Tag: pregnancy

Predicting diabetes risk

A new computer algorithm can predict in the early stages of pregnancy, or even before pregnancy has occurred, which women are at a high risk of gestational diabetes. (photo from Weizmann Institute)

A new computer algorithm can predict in the early stages of pregnancy, or even before pregnancy has occurred, which women are at a high risk of gestational diabetes, according to a study by researchers at the Weizmann Institute of Science.

The study, reported recently in Nature Medicine, analyzed data on nearly 600,000 pregnancies available from Israel’s largest health organization, Clalit Health Services.

“Our ultimate goal has been to help the health system take measures so as to prevent diabetes from occurring in pregnancy,” said senior author Prof. Eran Segal of the institute’s computer science and applied mathematics, and molecular cell biology departments.

Gestational diabetes is characterized by high blood sugar levels that develop during pregnancy in women who did not previously have diabetes. It occurs in three to nine percent of all pregnancies and is fraught with risks for both mother and baby. Typically, gestational diabetes is diagnosed between the 24th and 28th weeks of pregnancy, with the help of a glucose tolerance test in which the woman drinks a glucose solution and then undergoes a blood test to see how quickly the glucose is cleared from her blood.

In the new study, Segal and colleagues started out by applying a machine learning method to Clalit’s health records on some 450,000 pregnancies in women who gave birth between 2010 and 2017. Gestational diabetes had been diagnosed by glucose tolerance testing in about four percent of these pregnancies. After processing the dataset – made up of more than 2,000 parameters for each pregnancy, including the woman’s blood test results and her and her family’s medical histories – the scientists’ algorithm revealed that nine of the parameters were sufficient to accurately identify the women who were at a high risk of developing gestational diabetes. The nine parameters included the woman’s age, body mass index, family history of diabetes and results of her glucose tests during previous pregnancies (if any).

Next, to make sure that the nine parameters could indeed accurately predict the risk of gestational diabetes, the researchers applied them to Clalit’s health records on about 140,000 additional pregnancies that had not been part of the initial analysis. The results validated the study’s findings: the nine parameters helped accurately identify the women who ultimately developed gestational diabetes.

These findings suggest that, by having a woman answer just nine questions, it should be possible to tell in advance whether she is at a high risk of developing gestational diabetes. If this information is available early on – in the early stages of pregnancy or even before the woman has gotten pregnant – it might be possible to reduce her risk of diabetes through lifestyle measures such as exercise and diet. On the other hand, women identified by the questionnaire as being at a low risk of gestational diabetes may be spared the cost and inconvenience of the glucose testing. (Visit weizmann.ac.il/sites/gd-predictor to access the self-assessment questionnaire.)

In more general terms, this study has demonstrated the usefulness of large human-based datasets, specifically electronic health records, for deriving personalized disease predictions that can lead to preventive and therapeutic measures.

The work was led by graduate students Nitzan Shalom Artzi, Dr. Smadar Shilo and Hagai Rossman from Segal’s lab at the Weizmann Institute of Science, who collaborated with Prof. Eran Hadar, Dr. Shiri Barbash-Hazan, Prof. Avi Ben-Haroush and Prof. Arnon Wiznitzer of the Rabin Medical Centre in Petach Tikvah; and Prof. Ran D. Balicer and Dr. Becca Feldman of Clalit Health Services.

 

Safety in home births

With only about five percent of Canadians giving birth at home, one might think the practice is dangerous and that is why the number is so low. On the contrary. Studies show that, as long as the mother is at low risk, it is as safe to give birth at home as it is to give birth in a hospital.

Dr. Michael Klein is a family physician, pediatrician, newborn-intensive-care specialist, maternity care researcher and senior scientist emeritus at Vancouver’s Child and Family Research Institute.

“I am a part of a number of ongoing research projects,” said Klein. “We look at old and new technologies and assess them in relation to birth. I’m about normal birth – not complicated birth – keeping birth normal.”

photo - Dr. Michael Klein
Dr. Michael Klein (photo from Dr. Michael Klein)

In 2009, Klein worked on a study that looked at the safety of home births, evaluating three groups of births: home births by a midwife, hospital births by the same midwives, and a matched sample of physician births. The researchers looked at women who were identical in their risk profile and found that, regarding fetus development and the newborn baby, there was no difference in these three groups.

“Home birth seemed to be as safe as hospital birth, whether by the doctor or by the same midwife,” said Klein. “There are now two other studies from Ontario that show the same thing.

“Home birth is integrated within the health-care system in B.C.,” he continued. “Midwives are supported and part of the system, so when the midwife needs help from a hospital backup system, she gets it.

“Of course, what you also see is dramatically more interventions on the physician-hospital side than at home. And you find, interestingly, that the midwives – the same midwives delivering in hospitals – have results in terms of interventions of various sorts that are closer to the doctor’s side than they are to themselves at home.”

Klein attributes this observation to the influence of the hospital itself, a setting that is anxiety-driven. There may also be differences in the population, with women wanting a midwife in a hospital differently motivated from those wanting a midwife in a home setting.

In terms of the methodology of the study, it was very important that, once a woman was beginning her labor at home, no matter if the birth ended up being in a hospital or not, that she was counted in the home birth column or category.

“Roughly, a third of midwifery births will be home births,” said Klein. “That’s because this is what women are requesting. The model is what is called a ‘woman-centred model.’ If a woman wants a home birth and she meets the criteria in terms of her risk profile, then the midwife is obligated to deliver that service in the way she wants.

“I think there’s no question that we should have more home births. You may be unaware, but the minister of health in B.C. has supported that notion – that home births should be … I wouldn’t say promoted, but certainly made available.

“Women need to know what the options are and they need to know if they need help during labor that they will get it. A home birth, to be safe, needs to be within 30 minutes of an operating room. Contrary to what most people believe, things don’t suddenly go wrong. They evolve.”

Something else that can be a limiting factor in increasing home birth numbers is the lack of midwives across Canada.

“The joke is that you have to register with a midwife before conception,” said Klein.

In British Columbia, the midwifery class recently doubled in size. Why not quadruple the class size to keep up with demand? The simple answer is that the system is not currently able to support that, although it is estimated that a home birth costs the system between a third and half as much as a hospital birth.

“I think it’s too complex,” said Klein. “What we are talking about now is a serious planning exercise. That’s not happening. I think it will take time for the system to collapse a little bit more before it happens.

“The other player in all of this, which we haven’t talked about yet, is the doula. That movement is, of course, gaining more and more popularity. In some settings, it’s been so successful that some hospitals are supporting the doulas’ salaries.”

According to Klein, doulas are successful in lowering the caesarean-section rate and other interventions. “When you lower the c-section rate, it has a big impact on the hospital budget, because a person who has a caesarean stays twice as long in the hospital than one who has a vaginal birth,” he said.

Avoiding a c-section means less likelihood of a uterine scar in subsequent pregnancies. “Once a pregnant woman has a uterine scar, the whole reproductive trajectory is changed,” said Klein. “One is more likely to have a whole series of problems, complicated next pregnancies, placental attachment problems, ectopic pregnancies, stillborn births and infertility. With the c-section rate at four percent in home births and up to 30% in hospital births, that many more women will end up with a uterine scar and be at higher risk of complications.”

photo - Dr. Brian Goldman
Dr. Brian Goldman (photo from Dr. Brian Goldman)

Dr. Brian Goldman, an emergency physician at Mount Sinai Hospital in Toronto, and the host of White Coat, Black Art on CBC Radio One, has, for years, had an eye on the growing demand among women in Canada for licensed midwives.

“Midwives are experts in low-risk, uncomplicated births, as are family doctors,” said Goldman. “However, even though low-risk birth is a core part of the training of family physicians, very few of them want to attend low-risk births once out in practice.

“In Canada, we have a situation in which the vast majority of births – high-risk and low-risk alike – are attended by obstetricians. These specialists have tremendous knowledge, skill and experience which, in my opinion, is best put to use managing women who are likely to have a complicated pregnancy and birth. We need more professionals like midwives and family doctors to attend low-risk births.

“Most family doctors run busy practices and find it difficult for practice, family and social reasons to devote a significant amount of time to attending women in labor through the night. To me, midwives represent the likeliest prospect for increasing the pool of professionals qualified and interested in attending low-risk births.”

Rebeca Kuropatwa is a Winnipeg freelance writer.