Get the Artificial Intelligence (AI) Edge in Obstetrics and Gynaecology.

Artificial intelligence (AI) is on the fast track so far as the growth is concerned, from experimental to implementation in field of medicine. AI should be used ethically and intelligently. Large data base availability, advances in algorithm—theories, computing improvements has led to breakthrough in AI applications in current medicine. Machine learning (ML), which is subset of AI, allows computers to detect patterns through larger data base automatically, that can be used to make predictions. Is it paradigm shift? In the field of Obstetrics and Gynaecology, AI is used in reproductive medicine for diagnosis, treatment with fertility outcome, cancer treatment, USG–MRI images diagnosis, foetal echocardiography, cardiotocography (CTG), preterm labour prediction and urogynaecology. ChatGPT can be helpful in medical writing but there is always a challenge with respect to accuracy and reliability. AI can be used in research and experiments, there by strengthening evidence-based clinical practice. More research is ongoing on personalized diagnosis, treatment and remote medical expert team opinion. It does not replace the medical advice given by the clinician but that should not deter clinician by exploring more uses of AI. Despite various challenges and limitations, integration of AI in medical field is bound to progress in correct direction for better future.

Namaste AI The term artificial intelligence (AI) was first coined by John McCarthy at Dartmouth summer Research Project in 1955 [1]. AI is ability of machine to learn and display intelligence was inspired by structure of brain but is totally different from the (natural) intelligence displayed by humans/animals. It is simulation of human intelligence in machine that is programmed to think and learn like humans. In artificial neural network (ANN) of AI, brain’s neurons are represented by nodes that influence each other through connections, send data back and forth multiple times and then come up with most probable answer. AI has developed and progressed so rapidly, that it has penetrated in all sectors of human life including medicine. Computers driven by power, memory and large data storage have been handling complex learning tasks with good success in recent years. We use AI in daily life, like web search engine (Google), recommendation online entertainment system (YouTube/Netflix), speech recognition (Siri/Alexa), self-driven cars (Tesla) [2]. In medical field, breakthrough occurred due to huge amount of patient data, experiments, trials, hospital and environmental factors leading to challenges with innovative opportunities in clinical practice. The source of increased available data was from electronic medical records (EMR), hospital and cloud data sharing. This exceeded conventional statistical analysis to extract meaningful conclusion on complex diseases. Hence, there was need for higher levels of analysis to help medical personnel to utilize it for patient benefit. AI learned this potential relationship of large data and used algorithms to assist in clinical practice. New medical information was gained from successful cases, and clinical guidelines were made using such information. AI can help clinicians make self-assured decision, but it cannot replace clinical experience. AI can reduce inevitable medical errors by improving interpretation and decreasing workload, that otherwise could have been overlooked. Thus, it helps treatment and can make predictions on health risk, but human mind will be needed to implement it. Current feasibility of AI application is still narrow, when universal uniformity is still in question. Artificial intelligence needs training and support from partners to become successful. Best example would be IBM’s Watson for Oncology [1]. There are 3 types of artificial intelligence methods widely used in medical applications: [1] ML—Machine learning. NLP—Natural language processing. Robotic surgery. 4 essential core elements of AI: ML, NLP, ANN, Computer vision ML clusters feature of patients and predicts outcome after analysis of structured data. It allows computers to make predictions after detecting patterns from large complexes. Traditional statistics can predict/estimate disease condition, whereas ML will focus on clinical decision system for optimal outcome assisting medical personnel to make decision. For accurate information, large storage data suitable for computational purpose and robust computing power should be available. With insufficient data input, results may not be proper. Supervised machine learning is useful but requires humans for labelling and hence is time-consuming. Unsupervised learning is used to predict unknown results. Reinforcement learning concentrates on improving accuracy with trial and error and hence is used for medical image processing, personal medications and robotic surgery. Computer vision means understanding of images and videos like facial recognition. National language processing (NLP) aims to understand human language that extracts and processes meaningful information from unstructured clinical data like electronic medical records (EMR) to complement structured data. NLP allows doctors to write normally, rather than record information within specific framework for computer to identify data. NLP converts raw data into structured data that machine can read and analyse Fig. 1. Example would be artificial neural network (ANN); feed forward type has been able to predict mortality in acute pancreatitis more accurately than scoring system [3]. Robotic Surgery Minimally invasive surgery has become the most influential innovative surgical development of modern time. Entering human body with small incisions, using high resolution cameras and long—thin instruments to perform surgery for early peri-operative recovery, less pain, better post-operative quality of life and reproductive outcome. Robotic surgery has provided better ergonomics with 3D visual effect, high precision, finer instruments with shorter learning curve. Robotic surgery has been used in the field of gynaecology for endometrial carcinoma, uterine myoma, deep infiltrating endometriosis (DIE), adenomyoma, adnexal pathology and fertility enhancing surgery. It has better results in DIE, endometrial carcinoma with more precision. In patients with adenomyoma (where demarcation is usually unclear), meticulous suturing is feasible with clear 3D vision, thereby improving symptoms with resolution of pathology. With robots available in many public/private hospitals, it has become a part of AI surgical skill, but for the high cost. With wider usage, better outcome will be seen with relatively low cost. Overview of AI in Obstetrics/Gynaecology Role of AI in Reproductive Medicine Advances in AI are proportionately connected with more data flowing in reproductive medicine. Fertility treatment varies with individuals, with no one size fits all. With progress in assisted reproductive technology (ART) treatment like oocyte or embryo cryopreservation, PGD—preimplantation genetic testing, embryo selection techniques, clinical pregnancy rates have improved. The quality of embryo is the most crucial factor, and there are no methods available to judge the same. The embryo, egg or sperm selection methods have not yet been identified. Hence, it is difficult to understand the reason for failure or parameters to predict success. AI can optimize the treatment using huge data with complex diagnosis and therapeutic modalities for successful results with less financial burden. Applications Oocyte Selection Good quality oocytes give high success rate. Many strategies have been proposed to evaluate and select oocyte with best developmental potential, but still, it may not be able to give results. The best method of oocyte selection should be non-invasive, not expensive and capable of getting incorporated into embryology system with least impact. AI methods will help evaluate human oocyte with good developmental potential. Embryo Selection Embryologist uses visualization method (morphology—dynamic development) to select embryos or oocytes, and evaluation is subjective. There is more possibility of pre-eclampsia, multi-foetal pregnancy, maternal haemorrhage, if more than one embryo is transferred. Morphology of embryo remains the main factor for selection. AI has optimized culture condition of embryo, improving its survival and development. Grading and ranking embryos help predict decision making and AI developed morphokinetic model that can exclude embryos with lowest implantation potential. Sperm Selection/Semen Quality The computer-aided sperm analysis (CASA) is used for semen examination. Precise results are challenging, because of difficult evaluation of sperm morphology manually and no uniformity between laboratories. One-third of male factor fertility are idiopathic, and the current method of semen analysis cannot detect multiple male factors. There is link between semen quality and environmental factors. Prediction of chromosomal abnormality could be up to 95%, while taking into consideration height, testicular volume, follicular-stimulating hormone (FSH), luteinizing hormone (LH), testosterone and ejaculate volume [1]. AI techniques were used taking into consideration these factors, and it helped improve performance with avoidance of environmental factors with better results. Predictive Model Creation With AI, clinicians can create personalized treatment module of ART, predict optimal time of transfer and improve pregnancy outcome. AI incorporated accuracy of prediction is gradually improving after using previous in vitro fertilization (IVF)/intracytoplasmic sperm injection (ICSI) records. The crucial predictive factors being age of women, no of developed embryos, serum estradiol levels on day of human chorionic gonadotropin (HCG) administration. Supervised learning method has developed strategies for female age-related different embryo transfer. AI with ML can dramatically promote reproductive medicine in near future, as there are ongoing studies on good non-invasive marker to improve implantation rate and efficacy of treatment. Limitations being retrospective small data from single source, no randomized control trials, ethical consideration and possibility of risk of offsprings. Obstetrics Foetal Heart Monitoring/Pregnancy Surveillance Foetal heart rate (FHR) pattern shows cardiac and neurological responses to haemodynamic changes. CTG (cardiotocography) has been able to reduce neonatal complications, but regular observations are required to take prompt/timely decisions. Systematic review did not show any improvement in neonatal outcome after ML interpretation because AI models that are used were based on human interpretation [4]. With advanced computer system and engineering theory, leading to automatic interpretation of CTG without human interpretation, it will be able to give accurate results [5]. It can be used to monitor high risk pregnancy, to identify foetus at distress. Ultrasonography (USG) Obstetrics USG measurements, though standardized can be challenging at times in case of obesity, acoustic shadow, speckled noise. Currently manual USG methods are slow, with possibility of subjective errors. Data storage of 2D USG images is not very useful. New technology is being improvised to improve the acquired image to standardize measurements. ML has been able to distinguish different foetal body parts, and semi-automatic programmes have been implemented for body measurement using AI algorithm after appropriate body part is selected by the sonologist. Automated programmes that are in service are foetal head measurements, congenital malformations, nuchal translucency, foetal heart, AFI and type of cervix that can be used by trained professionals. In late first trimester, difference in texture of placenta has been studied in hypertensive disorders of pregnancy (HDP) to predict possibility of abnormal outcome in late pregnancy before clinical presentation [6]. Training is required to get high quality image within appropriate time to be able to capture in image scanning procedure. Deep learning model is being developed by using motion, action and pupillary response of sonologist with safety issue information. Foetal Echocardiography Foetal echocardiography is useful for making diagnosis of congenital cardiac anomalies, monitoring foetal growth restriction (FGR) and twin-to-twin transfusion syndrome (TTTS). Performing the same is challenging due to small heart, faster heart rate, involuntary foetal movements, limited access and lack of expertise. Intelligent navigation method like ‘FINE’ has been developed to detect cardiac anomalies, and deep learning (DL) method has been devised to have essential view of heart with structures from all dimensions. Limitation being proper assessment of all images with clinical decision is difficult. Preterm Labour AI is being used for measurement of gestational age, amniotic fluid index (AFI), cervical length and prediction of preterm labour. Deep learning base programmes have been devised to measure angle of progression for suspected preterm labour. International Society of Ultrasound in Obstetrics & Gynaecology has introduced ‘Artificial Intelligence in imaging’ session [4]. Apart from taking measurements, system is devised to use this data to make diagnosis for further treatment directions. Magnetic Resonance Imaging (MRI) AI is used in obstetrics for foetal brain and for diagnosis of placenta accreta/previa. With AI techniques, ventriculomegaly that has been diagnosed antenatally could predict of the possibility of further treatment after birth with great accuracy. AI-based MRI scans gave accurate diagnosis of placenta accreta/percreta and in TTTS, accurate information of volume and distribution of vessels over placenta. Gynaecological Oncology Gynaecological cancer prognosis depends upon International Federation of Obstetrics & Gynaecology (FIGO) classification. With advent of new radiological and bio markers, there is impact on the treatment. For endometrial cancer, p53/KRAS gene mutation values and extramural vascular invasion of pelvic tumours on radiology have stratification value [3]. Despite research, there is a challenge to treat cancer due to multi-factorial aetiology. Predicting response to neoadjuvant therapy on individual basis needs deeper understanding, and AI algorithms are being developed to tackle this. Example would be Software text lab 2, for epithelial serous ovarian tumour, where apart from CA 125 levels, other factors like size, shape, texture, wavelength, intensity were considered, and prediction of prognosis was established with regards response to chemo and surgical therapy [3]. In patients with CIN (cervical intraepithelial neoplasia), after using data of (human papilloma virus) HPV DNA and colposcopy, ANN’s prediction of progression to carcinoma has specificity of 99% with sensitivity of 93%, which gives an opportunity for timely intervention for better patient care [3]. Personalized Medicine Personalized medicine means use of combined knowledge of an individual like genetic, specific medical history to predict possibility of disease with its prognosis and response to treatment. It can guide patient management and forecast outcome. Example would be BRCA 1/BRCA 2 gene for breast cancer predictability, KRAS for endometrial cancer, WNT signal for ovarian—endometrial—cervical cancer prognosis on individual basis [3]. This has caused paradigm shift in medical management to preventive precision care that required detailed vast data. AI has managed to synthesize data in oncology with individual medicine. Gynaecology AI has been used for diagnosis of endometriosis and predict growth/behaviour of fibroid from imaging data. In urogynaecology, MRI images could help diagnosis/quantification of pelvic organ prolapse (POP), understand urodynamic study and subgroups of urinary incontinence (OAB–Overactive Bladder). However, post-therapy (surgical–non-surgical), improvement in quality of life could not be ascertained due to limited data/literature. ChatGPT and AI ChatGPT was produced by OpenAI in Nov 2022 [7]. ChatGPT has potential to impart preliminary information on most of the topics in Obstetrics and Gynaecology. ChatGPT has power of deep learning that can mimic human language. Chatbot has 2 components—versatile AI system and chat interface that enables to have interactive session through queries, followed by response, and emulating human conversation. ChatGPT can serve as ‘clinical assistant’ and help in research writing. It has ability to extract data from electronic medical records and literature search, providing guidance on formatting and writing style. Medical personnel can then review and edit to have precision on what is relevant. It can collaborate multiple reviewer’s opinion to have conclusive outcome that can speed up medical writing with accuracy. ChatGPT can help in formulating differential diagnosis, explanation in simple language about emergency obstetric situation, early pregnancy diagnosis, peri-partum care, family planning and sexual health. Management after diagnosis is articulate and well informed. Though ChatGPT has been able to outperform humans, challenge is on accuracy and reliability so far information on various topic is concerned. Occasional lapses in understanding the content of question can lead to misinformation and misinterpretation (hallucination). Hence, it does not replace medical advice given by the clinician but that should not deter clinician by exploring more uses of ChatGPT. Limitations/Challenges Bubble or not, the AI Genie is out of the Bottle AI in health industry is like new digital literacy. The only way to succeed is to stop resisting and embrace it to harness its power. AI needs to be implemented in clinical work, though there are some shortfalls. ML models lack universal understanding of inner working, leading to ethical, legal and liability issues creating distrust of patients and clinicians. Institutions and clinicians associated with ML should be responsible for the outcome. The limitations of AI being systematic bias, leading to skewed results is due to improper labelling. Performance may suffer, if data is insufficient; hence, larger data collection and sharing are important for success. Collection of large quantity of data requires standardization across the institutions over the broad territory, which is challenging [8]. AI can accept data that is mentioned and integrated. Hence, efforts need to be made to integrate health, laboratory, imaging records for accurate diagnosis and treatment. AI technology has exceeded performance of few clinicians, raising concern of possibility that MI models may replace doctors. AI is just tool to increase comfort and will always be complimentary to clinician. AI can save time and effort of clinician by doing repetitive task, but clinicians should not blindly follow AI model but think while applying results in their clinical work. Trust needs to be built by clinicians and patients while accepting system’s recommendation. But then the issue comes, while following AI’s recommendation, who is liable clinician or hospital? Step Forwards AI has emerged as game changing tool, yielding massive benefit from data base collection, which is the source of wisdom. Basic work of data mining from EMRs, medical images, laboratory results, genetic information and health records can change the way of practising medicine. Example would be in reproductive medicine; it helps physician select better sperms, oocyte and embryos. New technologies for non-subjective sperms and embryo selection, oocyte denudation by mechanical removal of cumulus cells, oocyte positioning, fertilization, embryo culture and monitoring embryo development in automated device can improve efficiency and outcome of ART. Similarly, IBM’s Watson health (ML) provides diagnosis and possible treatment option for cancer [1]. AI can streamline appointments, manage electronic health data, analyse laboratory results [9]. Chatbots can assist patients answer routine questions, provide educational material and guide them on self-care in between the appointments. It thereby allows healthcare worker to spend quality time on patient care. Ensuring patient privacy, informed consent, counselling and transparency in AI module can create strong bond and trust. Evidence-based high quality research approach is the way forwards to face many challenges in clinical practice. The grey areas in traditional research and statistics have failed to address complex problems and provide solutions in clinical practice. Clinical trials are costly, time-consuming and systematic trials may not be feasible. Hence, there is need for AI-generated module to answer these complex issues. AI-based system can help healthcare provider make evidence-based decision, thereby reducing potential of human error. AI Godfather Nobel Prize winner (2024), Professor Geoffrey Hinton has cautioned that AI—superintelligence can affect humanity. Due to lack of understanding about how they function, it can create subgoal with more control, which may be able to persuade and manipulate people to do things that can be harmful [10]. This should be kept in mind on long-term basis, as AI capabilities are moving faster than any technology so far. Hence, one cannot be complacent about AI’s impact on humans. Success will happen by working on safety of AI and not relying too much on AI. Scenario in Low Resource Setting The infrastructure, cost-effectiveness is different in developing countries, but the healthcare concept remains same. The use of AI to offer immediate assistance to clinicians and patients can reduce manual oversight and can give time to staff to look after the human side of medicine. AI can now interpret clinical notes, laboratory results, imaging and real time vitals together to reach diagnosis. Example would be sonologist/radiologist spending time to write/dictate preliminary report, where AI can produce initial report, and consultant can modify or verify report saving time/cost. In smaller town or rural setting, with possibility of AI and telemedicine, one consultant can serve multiple locations effectively. Collection of data in vast, varied country like India is challenging, as Western world data collection may not always be applicable. AI model has been fed with relevant representative information to collect data from multiple regions in many languages. With availability of data and smart phones with basic infrastructure, early diagnosis, triaging care and monitoring can be done with AI as backbone, which could be cheaper than building major hospital in every district [11]. To Conclude AI is hot topic—everyday it appears somewhere in the news media. With increasing trend towards research funding, expectation from AI has escalated with excitement. It is a promising tool in the subject of Obstetrics and Gynaecology with CTG interpretation, foetal physiology, imaging field in USG—MRI, molecular biology in cancer and personalized medicine vision being few examples. AI is not the substitute for medical staff, but it plays role of an assistant in clinical practice. Medical personnel need to remove bias and adapt AI in medical system.

Wang R, Pan W, Jin L, et al. Artificial intelligence in reproductive medicine. Reproduction. 2019;158(4):R139–54. Seval MM, Varli B. Current developments in artificial intelligence from Obstetrics and Gynecology to Urogynecology. Front Med. 2023. https://doi.org/10.3389/fmed.2023.1098205. Emin EI, Emin E, Papalois A, et al. Artificial intelligence in obstetrics and gynaecology: is this the way forward? In Vivo. 2019;33(5):1547–55. Kim HY, Cho GJ, Kwon HS. Applications of artificial intelligence in obstetrics. Ultrasonography. 2022;42(1):2–9. Desai GS. Artificial intelligence: the future of obstetrics and gynecology. J Obstetrics Gynecology India. 2018. https://doi.org/10.1007/s13224-018-1118-4. Malani S, Shrivastava D, Raka MS, et al. A comprehensive review of the role of artificial intelligence in obstetrics and gynecology. Cureus. 2023;15(2):e34891. https://doi.org/10.7759/cureus.34891. Yazdani A, Costa S, Kroon B. Artificial intelligence: friend or foe? ANZJOG Australian New Zealand J Obstetrics Gynaecology. 2023;63(2):127–30. Patel DJ, Chaudhari K, Acharya N, et al. Artificial intelligence in obstetrics and gynecology: transforming care and outcomes. Cureus. 2024. https://doi.org/10.7759/cureus.64725. Einarsson JI. Artificial intelligence in Obstetrics- Gynecology: A revolution on the horizon. Contemporary OB/GYN J: 2023:68 (10) NobelPrize.org: https://www.nobelprize.org › prizes › press-release Vishnu Vardhan, Founder & CEO, SML: Entrepreneur India https://www.entrepreneurindia.com › vishnu Author information Authors and Affiliations Corresponding author Additional information Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Sujata Dalvi, Editor in Chief, MD, DGO, FCPS, FICOG, Hon. Clinical Associate, Nowrosjee Wadia Hospital, Consultant, Glen Eagles, Saifee, Bhatia, St. Elizabeth Hospitals, Ex-Associate Professor, Unit Head, KEM Hospital and Seth GS Medical College. Mumbai. Rights and permissions About this article Cite this article Dalvi, S. Get the Artificial Intelligence (AI) Edge in Obstetrics and Gynaecology. J Obstet Gynecol India 75, 95–100 (2025). https://doi.org/10.1007/s13224-025-02127-3 Received: Accepted: Published: Version of record: Issue date: DOI: https://doi.org/10.1007/s13224-025-02127-3