digitális forradalom cikkbe.jpg

 PROFILE

Dr Bukowski enjoys an international reputation and peer recognition for his research innovation and originality. His findings have been published by the leading general medicine and specialty journals, which recognized several of his manuscripts by accompanying editorials.

 

After receiving his MD with distinction and a PhD in Reproductive Sciences from the Poznan University of Medical Sciences in Poznan, Poland, and the Freie Universität Berlin in Berlin, Germany, he completed residency training in Obstetrics and Gynecology at the Poznan University of Medical Sciences and a second residency at the Eastern Virginia Medical School in Norfolk, Virginia. He received postdoctoral training in Reproductive Endocrinology at the Howard and Georgeanna Jones Institute for Reproductive Medicine, also located in Norfolk, Virginia. He then completed a Fellowship in Maternal-Fetal Medicine and received a Master of Medical Sciences degree at the University of Texas Medical Branch at Galveston.

 

After the completion of his training, Dr Bukowski was appointed Professor at the Department of Obstetrics and Gynecology of the University of Texas Medical Branch at Galveston and then as Professor and Director of the Division of Maternal-Fetal Medicine in the Department of Obstetrics, Gynecology, and Reproductive Sciences at the Yale School of Medicine.

 

Dr Bukowski is considered one of the leading experts in pregnancy research, especially in the fields of preterm birth, fetal growth abnormalities, and individualization of care. He is leading a multidisciplinary group of computer and data scientists at the University of Texas at Austin in collaboration with the Texas Advanced Computing Center and Oden Institute for Computational Engineering and Sciences https://www.tacc.utexas.edu https://oden.utexas.edu/people/directory/Radek-Bukowski

He is a Senior Honorary Visiting Fellow of the Cambridge University, UK.

Radek Bukowski appointed Editor of Computational Medicine for AJOG. Am J Obstet Gynecol. 2020 Jul;223(1):1-2. https://www.ajog.org/article/S0002-9378(20)30390-2/fulltext

The End Of The Average Patient

Over the past few decades, big data, artificial intelligence, and computational science have revolutionized the healthcare industry, changing the way diseases are understood, diagnosed, and treated. Today, clinicians can capitalize on the wealth of available data and computational resources to develop detailed models to predict health status to inform patient care, leading to enhanced outcomes, fewer errors, reduced costs, and stronger clinician-patient relationships. This data and computational model informed care is known as computational medicine.

 

Through the use of computational models and decision-making tools, we are able to answer one of the most important questions in pregnancy, ‘What is the safest delivery method for the individual patient and her baby?’ We enter a variety of risk factors and protective characteristics that are unique to each patient. Our model is able to accurately predict if going into labor or elective cesarean section (C-section) before labor begins would lead to the best possible outcome for both patients, the mother and baby.

Even a few risk factors and protective characteristics create a vast number of combinations unique to that patient. Some of the combinations are more impactful and others less, but there are no two identical individuals. Even identical twins differ in their health. Accounting for this multitude of unique combinations has only recently become possible with the advancements in computing.

 

The Individualized Computational Care Clinic at UT Health Austin provides referral-based consultations to pregnant patients and their providers. Dr. Bukowski visits with the patient and their provider twice during pregnancy, once in the beginning of the pregnancy and once again at the end, three to four weeks before the patient’s due date. For each patient, a unique digital profile is created that can be updated throughout the pregnancy to ensure the best individual prediction as new information arises.

 

The model has been validated in over 16 million pregnancies, showing nearly perfect agreement between the predicted and the observed outcomes. While the prediction and decision making are just a starting point, this knowledge empowers patients to take control of their care and make the individually optimal decision while fully aware of their risks and options.

 

The response from our patients and their providers has been overwhelmingly positive and has widely exceeded our expectations. Pregnancy is complex, and we’ve found that by providing patients with this type of individual information, it allows them to feel more in control and more at ease about their pregnancy and delivery. This work is very near and dear to my heart, and we are excited to be working on subsequent models that we hope to implement soon.