Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery
Background and Purpose: Tumor recurrence, a characteristic of malignant tumors, is the biggest concern for rectal cancer survivors. The epidemiology of the disease calls for a pressing need to improve healthcare quality and patient outcomes. Prediction models such as Bayesian networks, which can pro...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | Physics and Imaging in Radiation Oncology |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405631622000264 |
| _version_ | 1828333892917002240 |
|---|---|
| author | Biche Osong Carlotta Masciocchi Andrea Damiani Inigo Bermejo Elisa Meldolesi Giuditta Chiloiro Maaike Berbee Seok Ho Lee Andre Dekker Vincenzo Valentini Jean-Pierre Gerard Claus Rödel Krzysztof Bujko Cornelis van de Velde Joakim Folkesson Aldo Sainato Robert Glynne-Jones Samuel Ngan Morten Brændengen David Sebag-Montefiore Johan van Soest |
| author_facet | Biche Osong Carlotta Masciocchi Andrea Damiani Inigo Bermejo Elisa Meldolesi Giuditta Chiloiro Maaike Berbee Seok Ho Lee Andre Dekker Vincenzo Valentini Jean-Pierre Gerard Claus Rödel Krzysztof Bujko Cornelis van de Velde Joakim Folkesson Aldo Sainato Robert Glynne-Jones Samuel Ngan Morten Brændengen David Sebag-Montefiore Johan van Soest |
| author_sort | Biche Osong |
| collection | DOAJ |
| description | Background and Purpose: Tumor recurrence, a characteristic of malignant tumors, is the biggest concern for rectal cancer survivors. The epidemiology of the disease calls for a pressing need to improve healthcare quality and patient outcomes. Prediction models such as Bayesian networks, which can probabilistically reason under uncertainty, could assist caregivers with patient management. However, some concerns are associated with the standard approaches to developing these structures in medicine. Therefore, this study aims to compare Bayesian network structures that stem from these two techniques. Materials and Methods: A retrospective analysis was performed on 6754 locally advanced rectal cancer (LARC) patients enrolled in 14 international clinical trials. Local tumor recurrence at 2, 3, and 5-years was defined as the endpoints of interest. Five rectal cancer treating physicians from three countries elicited the expert structure. The algorithmic structure was inferred from the data with the hill-climbing algorithm. Structural performance was assessed with calibration plots and area under the curve values. Results: The area under the curve for the expert structure on the training and validation data was above 0.9 and 0.8, respectively, for all the time points. However, the algorithmic structure had superior predictive performance over the expert structure for all time points of interest. Conclusion: We have developed and internally validated a Bayesian networks structure from experts’ opinions, which can predict the risk of a LARC patient developing a tumor recurrence at 2, 3, and 5 years. Our result shows that the algorithmic-based structures are more performant and less interpretable than expert-based structures. |
| first_indexed | 2024-04-13T21:26:47Z |
| format | Article |
| id | doaj.art-3c2783db66b2494396a0347753924d73 |
| institution | Directory Open Access Journal |
| issn | 2405-6316 |
| language | English |
| last_indexed | 2024-04-13T21:26:47Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Physics and Imaging in Radiation Oncology |
| spelling | doaj.art-3c2783db66b2494396a0347753924d732022-12-22T02:29:18ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162022-04-012217Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgeryBiche Osong0Carlotta Masciocchi1Andrea Damiani2Inigo Bermejo3Elisa Meldolesi4Giuditta Chiloiro5Maaike Berbee6Seok Ho Lee7Andre Dekker8Vincenzo Valentini9Jean-Pierre Gerard10Claus Rödel11Krzysztof Bujko12Cornelis van de Velde13Joakim Folkesson14Aldo Sainato15Robert Glynne-Jones16Samuel Ngan17Morten Brændengen18David Sebag-Montefiore19Johan van Soest20Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The Netherlands; Corresponding author.Fondazione Policlinico Universitario A. Gemelli IRCCS, Roma, ItaliaUniversita Cattolica del Sacro Cuore, Roma, ItalyDepartment of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The NetherlandsFondazione Policlinico Universitario A. Gemelli IRCCS, Roma, ItaliaFondazione Policlinico Universitario A. Gemelli IRCCS, Roma, ItaliaDepartment of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The NetherlandsDepartment of Radiation Oncology, Gachon University, College of Medicine, Gil Medical Center, Incheon, South KoreaDepartment of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The NetherlandsFondazione Policlinico Universitario A. Gemelli IRCCS, Roma, Italia; Universita Cattolica del Sacro Cuore, Roma, ItalyDepartment of Radiotherapy, Centre Antoine-Lacassagne, Nice, FranceDepartment of Radiotherapy, University of Frankfurt, GermanyDepartment of Radiotherapy I, M. Skłodowska-Curie National Research Institute of Oncology, Warsaw, PolandDepartment of Surgery, Leiden University Medical Center, The NetherlandsDepartment of Surgery, Uppsala University Hospital, Uppsala, SwedenDepartment of Radiotherapy, Pisa University, ItalyDepartment of Radiotherapy, Mount Vernon Cancer Centre, Northwood, United KingdomDepartment of Radiation Oncology, Peter MacCallum Cancer Centre, Melbourne, Victoria, AustraliaDepartment of Oncology, Oslo University Hospital, Oslo, NorwayLeeds Institute of Medical Research, University of Leeds, Leeds, United KingdomDepartment of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The NetherlandsBackground and Purpose: Tumor recurrence, a characteristic of malignant tumors, is the biggest concern for rectal cancer survivors. The epidemiology of the disease calls for a pressing need to improve healthcare quality and patient outcomes. Prediction models such as Bayesian networks, which can probabilistically reason under uncertainty, could assist caregivers with patient management. However, some concerns are associated with the standard approaches to developing these structures in medicine. Therefore, this study aims to compare Bayesian network structures that stem from these two techniques. Materials and Methods: A retrospective analysis was performed on 6754 locally advanced rectal cancer (LARC) patients enrolled in 14 international clinical trials. Local tumor recurrence at 2, 3, and 5-years was defined as the endpoints of interest. Five rectal cancer treating physicians from three countries elicited the expert structure. The algorithmic structure was inferred from the data with the hill-climbing algorithm. Structural performance was assessed with calibration plots and area under the curve values. Results: The area under the curve for the expert structure on the training and validation data was above 0.9 and 0.8, respectively, for all the time points. However, the algorithmic structure had superior predictive performance over the expert structure for all time points of interest. Conclusion: We have developed and internally validated a Bayesian networks structure from experts’ opinions, which can predict the risk of a LARC patient developing a tumor recurrence at 2, 3, and 5 years. Our result shows that the algorithmic-based structures are more performant and less interpretable than expert-based structures.http://www.sciencedirect.com/science/article/pii/S2405631622000264 |
| spellingShingle | Biche Osong Carlotta Masciocchi Andrea Damiani Inigo Bermejo Elisa Meldolesi Giuditta Chiloiro Maaike Berbee Seok Ho Lee Andre Dekker Vincenzo Valentini Jean-Pierre Gerard Claus Rödel Krzysztof Bujko Cornelis van de Velde Joakim Folkesson Aldo Sainato Robert Glynne-Jones Samuel Ngan Morten Brændengen David Sebag-Montefiore Johan van Soest Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery Physics and Imaging in Radiation Oncology |
| title | Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery |
| title_full | Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery |
| title_fullStr | Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery |
| title_full_unstemmed | Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery |
| title_short | Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery |
| title_sort | bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery |
| url | http://www.sciencedirect.com/science/article/pii/S2405631622000264 |
| work_keys_str_mv | AT bicheosong bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT carlottamasciocchi bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT andreadamiani bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT inigobermejo bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT elisameldolesi bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT giudittachiloiro bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT maaikeberbee bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT seokholee bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT andredekker bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT vincenzovalentini bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT jeanpierregerard bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT clausrodel bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT krzysztofbujko bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT cornelisvandevelde bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT joakimfolkesson bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT aldosainato bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT robertglynnejones bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT samuelngan bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT mortenbrændengen bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT davidsebagmontefiore bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery AT johanvansoest bayesiannetworkstructureforpredictinglocaltumorrecurrenceinrectalcancerpatientstreatedwithneoadjuvantchemoradiationfollowedbysurgery |