1
|
Bambha K, Kim NJ, Sturdevant M, Perkins JD, Kling C, Bakthavatsalam R, Healey P, Dick A, Reyes JD, Biggins SW. Maximizing utility of nondirected living liver donor grafts using machine learning. Front Immunol 2023; 14:1194338. [PMID: 37457719 PMCID: PMC10344453 DOI: 10.3389/fimmu.2023.1194338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2023] [Accepted: 06/13/2023] [Indexed: 07/18/2023] Open
Abstract
Objective There is an unmet need for optimizing hepatic allograft allocation from nondirected living liver donors (ND-LLD). Materials and method Using OPTN living donor liver transplant (LDLT) data (1/1/2000-12/31/2019), we identified 6328 LDLTs (4621 right, 644 left, 1063 left-lateral grafts). Random forest survival models were constructed to predict 10-year graft survival for each of the 3 graft types. Results Donor-to-recipient body surface area ratio was an important predictor in all 3 models. Other predictors in all 3 models were: malignant diagnosis, medical location at LDLT (inpatient/ICU), and moderate ascites. Biliary atresia was important in left and left-lateral graft models. Re-transplant was important in right graft models. C-index for 10-year graft survival predictions for the 3 models were: 0.70 (left-lateral); 0.63 (left); 0.61 (right). Similar C-indices were found for 1-, 3-, and 5-year graft survivals. Comparison of model predictions to actual 10-year graft survivals demonstrated that the predicted upper quartile survival group in each model had significantly better actual 10-year graft survival compared to the lower quartiles (p<0.005). Conclusion When applied in clinical context, our models assist with the identification and stratification of potential recipients for hepatic grafts from ND-LLD based on predicted graft survivals, while accounting for complex donor-recipient interactions. These analyses highlight the unmet need for granular data collection and machine learning modeling to identify potential recipients who have the best predicted transplant outcomes with ND-LLD grafts.
Collapse
Affiliation(s)
- Kiran Bambha
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Washington, Seattle, WA, United States
- Center for Liver Investigation Fostering discovery (C-LIFE), University of Washington, Seattle, WA, United States
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
| | - Nicole J. Kim
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Washington, Seattle, WA, United States
- Center for Liver Investigation Fostering discovery (C-LIFE), University of Washington, Seattle, WA, United States
| | - Mark Sturdevant
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Division of Transplant Surgery, Department of Surgery, University of Washington, Seattle, WA, United States
| | - James D. Perkins
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Division of Transplant Surgery, Department of Surgery, University of Washington, Seattle, WA, United States
| | - Catherine Kling
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Division of Transplant Surgery, Department of Surgery, University of Washington, Seattle, WA, United States
| | - Ramasamy Bakthavatsalam
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Division of Transplant Surgery, Department of Surgery, University of Washington, Seattle, WA, United States
| | - Patrick Healey
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Pediatric Transplant Surgery Division, Department of Surgery, Seattle Children’s Hospital, Seattle, WA, United States
| | - Andre Dick
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Pediatric Transplant Surgery Division, Department of Surgery, Seattle Children’s Hospital, Seattle, WA, United States
| | - Jorge D. Reyes
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
- Division of Transplant Surgery, Department of Surgery, University of Washington, Seattle, WA, United States
- Pediatric Transplant Surgery Division, Department of Surgery, Seattle Children’s Hospital, Seattle, WA, United States
| | - Scott W. Biggins
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Washington, Seattle, WA, United States
- Center for Liver Investigation Fostering discovery (C-LIFE), University of Washington, Seattle, WA, United States
- Clinical and Bio-Analytics Transplant Laboratory (C-BATL), University of Washington, Seattle, WA, United States
| |
Collapse
|
2
|
Bertsimas D, Li M, Zhang N, Estrada C, Scott Wang HH. High-performance pediatric surgical risk calculator: A novel algorithm based on machine learning and pediatric NSQIP data. Am J Surg 2023:S0002-9610(23)00106-X. [PMID: 36948897 DOI: 10.1016/j.amjsurg.2023.03.009] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Revised: 02/09/2023] [Accepted: 03/10/2023] [Indexed: 03/14/2023]
Abstract
BACKGROUNDS New methods such as machine learning could provide accurate predictions with little statistical assumptions. We seek to develop prediction model of pediatric surgical complications based on pediatric National Surgical Quality Improvement Program(NSQIP). METHODS All 2012-2018 pediatric-NSQIP procedures were reviewed. Primary outcome was defined as 30-day post-operative morbidity/mortality. Morbidity was further classified as any, major and minor. Models were developed using 2012-2017 data. 2018 data was used as independent performance evaluation. RESULTS 431,148 patients were included in the 2012-2017 training and 108,604 were included in the 2018 testing set. Our prediction models had high performance in mortality prediction at 0.94 AUC in testing set. Our models outperformed ACS-NSQIP Calculator in all categories for morbidity (0.90 AUC for major, 0.86 AUC for any, 0.69 AUC in minor complications). CONCLUSIONS We developed a high-performing pediatric surgical risk prediction model. This powerful tool could potentially be used to improve the surgical care quality.
Collapse
Affiliation(s)
- Dimitris Bertsimas
- Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Michael Li
- Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Nova Zhang
- Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Carlos Estrada
- Advanced Analytics Group of Pediatric Urology, Department of Urology, Boston Children's Hospital, Boston, MA, USA
| | - Hsin-Hsiao Scott Wang
- Advanced Analytics Group of Pediatric Urology, Department of Urology, Boston Children's Hospital, Boston, MA, USA.
| |
Collapse
|
3
|
Khurana A, Navik U, Allawadhi P, Yadav P, Weiskirchen R. Spotlight on liver macrophages for halting liver disease progression and injury. Expert Opin Ther Targets 2022; 26:707-719. [PMID: 36202756 DOI: 10.1080/14728222.2022.2133699] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/06/2022]
Abstract
INTRODUCTION Over the past two decades, understanding of hepatic macrophage biology has provided astounding details of their role in the progression and regression of liver diseases. The hepatic macrophages constitute resident macrophages, Kupffer cells, and circulating bone marrow monocyte-derived macrophages, which play a diverse role in liver injury and repair. Imbalance in the macrophage population leads to pathological consequences and is responsible for the initiation and progression of acute and chronic liver injuries. Further, distinct populations of hepatic macrophages and their high heterogeneity make their complex role enigmatic. The unique features of distinct phenotypes of macrophages have provided novel biomarkers for defining the stages of liver diseases. The distinct mechanisms of hepatic macrophages polarization and recruitment have been at the fore front of research. In addition, the secretome of hepatic macrophages and their immune regulation has provided clinically relevant therapeutic targets. AREAS COVERED Herein we have highlighted the current understanding in the area of hepatic macrophages, and their role in the progression of liver injury. EXPERT OPINION It is essential to ascertain the physiological and pathological role of evolutionarily conserved distinct macrophage phenotypes in different liver diseases before viable approaches may see a clinical translation.
Collapse
Affiliation(s)
- Amit Khurana
- Institute of Molecular Pathobiochemistry, Experimental Gene Therapy and Clinical Chemistry (IFMPEGKC), RWTH Aachen University Hospital, Pauwelsstr. 30, D-52074, Aachen, Germany
| | - Umashanker Navik
- Department of Pharmacology, Central University of Punjab, Ghudda, Bathinda - 151401, Punjab, India
| | - Prince Allawadhi
- Department of Pharmacy, Vaish Institute of Pharmaceutical Education and Research (VIPER), Pandit Bhagwat Dayal Sharma University of Health Sciences (Pt. B. D. S. UHS), Rohtak - 124001, Haryana, India
| | - Poonam Yadav
- Department of Pharmacology, Central University of Punjab, Ghudda, Bathinda - 151401, Punjab, India
| | - Ralf Weiskirchen
- Institute of Molecular Pathobiochemistry, Experimental Gene Therapy and Clinical Chemistry (IFMPEGKC), RWTH Aachen University Hospital, Pauwelsstr. 30, D-52074, Aachen, Germany
| |
Collapse
|
4
|
Disparities in the Use of Older Donation After Circulatory Death Liver Allografts in the United States Versus the United Kingdom. Transplantation 2022; 106:e358-e367. [PMID: 35642976 DOI: 10.1097/tp.0000000000004185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
BACKGROUND This study aimed to assess the differences between the United States and the United Kingdom in the characteristics and posttransplant survival of patients who received donation after circulatory death (DCD) liver allografts from donors aged >60 y. METHODS Data were collected from the UK Transplant Registry and the United Network for Organ Sharing databases. Cohorts were dichotomized into donor age subgroups (donor >60 y [D >60]; donor ≤60 y [D ≤60]). Study period: January 1, 2001, to December 31, 2015. RESULTS 1157 DCD LTs were performed in the United Kingdom versus 3394 in the United States. Only 13.8% of US DCD donors were aged >50 y, contrary to 44.3% in the United Kingdom. D >60 were 22.6% in the United Kingdom versus 2.4% in the United States. In the United Kingdom, 64.2% of D >60 clustered in 2 metropolitan centers. In the United States, there was marked inter-regional variation. A total of 78.3% of the US DCD allografts were used locally. One- and 5-y unadjusted DCD graft survival was higher in the United Kingdom versus the United States (87.3% versus 81.4%, and 78.0% versus 71.3%, respectively; P < 0.001). One- and 5-y D >60 graft survival was higher in the United Kingdom (87.3% versus 68.1%, and 77.9% versus 51.4%, United Kingdom versus United States, respectively; P < 0.001). In both groups, grafts from donors ≤30 y had the best survival. Survival was similar for donors aged 41 to 50 versus 51 to 60 in both cohorts. CONCLUSIONS Compared with the United Kingdom, older DCD LT utilization remained low in the United States, with worse D >60 survival. Nonetheless, present data indicate similar survivals for older donors aged ≤60, supporting an extension to the current US DCD age cutoff.
Collapse
|
5
|
Khorsandi SE, Hardgrave HJ, Osborn T, Klutts G, Nigh J, Spencer-Cole RT, Kakos CD, Anastasiou I, Mavros MN, Giorgakis E. Artificial Intelligence in Liver Transplantation. Transplant Proc 2021; 53:2939-2944. [PMID: 34740449 DOI: 10.1016/j.transproceed.2021.09.045] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2021] [Accepted: 09/30/2021] [Indexed: 12/12/2022]
Abstract
BACKGROUND Advancements based on artificial intelligence have emerged in all areas of medicine. Many decisions in organ transplantation can now potentially be addressed in a more precise manner with the aid of artificial intelligence. METHOD/RESULTS All elements of liver transplantation consist of a set of input variables and a set of output variables. Artificial intelligence identifies relationships between the input variables; that is, how they select the data groups to train patterns and how they can predict the potential outcomes of the output variables. The most widely used classifiers to address the different aspects of liver transplantation are artificial neural networks, decision tree classifiers, random forest, and naïve Bayes classification models. Artificial intelligence applications are being evaluated in liver transplantation, especially in organ allocation, donor-recipient matching, survival prediction analysis, and transplant oncology. CONCLUSION In the years to come, deep learning-based models will be used by liver transplant experts to support their decisions, especially in areas where securing equitability in the transplant process needs to be optimized.
Collapse
Affiliation(s)
- Shirin Elizabeth Khorsandi
- Institute of Liver Studies, King's College Hospital, Denmark Hill, London, UK; Institute of Hepatology, Foundation for Liver Research, Denmark Hill, London, UK; Faculty of Life Sciences & Medicine, King's College London, Strand, London, UK
| | - Hailey J Hardgrave
- College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Tamara Osborn
- Department of Surgery, University of Arkansas for Medical Sciences Medical Center, Little Rock, Arkansas
| | - Garrett Klutts
- Department of Surgery, University of Arkansas for Medical Sciences Medical Center, Little Rock, Arkansas
| | - Joe Nigh
- Department of Surgery, University of Arkansas for Medical Sciences Medical Center, Little Rock, Arkansas
| | | | - Christos D Kakos
- Surgery Working Group, Society of Junior Doctors, Athens, Greece
| | - Ioannis Anastasiou
- Department of Medicine, University of Arkansas for Medical Sciences Medical Center, Little Rock, Arkansas
| | - Michail N Mavros
- Department of Surgery, University of Arkansas for Medical Sciences Medical Center, Little Rock, Arkansas; Surgical Oncology, University of Arkansas for Medical Sciences Winthrop P. Rockefeller Cancer Institute, Little Rock, Arkansas
| | - Emmanouil Giorgakis
- Department of Surgery, University of Arkansas for Medical Sciences Medical Center, Little Rock, Arkansas; Surgical Oncology, University of Arkansas for Medical Sciences Winthrop P. Rockefeller Cancer Institute, Little Rock, Arkansas.
| |
Collapse
|
6
|
Wiest I, Barreiros AP, Schlitt HJ, Ebert MP, Teufel A. Evaluation und Notwendigkeit einer Anpassung des MELD Scores in der Eurotransplantregion. ZEITSCHRIFT FUR GASTROENTEROLOGIE 2021; 59:991-994. [PMID: 34507377 DOI: 10.1055/a-1484-1544] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
- Isabella Wiest
- II. Medizinische Klinik, Universitätsklinikum Mannheim, Medizinische Fakultät Mannheim, Universität Heidelberg, Mannheim
| | | | - Hans Jürgen Schlitt
- Klinik und Poliklinik für Chirurgie, Universitätsklinikum Regensburg, Regensburg
| | - Matthias Philip Ebert
- II. Medizinische Klinik, Universitätsklinikum Mannheim, Medizinische Fakultät Mannheim, Universität Heidelberg, Mannheim.,Klinische Kooperationseinheit Healthy Metabolism, Zentrum für Präventivmedizin und Digitale Gesundheit Baden-Württemberg, Medizinische Fakultät Mannheim Universität Heidelberg, Mannheim
| | - Andreas Teufel
- Klinische Kooperationseinheit Healthy Metabolism, Zentrum für Präventivmedizin und Digitale Gesundheit Baden-Württemberg, Medizinische Fakultät Mannheim Universität Heidelberg, Mannheim.,II. Medizinische Klinik, Sektion Hepatologie, Universitätsklinikum Mannheim, Medizinische Fakultät Mannheim, Universität Heidelberg, Mannheim
| |
Collapse
|