Organnect.ai SM is a decision support system for transplant surgeons and administrators. It uses Artificial Intelligence to match patients who need an organ transplant with the most suitable organs. It augments the decision making during pre-transplant assessments, donor-recipient matchmaking, and the post-transplant monitoring of recipients.
Organnect.ai SM uses Deep Learning techniques to “learn” from historical patient transplant data. It can therefore discover trends and patterns in the data and identify the complex interactions among the many variables that impact the outcome of an organ transplant. Then, it uses the acquired knowledge, along with sophisticated Deep Neural Networks, to predict the probability and timing of events such as the death of potential DCD Donors during pre-transplant phase and to predict if and when a transplant will fail after surgery.
Organnect.ai SM offers an interactive user interface. Users can run customized searches for donor-recipient matchmaking. For each possible match, it shows an estimate of how long the organ will last, recipient’s chances of survival, and risk of long term complications. If no suitable matches are available, users can also view the estimated wait times and patient’s chances of survival until the next organ is available. Users can also see similar cases from the past and their outcomes to further inform their decisions. The design is also in compliance with Canadian and international standards including Personal Information Protection and Electronic Documents Act (PIPEDA), Personal Health Information (PCI), Health Insurance Portability and Accountability Act (HIPAA), and Personal Health Information Protection Act (PHIPA).
The complete AI-Powered Transplantation Solution
Artificial Intelligence – Powered Clinical Decision Support System to Increase DCD Donation Rates and Reduce Warm/Cold Ischemic Times and Transplant Costs.
Organnect.ai SM DCD can increase the rate of organ donation by predicting both the probability of death and the time of death after withdrawal of life-sustaining measures. This results in a higher rate of successful donation and more efficient resource planning in transplantation. Predicting the patient’s mortality is a challenging task. The patient’s condition is a result of a complex interaction among medical history, care, and other numerous other factors. The tremendous scope and range of the relevant variables makes interpretation too sophisticated for the human brain. Organnect.ai SM DCD uses deep learning techniques to utilize this data and accurately predict the probability and time of death of each potential donor, providing enough time to the transplant team for matching process and recipient selection. These predictions are interpretable and provided alongside statistical insights presenting their accuracy. Organnect.ai SM DCD has the option to be tailored to match your clinical process and requirements.
Artificial Intelligence – Powered Decision Support System to Optimize Transplant Matchmaking and Graft Functionality/Survival.
The demand and supply gap for organ transplantation continues to grow. Based on 2020 data, only 83% and 90% of deceased and living donor grafts survived over 5 years, which is not different from 2011 figures.
Providing better survival for transplanted organs could intensely improve the present gap.
In addition to supporting healthcare professionals, Organnect.ai SM SMART MATCH aims to assist patients with chronic organ disease during all stages of the illness. This support starts from the day their disease is diagnosed by predicting the course and if/when they would need organ replacement therapy.
Organnect.ai SM SMART MATCH is able to estimate the chance of a successful transplant for any donor-recipient pair, provide customized predictions for each pair, and predict the time and cause of potential graft failure after the organ is transplanted.
Enroll for a Product Demonstration
(Available Now)Publications/Presentations
| Title | Author(s) | Publication | Year | Link |
|---|---|---|---|---|
| Reverse Survival Model (RSM): A Pipeline for Explaining Predictions of Deep Survival Models | Mohammad R Rezaei | Arxiv | 2022 | Link |
| Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecture | Ebrahim Pourjafari | Machine Learning for Healthcare | 2022 |
Conference Presentations/Posters
| Title | Author(s) | Conference Name | Date, City, Country | Link |
|---|---|---|---|---|
| Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecture | Ebrahim Pourjafari | MLHC | Durham, North Carolina, August 2022 | Link |
| Novel Artificial Intelligence Algorithm Using Donor/Recipient Factors Outperforms Existing Methods in Predicting Kidney Transplant Outcome: A Study of 142,971 Transplants from the SRTR | Sana Mohseni | CST | Banff, Canada, Sep 2022 | |
| Deep neural network model to determine and rank the predictors of failure time in kidney transplantation in patients younger than 18 | Orkideh Olang | CST | Banff, Canada, Sep 2022 | |
| Comparison of various scoring systems and mortality prediction models; characteristics, variables, and performances, to be used in our Artificial Intelligence (AI) death prediction model | Ali Shahabinezhad | CCC-F2022 | Toronto, Canada, Nov 23-25 | Link |
| TabNet Classifier: A new Neural Network Model for Identifying Acute Kidney Rejection for Deceased Donors | Nick Sajadi | CCC-F2023 | Toronto, Canada, Nov 23-25 | Link |
| The impact of donor heavy smoking history on their vascular events occurrence and acute rejection of graft after transplant in recipients. | Ebrahim Pourjafari | CCC-F2024 | Toronto, Canada, Nov 23-25 | Link |
| Effects of body mass index on importance of variables for kidney transplant outcomes | Sana Mohseni | CEoT | Arizona , US, Feb 23-25, 2023 | |
| Donor Selection for Kidney Recipients Younger than 14 Years old Using the Reverse Survival Model | Sana Mohseni | CEoT | Arizona , US, Feb 23-25, 2023 | |
| Artificial Intelligence Algorithm Predicts Kidney Transplant Outcome by Using Donor-Recipients Factors: Study of 142,971 Transplant Pairs | Sana Mohseni | ITS | Niagara, Canada, April 30 to May 3, 2023 | |
| Deep neural network model can effectively determine and rank the predictors of failure after kidney transplantation in patients younger than 18 | Orkideh Olang | ITS | Niagara, Canada, April 30 to May 3, 2023 | |
| Enhanced Reliability Of Artificial Intelligence Survival Models To Predict 1-year Survival After Kidney Transplant Using A Novel Combined Model | Sana Mohseni | ATC | San Diego, June 3-7, 2023 | |
| Organ Survival Prediction Of High Risk Recipients Based On Reverse Survival Model | Dr. Shafiee | ATC | San Diego, June 3-7, 2023 | |
| Comparison Of Epts And Pra With An Ai Based Model To Predict Short Term Transplant Survivorship | Orkideh Olang | ATC | San Diego, June 3-7, 2023 |
