Connect with us

Life

Predicting Fetal Well-being with Deep Learning

AI fetal monitoring using deep learning models for CTG interpretation improves neonatal outcomes and reduces provider burden.

Published

on

AI fetal monitoring

TL;DR:

  • AI models can predict fetal well-being using cardiotocography (CTG) signals.
  • Deep learning methods improve CTG interpretation, reducing false-positive rates.
  • Combining fetal heart rate (FHR) and uterine contractions (UC) data enhances model performance.

The Future of Fetal Monitoring

Imagine a world where artificial intelligence (AI) can accurately predict the well-being of a fetus during pregnancy and labour. This is no longer a dream; it’s a reality. Recent advancements in AI and deep learning are revolutionising the field of fetal monitoring, offering the potential to improve neonatal outcomes and reduce the burden on healthcare providers. In this article, we delve into the groundbreaking work on developing and evaluating machine learning models for cardiotocography (CTG) interpretation.

Understanding Cardiotocography (CTG)

Cardiotocography (CTG) is a crucial technique used during pregnancy and labour to monitor fetal well-being. It involves recording the fetal heart rate (FHR) and uterine contractions (UC) using doppler ultrasound. CTG can be done continuously or intermittently, with sensors placed externally or internally.

Currently, healthcare providers interpret CTG recordings using guidelines from organisations like the National Institute of Child Health and Human Development (NICHD) or the International Federation of Gynecologists and Obstetricians (FIGO). These guidelines define patterns in CTG and FHR traces that may indicate fetal distress.

The Role of AI in Improving CTG Interpretation

Despite its widespread use, CTG interpretation is complex and subjective, leading to high false-positive rates and intra- and inter-observer variability. This is particularly challenging in low-resource settings where access to skilled interpreters is limited.

Enter AI. Recent research has focused on using deep learning methods to improve CTG interpretation. These methods use physiological time series data as input, offering a more comprehensive analysis compared to traditional feature extraction techniques.

Advertisement

Developing and Evaluating Deep Learning Models for CTG

In a recent paper titled “Development and evaluation of deep learning models for cardiotocography interpretation,” researchers developed end-to-end neural network-based models to predict measures of fetal well-being. These models were trained on an open-source CTG dataset, the CTU-UHB Intrapartum Cardiotocography Database, which includes 552 FHR and UC CTG signal pairs.

Model Architecture

The researchers began with the CTG-net network architecture, which convolves the paired FHR and UC input signals temporally before conducting a depthwise convolution to learn the relationship between them. They added several methodological configurations, including architecture and hyperparameter optimization, single input variation, and the addition of clinical metadata.

Pre-processing and Pre-training

To improve data quality, the researchers created a pre-processing pipeline that included inputting missing measurements, random cropping, and additive multiscale noise for data augmentation and downsampling. This generated a large dataset for pre-training and training the models.

Intermittent versus Continuous CTG Use Cases

CTG use comes in two primary formats: intermittent and continuous. In high-resource settings, continuous CTGs are used to monitor fetal heart rate throughout labour. In low-resource settings, intermittent CTGs are often used, covering only about 30 minutes at any point during labour.

The researchers simulated intermittent settings by splitting the 90-minute signals in the dataset into 30-minute signals and training and evaluating the model at different time points. This helped understand how training and evaluating on intermittent time points impacts model performance.

Advertisement

Predicting Objective and Subjective Ground Truth Labels

The researchers used three outcome labels from the dataset:

  • Arterial umbilical cord blood pH: An objective measurement that tracks fetal acidosis, an indication of fetal distress.
  • Apgar score: A subjective measure recorded by a clinician after delivery that reflects the general health of the newborn.
  • Abnormal label: If either Apgar or pH results were abnormal.

Evaluating Model Prediction Robustness

The researchers performed several comparisons to evaluate model performance, including:

  • Performance on the dataset versus the state-of-the-art CTG-net model.
  • Apgar versus pH classification tasks.
  • FHR-only versus FHR+UC.
  • Base model using the last 30 minutes of labour (continuous case) versus intermittent measurements.
  • Base model of FHR+UC versus FHR+UC+Metadata.
  • Subgroup performance of the base model (FHR+UC) with subgroups determined by binarizing clinical metadata.

The results showed that combining FHR+UC achieved the highest model performance for both pH and Apgar classification. The pre-training step enabled the highest model performance, and adding clinical metadata slightly improved model performance for pH but less so for Apgar.

Subgroup Evaluations

The researchers found significant differences in baseline performance between subgroups with frequent and infrequent UC signals gaps for pH prediction and for subgroups with frequent and infrequent FHR signal gaps for Apgar prediction. With metadata, the performance disparities observed with pH prediction were mitigated. However, including metadata increased the AUROC performance disparities for demographic and clinical-related subgroups on this task.

Open CTG Model for Research Use Cases

The researchers are currently exploring open-sourcing their models, hoping that other researchers and stakeholders can build on this work with their own datasets to evaluate it for their clinical use cases.

Limitations and Future Work

The study had limitations that constrain the generalizability of the findings. Future investigations should involve a larger and more diverse dataset sourced from maternity centers worldwide, encompassing varied clinical contexts, demographics, and outcomes. Additionally, further work is needed to understand how such prediction algorithms can be optimally integrated into clinical workflows to improve neonatal outcomes.

The Promise of AI in Fetal Monitoring

The development and evaluation of deep learning models for CTG interpretation hold immense promise for improving fetal monitoring and neonatal outcomes. By leveraging AI, healthcare providers can gain objective interpretation assistance, reducing the burden and potentially improving fetal outcomes.

Advertisement

Comment and Share:

What are your thoughts on the future of AI in fetal monitoring? Do you think AI can revolutionise the field and improve neonatal outcomes? Share your experiences and thoughts in the comments below. Don’t forget to subscribe for updates on AI and AGI developments and join the conversation!

Author


Discover more from AIinASIA

Subscribe to get the latest posts sent to your email.

Continue Reading
Advertisement
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Life

Meet Tesla’s Optimus: The Humanoid Robot That Can Do Anything

Tesla’s Optimus robot showcases the future of humanoid robots, capable of serving, dancing, and taking selfies. Explore its capabilities and the impact of AI in Asia.

Published

on

Tesla Optimus robot

TL;DR:

  • Tesla unveiled Optimus, a versatile humanoid robot, at the ‘We, Robot’ event.
  • Optimus can perform various tasks such as serving drinks, dancing, and taking selfies.
  • The robot’s cost is projected to be between $20,000 and $30,000.
  • Internet users were impressed, with some expressing interest in purchasing the robot.

The Rise of Humanoid Robots in Tech

Imagine a world where robots can serve you drinks, dance with you, and even take selfies. This is no longer a dream; it’s a reality with Tesla’s Optimus robot. At Tesla’s ‘We, Robot’ event in California, several humanoid Optimus robots showcased their remarkable abilities, leaving attendees and internet users amazed.

Optimus: The Multi-Talented Robot

Optimus is not just a robot; it’s a versatile humanoid friend that can perform a variety of tasks. From serving drinks to dancing and taking selfies, Optimus can do it all. Elon Musk, the CEO of Tesla, brought several Optimus robots to the event, demonstrating their capabilities and encouraging attendees to interact with them.

What Can Optimus Do?

  • Serve Drinks: Optimus can serve drinks at the bar, making it a perfect assistant for events and gatherings.
  • Dance: The robot can dance, adding a fun element to any occasion.
  • Take Selfies: Optimus can take selfies, capturing memorable moments with ease.
  • Talk: The robot can engage in conversations, making it a friendly companion.

The Cost of Innovation

Elon Musk revealed that Optimus would cost between $20,000 and $30,000 in the long term. While this may seem steep, the robot’s versatility and capabilities make it a worthwhile investment for many.

Internet Reactions to Optimus

The internet was abuzz with reactions to Optimus. Many users were impressed by the robot’s capabilities and the historical significance of the event. Some users, however, raised eyebrows at Optimus’s interacting skills, questioning whether a human was behind the controls.

User Comments

“When the hand dexterity of Optimus is equal to that of a human being, I would be interested in buying one. Particularly if it can access information on various subjects and learn. I could use the help working on our rental properties and around our place in Arizona.”

“Didn’t it feel like you were in some time travel trip to be there? This event made history for sure.”

“The ones mingling and serving drinks were remotely operated but still really impressive.”

Advertisement

“Is it really Optimus talking? Kinda feeling there’s a human behind it.”

The Future of Humanoid Robots

The unveiling of Optimus marks a significant milestone in the development of humanoid robots. As technology advances, these robots are becoming more capable and versatile, paving the way for a future where they can assist us in various aspects of our lives.

Potential Applications

  • Hospitality: Robots like Optimus can be used in hotels, restaurants, and events to serve guests and enhance their experience.
  • Healthcare: Humanoid robots can assist in hospitals and care homes, providing support to patients and staff.
  • Education: Robots can be used in classrooms to teach and engage students in innovative ways.
  • Home Assistance: Robots can help with household chores, providing assistance to families and the elderly.
  • Tesla’s Optimus robot is a testament to the incredible advancements in AI and AGI. As these technologies continue to evolve, they will transform the way we live and work, opening up new possibilities and opportunities. The future of humanoid robots is bright, and Optimus is just the beginning.

Comment and Share:

What do you think about Tesla’s Optimus robot? Would you consider buying one for your home or business? Share your thoughts and experiences with AI and AGI technologies in the comments below. Don’t forget to subscribe for updates on AI and AGI developments.

Author


Discover more from AIinASIA

Subscribe to get the latest posts sent to your email.

Continue Reading

Life

The Future of AI: Expert Insights and Emerging Trends

Discover the future of AI in Asia with expert insights from Terence Tao, highlighting the opportunities and risks of this transformative technology.

Published

on

AI in Asia

TL;DR:

  • AI Monopoly Concerns: Terence Tao, a renowned mathematician, warns against AI being controlled by a few companies.
  • AI in Elections: Tao’s analysis suggests the Venezuelan election results were likely manipulated.
  • AI Potential and Risks: While AI has transformative potential, it also poses significant risks, including deepfakes and weaponization.

Artificial Intelligence (AI) and Artificial General Intelligence (AGI) are rapidly evolving fields, particularly in Asia. As these technologies advance, they bring both opportunities and challenges. In this article, we delve into the insights of Terence Tao, a Fields Medal-winning mathematician, and explore the implications of AI and AGI for the region.

The Rise of AI in Asia

AI is transforming industries across Asia, from healthcare and finance to education and entertainment. Companies and governments are investing heavily in AI research and development, aiming to harness its potential to drive economic growth and innovation. However, as AI becomes more integrated into our daily lives, concerns about its ethical implications and potential misuse are growing.

Terence Tao on AI and AGI

Terence Tao, a renowned mathematician, has been vocal about the risks and opportunities of AI. In a recent interview, Tao expressed concern about the potential for AI to be controlled by a few powerful companies.

“It’s not good for something as important as AI to be a monopoly held by one or two companies,” Tao said.

Tao believes that open-source AI models and regulation are essential to prevent such a scenario.

AI in Elections: A Case Study

Tao has also applied his mathematical expertise to analyzing election results. In the case of the Venezuelan presidential election, Tao noted that the reported results were highly unusual, with exact percentages that are statistically improbable. “If the reported results were not erroneous or manipulated, then there is only a one in 100 million chance that the observed result of having extremely round percentages would have occurred,” he explained. Tao’s analysis suggests that the results were likely manipulated, highlighting the potential for AI to be used to detect and prevent election fraud.

Advertisement

The Potential and Risks of AI

AI has the potential to revolutionize industries and improve our daily lives. However, it also poses significant risks. Tao noted that AI could be used to create deepfakes, which could influence elections or spread misinformation. Additionally, AI could be used to develop new weapons, raising concerns about its potential for misuse.

Deepfakes and Election Integrity

One of the most pressing concerns about AI is its potential to create deepfakes. Deepfakes are synthetic media in which a person in an existing image or video is replaced with someone else’s likeness. Tao noted that deepfakes could be used to influence elections or spread misinformation, undermining public trust in democratic institutions.

AI and Weaponization

AI could also be used to develop new weapons, raising concerns about its potential for misuse. Tao noted that while AI has the potential to transform industries and improve our daily lives, it also poses significant risks. “It’s theoretically possible [for AI to pose a threat to humanity],” he said. “It’s a very powerful technology.”

The Future of AI in Asia

As AI continues to evolve, it is essential to consider its ethical implications and potential misuse. Governments and companies must work together to develop regulations and standards that ensure AI is used responsibly. Additionally, investment in AI research and development must be balanced with efforts to address its potential risks.

Regulation and Open-Source AI

Tao believes that open-source AI models and regulation are essential to prevent AI from being controlled by a few powerful companies. “There are some open source AI models out there, although they are two or three years behind the big commercial models,” he said. “It’s not good for something as important as AI to be a monopoly controlled by one or two companies.”

Advertisement

Investment in AI Research and Development

Asia is at the forefront of AI research and development, with companies and governments investing heavily in the technology. However, it is essential to balance this investment with efforts to address the potential risks of AI. Tao noted that while AI has the potential to transform industries and improve our daily lives, it also poses significant risks.

Embracing the Future of AI

AI and AGI are rapidly evolving fields with the potential to transform industries and improve our daily lives. However, as these technologies advance, it is essential to consider their ethical implications and potential misuse. Governments and companies must work together to develop regulations and standards that ensure AI is used responsibly. Additionally, investment in AI research and development must be balanced with efforts to address its potential risks. By embracing the future of AI, we can harness its potential to drive economic growth and innovation while mitigating its risks.

Comment and Share:

What do you think about the future of AI in Asia? Share your thoughts and experiences with AI and AGI technologies in the comments below. Don’t forget to subscribe for updates on AI and AGI developments.

Author


Discover more from AIinASIA

Subscribe to get the latest posts sent to your email.

Continue Reading

Life

AI Revolution at Wimbledon: 300 Jobs at Risk as Tradition Fades

AI in Wimbledon: The future of tennis and the impact on jobs.

Published

on

AI in Wimbledon

TL;DR:

  • Wimbledon plans to replace line judges with AI, putting 300 jobs at risk.
  • The decision follows the successful use of Hawk-Eye Live at the 2020 US Open.
  • Experts express concerns about job losses and the human element in tennis.

The AI Revolution at Wimbledon

Wimbledon, one of the world’s most prestigious tennis tournaments, is set to undergo a significant transformation. The All England Club has announced plans to replace line judges with Artificial Intelligence (AI) from next year. This decision has left many staff members devastated, as it puts 300 jobs at risk. The move comes four years after the successful implementation of the Hawk-Eye Live system at the 2020 US Open.

A Tradition Comes to an End

Line judges have been an integral part of Wimbledon since its inception 147 years ago. Their presence on the court has been a symbol of tradition and human involvement in the sport. However, the tide of AI seems unstoppable, and Wimbledon is not immune to its influence.

The Impact on Jobs

The decision to replace line judges with AI has sparked concerns about job losses. Chair umpire Richard Ings, speaking to the Telegraph, described it as a “sad but inevitable day.” He noted that while AI brings gains, it also results in the loss of the human touch. Ings said, “Nothing will hold back the tide of AI. And these technologies create gains for sure, but we also lose something on the human side. Will your job be safe from AI?”

The Human Element in Tennis

Ings also highlighted the emotional impact on line judges, stating that they have had their “love and passion ripped away” following the controversial call. He added, “More than 300 good people and excellent officials – the best of the best working at the pinnacle of the sport – today had their love and passion ripped away.”

John Parry, who umpired eight Wimbledon finals during his career, shared similar sentiments. He said, “It’s just a feeling of sadness because there are quite a nucleus of line judges at the top level who are now out of a job.” Parry also noted that some players, including Roger Federer, valued the human element in the game.

Advertisement

Concerns for Lesser Tournaments

The decision to replace line judges with AI has raised concerns about the future of lesser tennis tournaments. Those hoping to become line judges will no longer have the opportunity to work at a Grand Slam, which could lead to recruitment issues. Andrew Jarrett, a former Wimbledon referee, expressed his worries about the future. He said, “I saw the announcement and it’s inevitable, I think. It’s progress, like it or not. But there’s potentially more of a problem further down the food chain. Small pro events that can’t afford ELC (electronic line-calling) may struggle to source officials who no longer have the incentive of being able to prove their worth for selection to Wimbledon.”

The Lawn Tennis Association’s Response

The Lawn Tennis Association (LTA) has acknowledged the concerns and is working with the Association of British Tennis Officials to develop a new strategy. The aim is to ensure that officials can be retained within the sport. However, the future remains uncertain for many line judges.

The Future of AI in Sports

The decision to replace line judges with AI at Wimbledon is a significant step in the integration of technology into sports. While AI offers many benefits, such as increased accuracy and efficiency, it also raises important questions about the role of humans in the sporting world. As AI continues to advance, it is crucial to consider the impact on jobs and the human element in sports.

The decision to replace line judges with AI at Wimbledon marks a significant shift in the world of tennis. While AI offers many benefits, it also raises important questions about job security and the human element in sports. As AI continues to advance, it is crucial to consider its impact on the sporting world and the people who work within it. The future of AI in sports is uncertain, but one thing is clear: the tide of technology is unstoppable.

Comment and Share:

What are your thoughts on the decision to replace line judges with AI at Wimbledon? Do you think this is a positive step forward for the sport, or are you concerned about the loss of the human touch? Share your opinions in the comments below and subscribe for updates on AI and AGI developments.

Advertisement

Author


Discover more from AIinASIA

Subscribe to get the latest posts sent to your email.

Continue Reading

Trending

Discover more from AIinASIA

Subscribe now to keep reading and get access to the full archive.

Continue reading