Artificial Intelligence in Obstetrics practice
Download as PPTX, PDF0 likes2,744 views
Artificial intelligence (AI) is increasingly integrated into obstetrics, enhancing areas such as prenatal screening, diagnostics, and monitoring to improve maternal and fetal health outcomes. AI technologies facilitate automated image analysis, risk assessment, and personalized treatment plans, offering tools like AI-based ultrasound devices and predictive analytics for conditions like preeclampsia. However, challenges including data quality, ethical concerns, and integration into existing healthcare systems must be addressed to ensure the safe and effective use of AI in this field.
Artificial Intelligence in Obstetrics practice
- 1. ARTIFICIAL INTELLIGENCE IN OBSTETRICS
- 2. Smart Phones Face recognition technology AI Pictures Google Maps Weather prediction Health Apps NLP voice recognition technology Alexa, Google assistant ,Apple Siri PredictiveTexts Smart cars Social media Chat GPT AI has seamlessly integrated into various facets of our daily lives
- 3. WHAT IS AI Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and learn like humans Healthcare data is multifactorial and requires . Complex algorithms to analyse large amount of data which helps clinician in decision making Deep learning is type of AI which has tried to mimic human Intelligence Human brain Synapses pf neurons making multiple connections reasoning process ANN, CNN, SVN,computer vision, NLP
- 4. AI IN HEALTHCARE ENHANCED DIAGNOSTICS PERSONALIZED TREATMENTS EFFICIENT ADMINISTRATIVE PROCESSES, IMPROVED PATIENT OUTCOMES. • Apple Watch analyses your medical records blood pressure, sleep pattern excercises etc and monitors your health proactively Neuralink by Elon musk got the chip inserted in human brain of quadriplegic person and he was able to play games with AI powered • Risk Assessment: IBM Watson Health uses AI to analyze patient data and predict risks such as heart disease, allowing for early intervention. Dermatology:Apps like SkinVision use AI -skin lesions to assess the risk of skin cancer, providing recommendations for follow-up or further examination Imaging Analysis:AI tools like Google Health’s DeepMind and PathAI analyze medical images to detect conditions such as cancer, diabetic retinopathy, and pneumonia. •mammograms
- 5. USE OF AI IN OBSTETRICS •Prenatal Screening and Diagnostics • Automated Ultrasound Analysis • AI can help in detecting fetal abnormalities .Predictive Analytics • Risk Prediction for Preterm Birth, Preeclampsia,GDM • Fetal hear rate monitoring and labour management • Prenatal GeneticTesting • Remote Monitoring andTelehealth • Maternal Health Monitoring via Wearable Devices The use of AI in obstetrics is a rapidly growing field with significant potential to improve maternal and fetal health outcomes. enhancing diagnostic accuracy, treatment plans, and overall patient care.
- 6. AI IN FETAL ULTRASOUND . The combination of artificial intelligence (AI) and obstetric ultrasound may help optimize fetal ultrasound examination Automatic fetal ultrasound standard plane detection Shortening the examination time Reducing the physician’s workload Improving diagnostic accuracy. Biometric parameter measurement
- 7. FETAL CARDIAC IMAGING Congenital heart diseases are the most common fetal malformations Analysis of various planes Arnaout et al. demonstrated a deep learning method identifying the five most essential views of the fetal heart and segmentation of cardiac structures AI has capability to identify fetal structures as early as the first trimester of pregnancy Studies delineated four established fetal heart assessment key plans and expanded to identify up to nine fetal heart structures in the second trimester .
- 9. • A CNN algorithm can be trained to detect fetal CNS abnormalities. • PAICS achieved excellent diagnostic performance for various fetal CNS abnormalities. • comparable to experts, • required less time. • The PAICS has the potential to be an effective and efficient tool in screening for fetal CNS malformations in clinical practice. ISUOG 2021.
- 10. AI IN NT SCAN How AI Enhances NT Measurement: 1. Automated Detection: 1. AI algorithms can automatically identify the correct cross-section of the fetus needed for NT measurement, reducing operator dependency and variability. 2. Precise Measurement: 1. AI can provide highly accurate and consistent measurements of the NT 3. Image Analysis: 1. AI can filter out noise and artifacts, leading to clearer images and more precise measurements
- 11. AUTOMATED BIOMETRY Accurate fetal biometric measurements of head circumference (HC), Biparietal diameter (BPD) Abdomen circumference (AC), and femur length (FL) are used to estimate gestational age (GA) and fetal weight (EFW Reduce errors between inter- and intra-operator measurements Promote clinical efficiency, improve the accuracy of automatic measurement
- 13. LOW COST AI BASED ULTRASOUND Baby checker -Artificial Intelligence (AI) tools which work in combination with low-cost ultrasound devices. These ultrasound devices connect directly with a smartphone running the babychecker AI software Run offline and at low-cost Untrained users requires a maximum of 2 hours BabyChecker AI installed as a mobile application. BabyChecker is in low-resource settings. Through the 6-sweep obstetric protocol, the ultrasound images are acquired and analysed by the app. Timely referral can be done
- 15. PREECLAMPSIA PREDICTION Biomarker Analysis •Analysis of Biomarkers: •AI can analyze complex biomarker data, such as levels of specific proteins or metabolites in blood samples, to identify early signs of preeclampsia. •This includes analyzing data -Placental Growth Factor (PlGF) • soluble fms-like tyrosine kinase-1 (sFlt-1). •Genetic and Epigenetic Data: •AI can integrate genetic and epigenetic data to identify predispositions to preeclampsia, potentially allowing for earlier interventions
- 16. Conclusion The results of studies yielded high prediction performance of ML models for preeclampsia risk from routine early pregnancy information.
- 17. The objective of this study was to examine the potential value of neural networks for the prediction of PE by a combination of maternal factors and biomarkers obtained at 11–13 weeks’ gestation without converting raw data into MoMs. Conclusions Screening for PE using a non-linear machine-learning-based approach does not require a population-based normalization, and its performance is similar to that of logistic regression.
- 19. App targets to serve patients in resource-limited areas, only fasting glucose value ,other patient’s basic health information such as age, body weight, and height. Study proved that SVM based AI can achieve accurate diagnosis with less operation cost and higher efficacy.
- 20. •. 2019 Jul;54(1): Artificial intelligence and amniotic fluid multiomics: prediction of perinatal outcome in asymptomatic women with short cervix R O Bahado-Singh1 , J Sonek2 , D McKenna3 , D Cool4 , B Aydas5 , O Turkoglu1 , T Bjorndahl6 , R Mandal6 , D Wishart6 , P Friedman1 , S F Graham1 , A Yilmaz1 Objective: To evaluate the application of artificial intelligence (AI), i.e. deep learning and other machine-learning techniques, to amniotic fluid (AF) metabolomics and proteomics, alone and in combination with sonographic, clinical and demographic factors, in the prediction of perinatal outcome in asymptomatic pregnant women with short cervical length (CL). Conclusions: This is the first study to report use of AI with AF proteomics and metabolomics and ultrasound assessment in pregnancy. Machine learning, particularly deep learning, achieved good to excellent prediction of perinatal outcome in asymptomatic pregnant women with short CL in the second trimester.
- 21. AI IN FETAL HEART RATE AND LABOUR MONITORING Fetal Monitoring:AI algorithms can analyze real-time fetal heart rate data to detect patterns that might indicate distress or other issues, providing timely alerts. • Labor Monitoring: During labor,AI can help monitor contractions, fetal heart rates, and other indicators to provide insights into the progress of labor and suggest appropriate interventions.
- 22. •AI can automatically interpret FHR tracings according to established guidelines, such as those from the ACOG. • Reducing variability in interpretation between different clinicians • Ensuring more consistent assessments. Automated Interpretation of CTG
- 23. Artificial intelligence and machine learning in cardiotocography: A scoping review Jasmin L Aeberhard1 , Anda-Petronela Radan2 , Ricard Delgado-Gonzalo 3 , Karin Maya Strahm2 , Halla Bjorg Sigurthorsdottir 3 , Sophie Schneider2 , Daniel Surbek 2 Conclusions: There are several promising approaches in this area, but none of them has gained big acceptance in clinical practice. Further investigation and refinement of the algorithms and features are needed to achieve a validated decision-support system
- 24. HOME MOINITORING AI technology could be used for outpatient care in the form of home monitors,Wearable devices that can adequately provide surveillance of high risk patients AI-based systems can continuously track maternal health parameters such as blood pressure, glucose levels, and weight . AI algorithms analyze the data and provide real-time alerts to healthcare providers when deviations from the normal ranges are detected. Possibility of guiding decision-making and management using telecommunications, combined with in-home pregnancy monitoring can prove beneficial in the early detection of pregnancy complications and decrease maternal and infant mortality.
- 26. PATIENT ENGAGEMENT AND EDUCATION Virtual Assistants:AI-powered chatbots and virtual assistants can provide expectant mothers with information about pregnancy, answer common questions, and offer support between appointments. • EducationalTools:AI can help create personalized educational content and resources for patients, tailored to their specific needs and concerns.
- 27. Non-Invasive PrenatalTesting (NIPT): •Improved Accuracy: AI enhances the accuracy of NIPT by analyzing cell-free fetal DNA (cffDNA) in maternal blood to detect chromosomal abnormalities such as trisomy 21 (Down syndrome), trisomy 18, and trisomy 13. . Integration of Multi-Omics Data: •Comprehensive Analysis: AI can integrate and analyze data from various sources, including genomics, proteomics, and metabolomics, to provide a comprehensive assessment of fetal health and identify potential genetic issues.
- 28. CHALLENGES 1.Data Quality and Availability: . In obstetrics, data may be incomplete or biased, leading to ineffective or potentially harmful models. 2.Limited Understanding of Context: AI lacks the ability to understand complex human emotions and socio-cultural factors that can influence obstetric care, potentially leading to inappropriate recommendations. 3.Ethical Concerns: The use of AI can raise ethical questions regarding patient consent, privacy, and the potential for bias in algorithms that may lead to unequal treatment outcomes. 4.Dependence on Technology: Over-reliance on AI systems can undermine clinicians' skills and decision- making abilities, potentially leading to a decline in critical thinking and clinical acumen. 5.Integration Challenges: Integrating AI systems into existing healthcare workflows and systems can be difficult .
- 29. 6.Cost: The implementation and maintenance of AI technologies can be expensive 7.Regulatory Hurdles: The rapid evolution of AI technologies may outpace regulatory frameworks, leading to uncertainty about the safety and efficacy of AI tools in obstetrics. 8.Accountability Issues: Determining accountability in the case of errors or adverse events resulting from AI recommendations can be challenging, complicating legal and professional responsibility. 9.Potential for Job Displacement: While AI can augment clinical capabilities, there is concern about the potential for job displacement in the healthcare workforce, particularly in routine tasks. 10.Misinformation and Overconfidence: There is a risk that both patients and practitioners may overestimate the capabilities of AI, Addressing these drawbacks requires careful consideration and collaboration among healthcare providers, technologists, and regulators to ensure that AI is used safely and effectively in obstetrics.
- 30. CONCLUSIONS AI has the potential to guide practitioners in decision-making, reaching a diagnosis, and improving case management. AI Helps doctors to reduce their workload and increase their efficiency and accuracy But How doctors think ,reason and make clinical decisions is the most critical skill which no AI can substitute and of course human Touch