two definitions of machine learning method have been proposed First definition by Arthur Samuel describes this approach as "the field of study that gives computers the ability to learn without being explicitly programmed." This is the old and unofficial definition Instead Tom Mitchell proposed a more modern definition: “A computer program is said to learn from experience E with respect to some class of tasks T and performance measure p if its performance at tasks in T as measured by p improves with E" For example, computer-based chess, where E is the experience from playing previous games T is the task of playing chess, and

p is the probability that the software will win the next time it is played

Any machine learning method can be categorized into one of two types: supervised learning or unsupervised learning

a Supervisied learning

As children, we learned to classify new things under guidance of adults They point at a furry four leg creature that bark and tell us that it is a dog Through many such instructions, we get to know how to identify a dog among other animals Tins is the core concept of supervised machine learning In this method, the software is given a data set and already know how correct output should look like, having tire idea that there is a

relationship between the input and the output The task of a supervised machine learning mechanism is to try to find the relationship between the input data and the desired output, and then use that relationship to predict the output for the new input

The supervised machine learning method is divided into two types of problems, regression and classification In a regression problem, we are trying to predict results within a continuous output, meaning that we are trying to map input variables to some continuous function, for example, forecasting prices for a specific house from input data such as area, number

of floors, etc In a classification problem, we are instead trying to predict results in a discrete output In other words, we are trying to map input variables into discrete categories For example, predicting if this person lias cancer based on a series of pictures

The advantage of the supervised machine learning method is that it can find out the correlation between input aid output data that is close to reality and has good coverage of different cases However, tire disadvantage of machine learning methods IS that large input data is required, and tile data must be pre-labeled, which can be expensive in temis of time and money In addition, in order to have a good coverage of the different cases, the input data must be diverse and need to be updated continuously, because although

it is called a cat the cats in different places are different in shape, size, color, and sometimes we have to ask ourselves if it's a cat which is the same

in this machine learning approach

Figure 2.2 Example of an supervised learning system

b Vnsupervhed learning

Vnsupervised machine learning is used when we know little or no what rhe outcome will be While in supervised machine learning, we try to build a predictive model based on labeled input data, in die unsupervised learning method, instead of available labelled data, the model collects data from the environment and labels them itself, just like children who are able to imitate the actions of adults, classifying other animals by themselves or come up with rules of a game based on observations

Tire advantage of die unsupervised machine learning approach is that it does not need labeled data, and it can provide unknown information from the input data, as well as automatically classify die data by finding different characteristics from the data itself However, this method lias disadvantages such as it takes many steps to build, and it is difficult to understand what is going on inside the software or what method it is using to learn

233 Evaluate the effectiveness of artificial intelligence software

In order to classify whether a pregnant woman has fetus with birth defects, we have to answer a yes or no question, or in other words, positive or negative There are 4 possibilities when comparing the software's prediction

with fetus’s tnie condition If the prediction says that this case is positive and

in fact tills person is positive, this is called a true positive, but if in fact this person is negative, it is called a false positive Conversely, true negative occurs when both the prediction and fetus’s true condition are negative, and false negative occurs when the prediction is negative when in fact It is positive We can draw this table from the explanations above:

Table 2.3 Confusion matrix

Fetus’s true condition

The sensitivity (sometimes also named the detection rate in a clinical setting) of the software is the proportion of fetuses which test positive for birth defects among those which truly have tile condition Mathematically, this can be expressed as:

Sensitivity' = I True positive/ z Condition positive

Specificity of the software is tlie proportion of fetuses which test negative for birth defects among those which truly do not have the condition Mathematically, this can also be written as:

Specificity « z True negative/ z Condition negative

Finally, accuracy’ is the combination of true positive and true negative cases among the total population Mathematically, this can also be written as:Accuracy' = (I True positive + I True negative)/1 Total population2'

.MATERIALS AND METHODS

3.1 Protocol and registration

This study follows the PRISMA extension for scoping reviews was published in 2018 of Tricco The checklist contains 20 essential reporting items and 2 optional items to include when completing a scoping review2* The detail checklist is showed in Appendix

3.2 Study subjects

3.2.1 Inclusion criteria

- Articles published in English, in 2010-2020 period

- Studies must show evidence of using machine learning methods applied to screening of birth defects

- The purpose of those studies is to evaluate approaches toward application ofartificial intelligence in the screening of birth defects

- Studies must report clinical results of Al software in screening of birth defects through AƯC or accuracy or sensitivity or specificity

- Studies conducted using any types of design on any group of pregnant women

3.22 Exclusion criteria

- Studies aimed to identify’ markers but not the defects and their golden standards

• Studies that have animal subject

- Commentary articles, editorial articles, review articles and congress abstracts