Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 5 de 5
Filter
1.
Reprod Toxicol ; 113: 150-154, 2022 10.
Article in English | MEDLINE | ID: mdl-36067870

ABSTRACT

The Dutch Teratology Information Service Lareb counsels healthcare professionals and patients about medication use during pregnancy and lactation. To keep the evidence up to date, employees perform a standardized weekly PubMed query where relevant literature is identified manually. We aimed to develop an accurate machine-learning algorithm to predict the relevance of PubMed entries, thereby reducing the labor-intensive task of manually screening the articles. We fine-tuned a pre-trained natural language processing transformer model to identify relevant entries. We split 15,540 labeled entries into case-control-balanced train, validation, and test datasets. Additionally, we externally validated the model prospectively with 1288 labeled entries obtained from weekly queries after developing the model. This dataset was also independently labeled by a team of six experienced human raters to evaluate our model's performance. The validation of our machine learning model on the retrospectively collected outheld dataset obtained an area under the sensitivity-versus-specificity curve of 89.3 % (CI: 88.2- 90.4). In the prospective external validation of the model, our model classified relevant literature with a sensitivity versus specificity curve area of 87.4 % (CI: 85.0-89.8). Our model achieved a higher sensitivity than the human raters' team without sacrificing too much specificity. The team of human raters showed weak to moderate levels of agreement in their article classifications (kappa range 0.40-0.64). The human selection of the latest relevant literature is indispensable to keep the teratology information up to date. We show that automatic preselection of relevant abstracts using machine learning is possible without sacrificing the selection performance.


Subject(s)
Abstracting and Indexing , Algorithms , Machine Learning , Teratology , Abstracting and Indexing/methods , Female , Humans , Pregnancy , Prospective Studies , Reproducibility of Results , Retrospective Studies
2.
Ned Tijdschr Geneeskd ; 1652021 09 16.
Article in Dutch | MEDLINE | ID: mdl-34854634

ABSTRACT

BACKGROUND: Inflammatory bowel disease affects many women of childbearing potential. Women who wish to conceive face many uncertainties. Effects of their medications and their disease may interfere with normal pregnancy and development of the child. CASE DESCRIPTION: A 30 year old woman with Crohn's disease has a wish to conceive. Her disease has been in remission for 2 years with infliximab use. She is concerned about effects of the medication on her pregnancy and child. An individual risk assessment was made and infliximab was continued until week 22 of gestation. Her pregnancy was monitored, a healthy neonate was born at 38 weeks. CONCLUSION: For women on chronic medication an individual preconceptional risk assessmentis needed. The influence of the disease on pregnancy and fetushas to be weighed against possible risks of the drug(s). Crohn's disease is preferably in remission well before and during pregnancy.


Subject(s)
Crohn Disease , Inflammatory Bowel Diseases , Adult , Antibodies, Monoclonal , Child , Crohn Disease/drug therapy , Female , Humans , Infant, Newborn , Inflammatory Bowel Diseases/drug therapy , Infliximab/adverse effects , Pregnancy
3.
Ned Tijdschr Geneeskd ; 160: A9900, 2016.
Article in Dutch | MEDLINE | ID: mdl-27165457

ABSTRACT

Many women use medication during pregnancy. Both the healthcare professional and the pregnant woman often have many questions about the possible adverse effects of the medication that are not always answered in the product information. The Teratology Information Service (TIS), a part of the Netherlands Pharmacovigilance Centre Lareb, is a centre of expertise in the field of the safety of medication use and other external influences during spermatogenesis, pregnancy and lactation. The TIS collects, interprets, and disseminates information that can contribute to patient care. Healthcare professionals can contact the TIS for information and individual risk assessments. In this article we discuss the background and positioning of the TIS, the characteristics of telephone consultations, the collection of data and the considerations that are important for the use of medication during pregnancy and lactation.


Subject(s)
Information Services/standards , Lactation , Pharmacovigilance , Pregnancy , Teratology , Breast Feeding , Drug-Related Side Effects and Adverse Reactions , Female , Health Personnel , Humans , Male , Netherlands , Referral and Consultation , Risk Assessment , Spermatogenesis/drug effects
4.
Neurology ; 86(24): 2251-7, 2016 Jun 14.
Article in English | MEDLINE | ID: mdl-27194385

ABSTRACT

OBJECTIVE: To investigate pregnancy outcomes following maternal use of pregabalin. METHODS: This multicenter, observational prospective cohort study compared pregnancy outcomes in women exposed to pregabalin with those of matched controls (not exposed to any medications known to be teratogenic or to any antiepileptic drugs). Teratology Information Services systematically collected data between 2004 and 2013. RESULTS: Data were collected from 164 exposed pregnancies and 656 controls. A significantly higher major birth defect rate in the pregabalin group was observed after exclusion of chromosomal aberration syndromes, and when cases with exposure during first trimester of pregnancy were analyzed separately (7/116 [6.0%] vs 12/580 [2.1%]; odds ratio 3.0, 95% confidence interval 1.2-7.9, p = 0.03). The rate of live births was lower in the pregabalin group (71.9% vs 85.2%, p < 0.001), primarily due to a higher rate of both elective (9.8% vs 5.0%, p = 0.02) and medically indicated (5.5% vs 1.8%, p = 0.008) pregnancy terminations. In the Cox proportional cause specific hazards model, pregabalin exposure was not associated with a significantly higher risk of spontaneous abortion. CONCLUSIONS: This study demonstrated a signal for increased risk of major birth defects after first trimester exposure to pregabalin. However, several limitations such as the small sample size, differences across groups in maternal conditions, and concomitant medication exposure exclude definitive conclusions, so these results call for confirmation through independent studies.


Subject(s)
Abnormalities, Drug-Induced/epidemiology , Central Nervous System Agents/adverse effects , Pregabalin/adverse effects , Pregnancy Outcome/epidemiology , Adult , Central Nervous System Agents/therapeutic use , Europe , Female , Humans , Incidence , Pharmacovigilance , Pregabalin/therapeutic use , Pregnancy , Pregnancy Trimester, First/drug effects , Proportional Hazards Models , Prospective Studies , Risk
5.
Ned Tijdschr Geneeskd ; 157(41): A6567, 2013.
Article in Dutch | MEDLINE | ID: mdl-24103139

ABSTRACT

BACKGROUND: Acne is a common problem that is increasingly being effectively treated with isotretinoin, a highly teratogenic agent. According to the pregnancy prevention program, contraception should be used until at least one month after discontinuing the medication. CASE DESCRIPTION: A 29-year-old woman became pregnant shortly after discontinuing isotretinoin. She was referred to the gynaecologist for an abortion. However, since she wished to continue the pregnancy, she received personal advice on the risk of bearing a child with congenital abnormalities. After an uneventful pregnancy she gave birth to a healthy son. CONCLUSION: Given the teratogenicity of isotretinoin, every woman in the fertile phase of life should use contraception while taking the medication. If she becomes pregnant, however, the individual risk of having a child with congenital abnormalities can be carefully and reliably estimated by determining the precise date of conception through ultrasound and the date that isotretinoin was stopped.


Subject(s)
Abnormalities, Drug-Induced/prevention & control , Acne Vulgaris/drug therapy , Isotretinoin/adverse effects , Isotretinoin/therapeutic use , Abnormalities, Drug-Induced/epidemiology , Adult , Contraception/methods , Contraception/statistics & numerical data , Female , Humans , Pregnancy , Pregnancy Complications/chemically induced , Pregnancy Complications/epidemiology , Pregnancy Complications/prevention & control , Pregnancy Outcome , Teratogens
SELECTION OF CITATIONS
SEARCH DETAIL
...