Christina S Han, MD

Dr Han is an Associate at the Center for Fetal Medicine and Women’s Ultrasound, Los Angeles, Califoria and a Clinical Faculty in the Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, University of California, Los Angeles.

home

authors

christina-s-han-md

Ever wonder how self-driving cars recognize a ball in the road? How about when Amazon magically knows what items you need before you do? This is all thanks to pattern recognition of artificial intelligence (AI). Analytical AI refers to the general process by which machines or computers replicate and replace human tasks and cognition. Machine learning is a branch of AI in which algorithms, inspired by the human brain, encourage the computer to continue recognizing patterns automatically (Figure 1). A further subset is deep learning in which massive amounts of neuronal networks interpret and use large amounts of data for deeper “cognitive” capabilities. It has also been called a 

 (CNN) in part due to its resemblance to the neurons and connections in our cerebral cortexes. Deep learning has led to breakthroughs in healthcare, specifically in radiologic image recognition.


	One of the most common uses of AI in healthcare is computer-aided diagnosis (CAD) which has already been widely studied in many fields including prostate, breast and cardiac imaging.

 Many AI applications are used to develop and implement protocols, thereby shortening imaging time, optimizing staffing, and reducing costs.

They also have become instrumental in helping physicians make decisions about patient care.

 Ob/gyn, while late to the game, given the ubiquitous involvement of ultrasound in care of nearly every reproductive-aged woman in the modern world, has the potential to climb the ranks as the specialty most instrumental to use and development of AI. 

“I can’t believe you have to calculate all those measurements yourselves. Doesn’t the machine recognize the baby’s head?” 

-asks an inquisitive patient. A Tesla automobile costs roughly the same as a Voluson E10, yet the former can recognize multiple and simultaneous moving objects in the road but the latter has yet to reliably figure out how to recognize fetal organs, which are more or less identical in 97% of fetuses. While the initial task of learning to perform fetal ultrasound requires dexterity and rote hand skills, it seems plausible that a semi-trained sonographer can learn to place the probe in the correct location and computer aid can help identify the correct plane, prompt organ identification, and calculate many of the measurements automatically. 

In many new machines, automatic image recognition is already being used during biometric measurement of the fetal biparietal diameter (BPD), head circumference (HC), femur length (FL) and abdominal circumference (AC). In these instances, the sonographer is responsible for identifying the proper landmarks in the plane of choice, and once prompted, the machine will label and measure the desired biometric value. If correct, this saves time. On the contrary, if the image quality is poor, due to fetal position or maternal obesity for example, it may erroneously over or under measure the organ. One 

 compared 100 manual biometric measurements to 100 automated measurements and showed a time-saving of about 20 seconds and seven steps on each 20-minute anatomic survey.

 While the time-saving in each individual patient encounter may be insignificant, at the end of a busy day, every second counts towards improving sonographer efficiency and decreasing fatigue. 

Can AI improve accuracy and efficiency of mammography?

Three- and four-dimensional (3D/4D) ultrasound have further revolutionized the ability to acquire and process images, especially in the arena of CAD and image recognition. Many major ultrasound manufacturers have developed their own software, such as 

 (Virtual Organ Computer-aided Analysis) from GE or 

 for breast imaging from Samsung. Image recognition has boomed in fetal ultrasonography with groups studying virtually every plane and fetal organ. 

One of the earliest interests was 3D computer-aided analysis of the fetal heart. One study showed that satisfactory views of the four-chamber heart, outflow tracts, and stomach were only obtained in 43% to 65% of cases, and less in settings of obesity or fetal spine up.

 More recently, spatiotemporal image correlation (STIC) volume data sets have been used to identity nine standard fetal echocardiographic views with up to 98% sensitivity for screening congenital heart disease.

 Some other examples include the fetal thymus, for which CAD has assisted with border identification and accurate volume measurement of this complex pyramidal structure in 77% of cases.

 CAD has even been studied for identification of key characteristics of placenta accreta spectrum

 and cervical length, funneling, and sludge to predict preterm labor in patients with short cervix.

 Gestational age is no longer a limiting factor as these techniques have expanded to the first trimester in 

 to analyze the motion of multiple points on the fetal heart to provide information on its size, shape, and function. Calculation of this complex algorithm requires a simple 2D video clip of the beating four-chamber view and 3 minutes of post-production analysis, with the results potentially yielding a volume of information on fetal cardiac function.

 (Figure 2) developed by GE Healthcare and 

 Both use deep learning application to take one 3D sweep of the fetal brain and automatically recognize and measure the essential structures through the posterior fossa, ventricles, BPD, and HC. As it stands now, however, most providers use image recognition as a second pass or confirmation to increase their diagnostic accuracy and are not looking for replacement of their clinical acumen and years of training.

Data and a lot of it is the fundamental requirement for creating a successful deep learning application. One of the practical limitations of software developers is ethically and efficiently obtaining de-identified patient data to create such a thing. One of the biggest players on the AI block is the UK-based company Intelligent Ultrasound, which acquired over 

 from real obstetric scans to develop algorithms for the software 

. The goals of ScanNav are to provide real-time guidance to sonographers by automatically capturing the six correct images as recommended by the UK fetal anomaly-screening program and provide an audit showing that all the images were obtained. In a sense, this provides a layer of quality improvement to ensure that optimal patient care is being delivered. 

The software is still in development and some limitations include real-time guidance for probe placement, especially with unique patient considerations such as obesity. A crucial aspect to consider in these situations is patient privacy. While individual data may be de-identified, further advances in machine learning may be able to identify individuals if appropriate safety measures aren’t taken with data security.

At the end of 2018, SonoScape medical (Shenzhen, China) announced development of their 

 algorithm, designed for the S60 ultrasound system, which will scan the entire fetus with a single cine loop. Thousands of real images were used to develop algorithms to identify appropriate landmarks and accurate measurements. In addition, in true deep learning fashion, the system continues to fine-tune its analysis with each additional exam it performs. The S-fetus software will select the best images and automatically measure key growth components. This software will consolidate the multistep process of obtaining fetal biometry to a single push of a button. In addition to saving an immense amount of time and keystrokes for each patient, it will alert the sonographer if manual adjustments or measurements do not meet image standards, thus providing the sonographer feedback and resulting in better images. 

Fetal ultrasonography is a mainstay of routine prenatal care. Significant advancements have been made over the years to improve image quality and diagnostic accuracy while maintaining the ease, reproducibility, and efficiency for sonographers performing and physicians interpreting the images. One of AI’s greatest benefits is removing its dependency on the operator and standardizing our approach to improve patient safety, especially in low-resources settings where expertise may otherwise be lacking. Keep your eyes and ears open as the data and hype about this technology are only going to skyrocket in our field. The preliminary schedule for 

 in Berlin in October of this year includes courses on how large data and AI may impact our field, and the sessions are sure to be well attended. AI and deep learning certainly warrants all the buzz and energy surrounding it, but realistically, is not yet sophisticated enough to replace obstetricians, maternal-fetal medicine specialists or radiologists. Rest assured, we don’t have to worry about our job security quite yet. 

The authors report no potential conflicts of interest with regard to this article.

Schmidhuber J. Deep learning in neural networks: an overview. 

Loch T, Leuschner I, Genberg C, Weichert-Jacobsen K, Kuppers F, Yfantis E, et al. Artificial neural network analysis (ANNA) of prostatic transrectal ultrasound. 

Moon WK, Chen IL, Chang JM, Shin SU, Lo CM, Chang RF. The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound. 

Pereira F, Bueno A, Rodriguez A, et al. Automated detection of coarctation of aorta in neonates from two-dimensional echocardiograms. 

Pesapane F, Volonte C, Codari M, Sardanelli F. Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United States. 

Kahn CE, Jr. Artificial intelligence in radiology: decision support systems. 

Espinoza J, Good S, Russell E, Lee W. Does the use of automated fetal biometry improve clinical work flow efficiency? 

Cohen L, Mangers K, Grobman WA, et al. Three-dimensional fast acquisition with sonographically based volume computer-aided analysis for imaging of the fetal heart at 18 to 22 weeks’ gestation. 

Yeo L, Luewan S, Romero R. Fetal intelligent navigation echocardiography (fine) detects 98% of congenital heart disease. 

Re C, Bertucci E, Weissmann-Brenner A, Achiron R, Mazza V, Gindes L. Fetal thymus volume estimation by virtual organ computer-aided analysis in normal pregnancies. 

Qi H, Collins S, Noble JA. Automatic lacunae localization in placental ultrasound images via layer aggregation. 

Bahado-Singh RO, Sonek J, McKenna D, et al. Artificial Intelligence and amniotic fluid multiomics analysis: The prediction of perinatal outcome in asymptomatic short cervix. 

DeVore GR, Polanco B, Satou G, Sklansky M. Two-dimensional speckle tracking of the fetal heart: a practical step-by-step approach for the fetal sonologist. 

Rizzo G, Capponi A, Persico N, et al. 5D CNS+ Software for automatically imaging axial, sagittal, and coronal planes of normal and abnormal second-trimester fetal brains. 

Na L, Yang C, Lo CC, Zhao F, Fukuoka Y, Aswani A. Feasibility of reidentifying individuals in large national physical activity data sets from which protected health information has been removed with use of machine learning. 

Articles

Ob/gyn, while late to the game, has the potential to climb the ranks as the specialty most instrumental to the use and development of AI.

Artificial intelligence in ob/gyn ultrasound

Obesity has become an overwhelming epidemic in the United States and contributes an estimated $147 to nearly $210 billion per year in healthcare costs. It is estimated that over 60% of the US female population is considered overweight, with 45% of US women between ages 15 and 49 considered obese.

This prevalent disorder increases both risk of infertility and complications during pregnancy, and has become a major clinical risk factor for adverse outcomes for both mother and fetus.

 Women with obesity experience increased risks of maternal complications of gestational diabetes, preeclampsia, cesarean delivery, thromboembolism, and postpartum hemorrhage, and fetal complications, such as prematurity, congenital anomalies, macrosomia, birth complications, and stillbirth.

Maternal obesity is also associated with increased risk of fetal structural anomalies, especially cardiac defects, neural tube defects, sacral agenesis, anal atresia, and limb reduction abnormalites.

 Prevalence of cardiac defects in women with body mass index (BMI) > 40 kg/m

 is increased (RR 3.63; 95% CI 1.33- 9.91).


	In addition to the risk of structural anomalies, technical challenges associated with sonographic imaging result in a significantly lower detection rate for cardiac anomalies, as well as an increased risk of missing markers of aneuploidy.

 The percentage of overweight women who have suboptimal fetal echocardiography is 17.4% when compared to 6.4% in normal-weight patients.

Many factors contribute to suboptimal imaging in women with higher BMI. Sonographic visualization of fetal structures is degraded by depth of the body fat layer, with resultant increased depth of insonation, absorption of energy by the adipose tissue, and higher back-scatter from refraction.

 Over 50% of fetal anatomic surveys in women with obesity cannot be completed during the first ultrasound examination.

 Studies of second-
	trimester ultrasound examinations have shown that as BMI increases, there is a steady degradation in scan quality, and rates of poor visualization of fetal heart and spine correlate linearly with the degree of obesity.

 One study found that if a repeat ultrasound is performed at 21 weeks, then visualization of the heart improved; however, in 20% of exams, the fetal heart could not be adequately assessed despite several ultrasounds.


	Images obtained while scanning a patient with obesity are often of poor resolution secondary to backscatter, artifacts, and noise.

 There are several techniques that can result in better sonographic imaging of these patients. The primary goal is to reduce the distance between the transducer and the fetus, and to leverage advanced ultrasound technologies for post-processing.  


	The panniculus limits visualization due to absorption of ultrasound energy by the adipose tissue, as well as increasing depth of insonation. Because the basic tenet of good ultrasound technique is placement of the organ of interest as close as possible to the transducer, scanning at a point away from the thickest portion of the pannus (between the umbilicus and pubic symphysis) may improve image quality.

 Placing patients in alternate positions, such as lateral decubitus, oblique, semi-recumbent or upright may allow the sonographer to scan away from the areas of most depth, yielding better images. The decubitus position causes the pannus to fall away, allowing the practitioner to use the lateral flank as a window, while pointing the transducer medially. The pannus can also be lifted by an assistant or by the patient herself, and scanning can be performed from the infrapanicular crease to minimize the distance to the target of the ultrasound, the fetus.

 Using multiple positions throughout the course of a single visit can result in more optimal views of fetal anatomy and maternal structures. In addition, after the first trimester, it may be necessary to move the fetus into a different position, using a free hand.

 Figures 1 and 2 show examples of the importance of appropriate positioning of the patient during ultrasound. 


	It is also helpful to have the patient maintain a full bladder, which displaces the uterus cephalad, where the adipose tissue of the anterior abdominal wall may be thinner.


	A lower-frequency transducer (e.g. 1 MHz), as opposed to the traditional 2-to 5-MHz abdominal probe, can be combined with beam-forming algorithms to allow for better modeling in overweight patients.

 Because absorption is proportional to ultrasound frequency, lower-frequency transducers allow for less absorption, less attenuation, and more penetration, at the expense of less resolution. Using tissue aberration programs that correct and adjust for the speed changes that occur in adipose tissue also allows for improved resolution and greater depth of penetration. Real-time multiplanar imaging provided by isotropic and new crystal array transducers also be helpful in patients who are obese.


	Because the vaginal probe can be placed closer to the fetal anatomy when used with a transvaginal approach, it is particularly useful in patients with excess adiposity. A transvaginal approach should be considered routine in suboptimal imaging in the first trimester and in scenarios where fetal parts close to the cervix are suboptimally visualized (i.e., intracranial anatomy in a cephalic fetus, or fetal extremities and sacral spine in a breech fetus). The vaginal probe can also be placed directly in the umbilicus, using it as an acoustic window, and has been shown to improve the fetal cardiac exam.


	Use of specialized advanced imaging technologies allows for post-image capture enhancements. Increased signal-to-noise ratios and improved margin definition are easier with post-processing techniques. Use of compound imaging and tissue harmonic imaging has also vastly improved the quality of images that can be obtained from standard ultrasound techniques.

 The principle behind compound imaging is to combine multiple slices of images that have been obtained from different angles to generate an improved composite sonographic image.

 Tissue harmonic sonography, on the other hand, is a gray-scale sonographic technique that markedly improves sonographic contrast resolution, particularly in patients who are difficult to image with conventional techniques.

Ergonomic tips to prevent injury to sonographer/physician


	Taking into account good ergonomic practices is especially important for a practitioner performing ultrasonography on patients who are obese. When performing ultrasound regularly, repetitive injury is common, due to forceful or awkward positions, applying pressure for extended periods of time, and improper positioning. Musculoskeletal injuries are common in sonographers who work in the ob/gyn setting, and it is imperative that they remain aware of hand positions and proper posture and avoid awkward twisting movements while doing scans to avoid injury.

Avoiding bias against patients who are obese


	In our society, obesity is stigmatized, and even though one-third of the adult US population is obese, patients with it are frequently the targets of negative or derogatory comments, prejudice and poor treatment in many settings, including healthcare. There is a growing amount of evidence that supports the notion that physicians and other healthcare workers hold strong implicit bias about patients with obesity,

 and those biases need to be addressed at the systematic and training levels. Because many of our patients have already experienced negative reactions from others, it is even more important to provide them with compassionate care, and to avoid any unconscious bias against patients with obesity, especially because they are more likely to have complications during pregnancy and will need to be able to trust that their physician treats them with respect and dignity. 

Obesity is a growing epidemic in the United States. Patients who are obese are at increased risk of fetal anomalies and overall, adverse outcomes are increased in both mothers who are obese and their fetuses. Pregnant patients who are obese present significant technical challenges for those performing ultrasonography. Providers should leverage a patient position, optimize probe selection, and acquire an understanding of post-processing abilities of their ultrasound machines to maximize image quality and facilitate appropriate counseling of pregnant women who are obese.

 Patients who are obese often require additional ultrasounds to complete anatomical surveys, and have a higher utilization of healthcare resources during and after their pregnancies. The economic impacts of obesity cannot be ignored and working with our patients to improve their health before, during, and after their pregnancies can improve the health of society over the long term.

Hendler I, Blackwell S, Treadwekk M, Bujold E, Sokol R, Sorokin Y. Does advanced ultrasound equipment improve the adequacy of ultrasound visualization of fetal cardiac structures in the obese gravid woman? Am J Obstet Gynecol. 2004;190:1616-1620.

Hendler I, Blackwell S, Treadwekk M, Bujold E, Sokol R, Sorokin Y. The impact of maternal obesity on midtrimester sonographic visualization of fetal cardiac and craniospinal structures. Int J Obes. 2004;28:1607-1611.

Benacerraf B. The use of obstetrical ultrasound in the obese gravida. Sem Perinatol. 2013;37:345-347.

Maxwell C, Glanc P. Imaging and obesity: a perspective during pregnancy. Am J Roentgenol. 2011;196:311-319.

Brite J, Laughon SK, Troendle J, Mills J. Maternal overweight and obesity and risk of congenital heart defects in offspring. Int J Obes. 2014 Jun;38(6):878-882.

Uhden M, Knippel AJ, Stressig R, Hammer R, Siegmann H, Froelich S, Kozlowski P. Impact of maternal obesity and maternal overweight on the detection rate of fetal heart defects and the image quality of prenatal echocardiography. Ultraschall Med. 2011 Dec; 32(S2):E108-14.

Rosenberg JC, Guzman ER, Vintzileos AM, Knuppel RA. Transumbilical placement of the vaginal probe in obese pregnant women. Obstet Gyncecol. 1995;85:132-134.

Oktar SO, Yucel C, Ozdemir H, Uluturk A, Isik S. Comparison of conventional sonography, real-time compound sonography, tissue harmonic sonography, and  tissue harmonic compound sonography of abdominal and pelvic lesions. Am J Roentg. Nov 2003;181(5):1341-1347.

Phelan SM, Burges DJ, Yeazel MW, Hellerstedt WL, Griffin JM, van Ryn M. Impact of weight bias and stigma on quality of care and outcomes for patients with obesity. Obes Rev. 2015;16:319-326.

Proper positioning, careful choice of probe, and leveraging of post-processing capabilities all can improve ultrasound quality in this patient population.

How to optimize imaging in the obese gravida

	Preconception care is primary prevention. The goal is to affirm pregnancy intention, reduce any potential harm, and recognize modifiable risk factors related to pregnancy while stratifying pregnancies on a continuum of low- to high-risk. The Centers for Disease Control and Prevention (CDC) has defined preconception care as “a set of interventions that aim to identify and modify medical, behavioral, and social risks to a woman’s health or pregnancy outcome through prevention and management.”

	A recent consensus statement from the National Preconception Health and Health Care Initiative defined 9 specific preconception wellness measures to confirm high-quality preconception care: 1) pregnancy intention; 2) access to care; 3) preconception multivitamin with folic acid; 4) tobacco avoidance; 5) absence of uncontrolled depression; 6) healthy weight; 7) absence of sexually transmitted infections (STIs); 8) optimal glycemic control in women with pregestational diabetes; and 9) teratogenic medication avoidance.

Recommended: Should women with intrahepatic cholestasis of pregnancy be delivered early?

	By the time most women realize they are pregnant, organogenesis has begun and many prevention strategies (such as folic acid to prevent neural-tube defects (NTDs) or glycemic control to prevent diabetic embryopathy) are suboptimal in effect even if promptly initiated.

 Women who were given preconception counseling demonstrated a 50% greater likelihood of their subsequent pregnancies being intended.

Several organizations have focused on optimizing health before conception, which resulted in development of clinical recommendations and educational materials for providers and patients (Table 1).

	The first step in preconception care is reproductive counseling, including counseling about contraceptive options because nearly half of all pregnancies in the United States are unplanned.

 Following confirmation of pregnancy intention, a thorough history is indicated. Several questionnaires and forms are available for this purpose (Table 2).

	The United States Surgeon General’s Family History Initiative was launched to educate healthcare providers and patients about the value of using family history as a screening tool for inherited medical conditions and single-gene disorders.

 A family history is indicated for both partners

 and positive responses are followed up by risk assessment, testing, and genetic counseling. Completing genetic counseling and testing before conception is beneficial.

Precise identification of maternal genetic conditions is important when reviewing maternal risks and offspring morbidities associated with pregnancy, counseling about mode of inheritance, partner carrier screening, and risk of genetic condition in the offspring, and determining which prenatal diagnostic or preimplantation genetic screening or testing to recommend (Table 3).

	Immunization outside of pregnancy is generally preferable and live-virus vaccines are contraindicated in pregnancy because of their theoretical risk to the fetus.

	Two vaccinations, however, are of particular importance antepartum: influenza and pertussis. Influenza can cause significant morbidity and mortality in pregnancy and all clinicians who care for women of reproductive age should encourage them to be vaccinated for influenza every year.

 Women planning pregnancy should also receive tetanus toxoid, reduced diphtheria toxoid, and acellular pertussis (Tdap) vaccines during each pregnancy, between 27 and 36 weeks’ gestation.

	Increased understanding of the link between Zika virus and fetal neurological effects adds another discussion to preconception counseling. Because the rate of vertical transmission is unknown, the CDC recommends that women who have been diagnosed with Zika and those who may have been exposed wait at least 8 weeks after their exposure or onset of symptoms before attempting conception. The CDC website should be reviewed for the most up-to-date recommendations because they change regularly. Male partners should wait at least 6 months after their symptoms resolve to have unprotected intercourse.

 Women who reside in endemic areas should discuss reproductive life planning with a physician knowledgeable about Zika. The current recommendation is that they delay pregnancy.

	Physicians should ascertain chronic medical conditions as a part of preconception care. Some common medical conditions that have an effect on or are affected by pregnancy are briefly discussed below. All preexisting chronic medical conditions should be optimized preconceptionally with a multidisciplinary team.

 Seizure disorders are the most common neurologic diseases in pregnancy. One-third of women with a seizure disorder will experience more frequent seizures while pregnant. Seizure disorders increase the risk of congenital anomalies, whether or not the woman is taking antiepileptic drugs (AEDs).

 Women should be managed on the most effective AED, ideally monotherapy at the lowest effective dose, with the exception of valproate, which should be avoided. Given the increased rate of NTDs associated with AEDs, supplementation with 4 mg of folic acid (versus 0.4 mg) should be initiated before conception.

More: The role of IVF with PGS in recurrent miscarriage

 Chronic hypertension (cHTN) affects 3% to 5% of women of reproductive age.

 cHTN in pregnancy is associated with higher rates of preterm birth, placental abruption, intrauterine growth restriction, preeclampsia, and fetal demise. Women with cHTN are at risk of worsening hypertension and end organ damage, and 20%–25% develop superimposed preeclampsia.

 Treating severe-range blood pressures improves pregnancy outcomes.

 Angiotensin-converting enzyme (ACE) inhibitors and angiotensin receptor blockers (ARBs) are considered Category C in the first trimester and Category D in the second and third trimesters, and should be discontinued before conception. Labetalol, nifedipine, and methyldopa are the optimal agents to use during pregnancy; however, other agents can also be used with caution and in coordination with a maternal-fetal medicine (MFM) specialist.

 Women with long-standing hypertension should be assessed for retinopathy, renal disease, and ventricular hypertrophy.

 As more women with congenital cardiac disease, both corrected and uncorrected, reach reproductive age, preconception counseling for them becomes increasingly important. Pregnancy and its associated changes in cardiovascular physiology can pose significant risks. These women require a multidisciplinary approach with cardiology and MFM. The New York Heart Association Functional Classifications and World Health Organization Classification of Maternal Risk should be used.

NEXT: Pulmonary and gastrointestinal concerns

 Asthma complicates approximately 4%–8% of pregnancies.

 Women with poorly controlled asthma before pregnancy are more likely to experience worsening symptoms during pregnancy. The goal of treatment in pregnancy is to maintain adequate oxygenation of the fetus by preventing hypoxic episodes in the mother.

 Preconception care should focus on medically optimizing asthma control and identifying and reducing exposure to allergens.

	Asthma self-management skills- including self-monitoring with peak flow monitors, correct use of inhalers, and prompt handling of signs of worsening asthma-enhance asthma control. Inhaled corticosteroids are first-line controller therapy for persistent asthma during pregnancy.

 Inflammatory bowel disease (IBD) does not decrease fertility; however, fertility in patients with IBD is possibly affected by active disease, medications, and prior surgeries. Women with IBD experience worse obstetrical and pregnancy-related outcomes compared to the general population, even with disease remission.

	The course of IBD during pregnancy is determined by how active the disease is at conception. Women in remission at conception are likely to remain in remission during pregnancy. In contrast, up to 70% of women with active disease at conception will have continued or worsening symptoms.

	Stopping medications that are maintaining remission can induce relapse or flare. Methotrexate and diphenoxylate are contraindicated in pregnancy, whereas sulfasalazine, 5-aminosalicylates, and corticosteroids are considered safe. Many immunomodulators (ie, azathioprine and 6-mercaptopurine) and biologic agents (ie, infliximab) are safe during pregnancy but their use should be managed in coordination with MFM and an IBD specialist.

 Women with systemic lupus erythematosus (SLE) have better pregnancy prognoses if their disease has been quiescent for at least 6 months prior to pregnancy and they have normal or near-normal renal function. Active SLE at conception is a strong predictor of adverse maternal and obstetrical outcomes.

	Disease flares with pregnancy are difficult to decouple from the physiologic changes of pregnancy and from preeclampsia. Most SLE medication can be continued during pregnancy, but these drugs should be reviewed prior to conception. Medications contraindicated in pregnancy include cyclophosphamide, mycophenolate, methotrexate, and leflunomide. Other SLE drugs that are reasonably safe for use during pregnancy (with certain limitations beyond the scope of this review) are nonsteroidal anti-inflammatory drugs, glucocorticoids, azathioprine, rituximab, belimumab, and some antihypertensive medications.

	The most important aspect of preconception counseling in cases of SLE is to determine whether pregnancy may present an unacceptably high maternal or fetal risk, and to optimize preconception disease status.

	1. Johnson K, Posner SF, Biermann J, et al. Recommendations to improve preconception health and health care-United States. A report of the CDC/ATSDR Preconception Care Work Group and the Select Panel on Preconception Care. 

	2. Frayne DJ, Verbiest S, Chelmow D, et al. Health Care System Measures to Advance Preconception Wellness: Consensus Recommendations of the Clinical Workgroup of the National Preconception Health and Health Care Initiative. 

	3. ACOG Practice Bulletin. Clinical Management Guidelines for Obstetrician-Gynecologists. Number 60, March 2005. Pregestational diabetes mellitus. 

	4. Moos MK, Bangdiwala SI, Meibohm AR, Cefalo RC. The impact of a preconceptional health promotion program on intendedness of pregnancy. 

	5. Henshaw SK. Unintended pregnancy in the United States. 

	6. Yoon P SM. The family history public health initiative Atlanta, GA: CDC; 2004.

	7. Dolan SM, Moore C. Linking family history in obstetric and pediatric care: assessing risk for genetic disease and birth defects. 

	8. JGDC. Jewish Genetic Disease Consortium. 2015 [cited 2015 November]; Available from: http://www.jewishgeneticdiseases.org/genetics-and-carrier-screening/

	9. Committee opinion no. 608: influenza vaccination during pregnancy. 

	10. CDC. Pregnancy and Whooping Cough. 2016 [cited July 17, 2016]; Available from: https://www.cdc.gov/pertussis/pregnant/hcp/pregnant-patients.html

	11. Petersen EE, Polen KN, Meaney-Delman D, et al. Update: Interim Guidance for Health Care Providers Caring for Women of Reproductive Age with Possible Zika Virus Exposure – United States, 2016. 

	12. Simeone RM, Shapiro-Mendoza CK, Meaney-Delman D, et al. Possible Zika Virus Infection Among Pregnant Women - United States and Territories, May 2016. 

	13. Hadar E, Ashwal E, Hod M. The preconceptional period as an opportunity for prediction and prevention of noncommunicable disease. 

	14. SMFM Statement: benefit of antihypertensive therapy for mild-to-moderate chronic hypertension during pregnancy remains uncertain. 

	15. American College of O, Gynecologists, Task Force on Hypertension in P. Hypertension in pregnancy. Report of the American College of Obstetricians and Gynecologists’ Task Force on Hypertension in Pregnancy. 

	16. Sibai BM, Anderson GD. Pregnancy outcome of intensive therapy in severe hypertension in first trimester. 

	17. Canobbio MM, Warnes CA, Aboulhosn J, et al. Management of Pregnancy in Patients With Complex Congenital Heart Disease: A Scientific Statement for Healthcare Professionals From the American Heart Association. 

	18. Kwon HL, Belanger K, Bracken MB. Asthma prevalence among pregnant and childbearing-aged women in the United States: estimates from national health surveys. 

	19. Dombrowski MP, Schatz M. ACOG practice bulletin: clinical management guidelines for obstetrician-gynecologists number 90, February 2008: asthma in pregnancy. 

	20. Cornish J, Tan E, Teare J, et al. A metaanalysis on the influence of inflammatory bowel disease on pregnancy. 

	21. Getahun D, Fassett MJ, Longstreth GF, et al. Association between maternal inflammatory bowel disease and adverse perinatal outcomes. 

Preconception care is primary prevention. The goal is to affirm pregnancy intention, reduce any potential harm, and recognize modifiable risk factors related to pregnancy while stratifying pregnancies on a continuum of low- to high-risk.

Author | Christina S Han, MD

Articles

Artificial intelligence in ob/gyn ultrasound

How to optimize imaging in the obese gravida

Trimester zero (Part 1 of 2)