Blood TransfusionNCT07875114
Machine Learning for Transfusion Prediction in Oncologic Surgery
An observational study of Blood Transfusion, run by Kocaeli City Hospital at 1 site in Turkey (Türkiye).
Trial summary
This study aims to use artificial intelligence to predict intraoperative bleeding and blood loss in advance for oncologic surgeries with high bleeding risk. The goal is to more accurately determine the type and amount of blood products reserved for patients, improving the efficient use of blood bank resources. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Blood Transfusion
- How many people
- 950 participants
- Where
- 1 siteTurkey (Türkiye)
- Study dates
- 9 Aug 2025to 31 Dec 2026
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Study population: Patients aged over 18 years with ASA physical status I-III who underwent oncologic surgery at a single center between April 3, 2023, and the date of ethics committee approval, identified retrospectively from hospital medical records.
Who may be able to join
- Patients over 18 years of age
- Underwent oncologic surgery
- ASA physical status I-III
Who cannot join
- Underwent emergency surgery
- Hematologic disease
- Pregnancy
- Incomplete data
- Underwent cardiac surgery
Trial locations and contacts
1 site in 1 country.
About this study
Official title: The Role of Artificial Intelligence in Predicting Perioperative Transfusion in Oncologic Surgery
This study aims to use artificial intelligence to predict intraoperative bleeding and blood loss in advance for oncologic surgeries with high bleeding risk. The goal is to more accurately determine the type and amount of blood products reserved for patients, improving the efficient use of blood bank resources.
Read the detailed description
Accurate prediction of perioperative blood transfusion needs is important for resource allocation and for identifying patients at risk of postoperative complications. Oncologic surgeries are among the procedure types associated with a high risk of significant intraoperative bleeding, and blood products are often reserved for these patients before surgery based on clinical judgment. When reserved amounts exceed actual patient need, blood bank resources are used inefficiently.
This single-center, retrospective cohort study will review data from patients aged 18-65 with ASA physical status I-III who underwent oncologic surgery between April 3, 2023 (the date the hospital became operational) and the date of ethics committee approval. Patients undergoing emergency surgery, those with hematologic disease, pregnant patients, patients with incomplete data, and patients undergoing cardiac surgery will be excluded.
Preoperative variables to be collected include age, sex, body mass index, smoking status, comorbidities (hypertension, diabetes, coronary artery disease, other), anticoagulant use, ASA score, type and amount of blood products reserved before surgery, preoperative complete blood count and coagulation parameters, creatinine, albumin, CRP, and erythrocyte sedimentation rate. Intraoperative and postoperative variables will include surgery type and approach (open vs. laparoscopic), anesthesia type, use of regional block, surgical complexity score, operative duration, intraoperative fluid administration, blood loss, urine output, type and amount of blood products transfused (packed red blood cells, fresh frozen plasma, platelet suspension), complications, blood products used within the first 24 postoperative hours, postoperative hemogram parameters, and in-hospital mortality.
Several machine learning algorithms (logistic regression, LASSO, elastic net, ridge regression, support vector machines, random forest, extreme gradient boosting, feed-forward neural network, among others) will be trained and compared to identify the best-performing model. Thirty percent of the collected data will be used for model training and the remaining seventy percent for validation. The primary outcome is the accuracy of the algorithm's prediction of perioperative bleeding volume and required packed red blood cell units compared with actual clinical data. Secondary outcomes include the accuracy of predicted fresh frozen plasma and platelet suspension requirements, and associations with postoperative complications and mortality.
- Conditions
- Blood Transfusion
- Keywords
- Machine learning, Perioperative blood transfusion, Oncologic surgery, Blood product prediction, Patient blood management
What is being measured
The primary outcome is the main question the study is designed to answer.
Prediction of Packed Red Blood Cell (PRBC) Transfusion Requirement Using Artificial Intelligence
In patients undergoing oncologic surgery, the classification performance of an artificial intelligence algorithm-developed using preoperative clinical and laboratory data-in predicting the need for packed red blood cell (PRBC) transfusion (yes/no) will be evaluated against the patient's actual receipt of PRBC transfusion during the perioperative period (from the start of surgery to 24 hours postoperatively). The area under the receiver operating characteristic curve (AUC-ROC) will serve as the primary metric, with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) as supportive metrics.
Measured: Perioperative (from the start of surgery to 24 hours postoperatively)
Secondary outcomes (3)
Prediction of Fresh Frozen Plasma (FFP) Transfusion Requirement Using Artificial Intelligence
In patients undergoing oncologic surgery, the classification performance of an artificial intelligence algorithm-developed using preoperative clinical and laboratory data-in predicting the need for fresh frozen plasma (FFP) transfusion (yes/no) will be evaluated against the patient's actual receipt of FFP transfusion during the perioperative period (from the start of surgery to 24 hours postoperatively). The area under the receiver operating characteristic curve (AUC-ROC) will serve as the primary metric, with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) as supportive metrics.
Measured: Perioperative (from the start of surgery to 24 hours postoperatively)
Comparison of Artificial Intelligence Prediction with Current Clinical Blood Reservation Practice
The predictive performance of the artificial intelligence algorithm for actual blood product (PRBC and FFP) utilization (specificity and positive predictive value) will be compared with the predictive performance of the physician's standard preoperative blood reservation decision for actual utilization, in order to assess the potential of artificial intelligence to reduce unnecessary blood product reservation.
Measured: Perioperative (from the start of surgery to 24 hours postoperatively)
30-Day In-Hospital Mortality
Among all patients enrolled in the study, the incidence of all-cause in-hospital mortality (yes/no) within 30 days after surgery will be assessed, with the date of death recorded.
Measured: 30 days after surgery
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted15 Oct 2026
- Study start9 Aug 2025
- Primary completion1 Dec 2026 (estimated)
- Study completion31 Dec 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Blood TransfusionStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Retrospective
- Enrolment
- 950 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Kocaeli City Hospital
- Sponsor type
- Other government
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07875114
- Sponsor's protocol ID
- KSH_CA_1
- Status last verified
- Oct 2026
- First submitted
- 25 Sep 2026
- Last updated
- 15 Oct 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Study at a glance
From the registry record, last updated by the sponsor on 15 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- The Role of Artificial Intelligence in Predicting Perioperative Transfusion in Oncologic Surgery
- ClinicalTrials.gov ID
- NCT07875114
- Acronym / sponsor ID
- KSH_CA_1
- Conditions
- Blood Transfusion
- Keywords
- Machine learning, Perioperative blood transfusion, Oncologic surgery, Blood product prediction, Patient blood management
- Study type
- Observational
- Recruitment status
- Active, not recruiting
- Enrolment
- 950 participants (estimated)
- Lead sponsor
- Kocaeli City HospitalOther government
- Study start
- 9 Aug 2025 (actual)
- Primary completion
- 1 Dec 2026 (estimated)
- Study completion
- 31 Dec 2026 (estimated)
- First posted
- 15 Oct 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
This study aims to use artificial intelligence to predict intraoperative bleeding and blood loss in advance for oncologic surgeries with high bleeding risk. The goal is to more accurately determine the type and amount of blood products reserved for patients, improving the efficient use of blood bank resources.
Detailed description
Accurate prediction of perioperative blood transfusion needs is important for resource allocation and for identifying patients at risk of postoperative complications. Oncologic surgeries are among the procedure types associated with a high risk of significant intraoperative bleeding, and blood products are often reserved for these patients before surgery based on clinical judgment. When reserved amounts exceed actual patient need, blood bank resources are used inefficiently.
This single-center, retrospective cohort study will review data from patients aged 18-65 with ASA physical status I-III who underwent oncologic surgery between April 3, 2023 (the date the hospital became operational) and the date of ethics committee approval. Patients undergoing emergency surgery, those with hematologic disease, pregnant patients, patients with incomplete data, and patients undergoing cardiac surgery will be excluded.
Preoperative variables to be collected include age, sex, body mass index, smoking status, comorbidities (hypertension, diabetes, coronary artery disease, other), anticoagulant use, ASA score, type and amount of blood products reserved before surgery, preoperative complete blood count and coagulation parameters, creatinine, albumin, CRP, and erythrocyte sedimentation rate. Intraoperative and postoperative variables will include surgery type and approach (open vs. laparoscopic), anesthesia type, use of regional block, surgical complexity score, operative duration, intraoperative fluid administration, blood loss, urine output, type and amount of blood products transfused (packed red blood cells, fresh frozen plasma, platelet suspension), complications, blood products used within the first 24 postoperative hours, postoperative hemogram parameters, and in-hospital mortality.
Several machine learning algorithms (logistic regression, LASSO, elastic net, ridge regression, support vector machines, random forest, extreme gradient boosting, feed-forward neural network, among others) will be trained and compared to identify the best-performing model. Thirty percent of the collected data will be used for model training and the remaining seventy percent for validation. The primary outcome is the accuracy of the algorithm's prediction of perioperative bleeding volume and required packed red blood cell units compared with actual clinical data. Secondary outcomes include the accuracy of predicted fresh frozen plasma and platelet suspension requirements, and associations with postoperative complications and mortality.
Study design
- Observational model
- Cohort
- Time perspective
- Retrospective
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- Patients aged over 18 years with ASA physical status I-III who underwent oncologic surgery at a single center between April 3, 2023, and the date of ethics committee approval, identified retrospectively from hospital medical records.
Key inclusion criteria (3 listed)
- Patients over 18 years of age
- Underwent oncologic surgery
- ASA physical status I-III
Key exclusion criteria (5 listed)
- Underwent emergency surgery
- Hematologic disease
- Pregnancy
- Incomplete data
- Underwent cardiac surgery
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Primary outcome
Prediction of Packed Red Blood Cell (PRBC) Transfusion Requirement Using Artificial Intelligence
Time frame: Perioperative (from the start of surgery to 24 hours postoperatively)
In patients undergoing oncologic surgery, the classification performance of an artificial intelligence algorithm-developed using preoperative clinical and laboratory data-in predicting the need for packed red blood cell (PRBC) transfusion (yes/no) will be evaluated against the patient's actual receipt of PRBC transfusion during the perioperative period (from the start of surgery to 24 hours postoperatively). The area under the receiver operating characteristic curve (AUC-ROC) will serve as the primary metric, with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) as supportive metrics.
3 secondary outcomes
Prediction of Fresh Frozen Plasma (FFP) Transfusion Requirement Using Artificial Intelligence
Time frame: Perioperative (from the start of surgery to 24 hours postoperatively)
Comparison of Artificial Intelligence Prediction with Current Clinical Blood Reservation Practice
Time frame: Perioperative (from the start of surgery to 24 hours postoperatively)
30-Day In-Hospital Mortality
Time frame: 30 days after surgery
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 15 Oct 2026.
- Individual participant dataSharing planned: No
Related trials for Blood Transfusion
RecruitingPhase 3
A Study of Elritercept to Treat Anemia in Adults With Very Low, Low, or Intermediate Risk Myelodysplastic Syndromes (MDS) Who Need Regular Blood Transfusions
Myelodysplastic Syndromes
RecruitingObservational study
The Correlation Between Red Cell Transfusion and Complications of Prematurity
Retinopathy of Prematurity (ROP), Bronchopulmonary Dysplasia (BPD)
Recruiting
Blood Transfusion Strategies During Major Surgery
Perioperative Red Blood Cell Transfusion
RecruitingObservational study
Role of Viscoelastometric Testing in the Development and Validation of a Clinical-biological Score for Predicting Bleeding in Patients With Malignant Haematological Disorders and Severe Thrombocytopenia
Thrombocytopenia, Platelet Transfusion
Active, not recruitingObservational study
Mechanisms of Anaphylaxis
Anaphylaxis, Allergy
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
The record lists no contact. Use the official record to reach the sponsor.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Blood Transfusion, run by Kocaeli City Hospital at 1 site in Turkey (Türkiye).
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 3 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: under way, not looking for participants, as of the sponsor's last update on 15 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Turkey (Türkiye). Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Prediction of Packed Red Blood Cell (PRBC) Transfusion Requirement Using Artificial Intelligence (time frame: Perioperative (from the start of surgery to 24 hours postoperatively)). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 15 Oct 2026.