Attenzione: i dati modificati non sono ancora stati salvati. Per confermare inserimenti o cancellazioni di voci è necessario confermare con il tasto SALVA/INSERISCI in fondo alla pagina
IRIS PubliCatt
Background and aims: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. Approach and results: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). Conclusions: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.
Jenny, L., Max, W., Yasaman, V., Jerome, B., Salvatorre, P., Rachel, O., Leigh, A., Yu, C., Celine, F., Andreas, G., Sven, F., Kristy, W., Dina, T., Pierre, B., Mike, A., Georgios, P., Helena, C., Raluca, P., Jean-Francois, D., Diana Julie, L., Stephen, H., Jeremy, C., Adriaan G, H., Hannele, Y., Javier, C., Mattias, E., Guruprasad P, A., Elisabetta, B., Manuel, R., Richard, T., Morten, K., Carla, Y., Jörn M, S., Detlef, S., Vlad, R., Clifford, B., Kevin, D., Koos, Z., Michael, P., Quentin M, A., Patrick M, B., Anstee, Q. M., Daly, A. K., Govaere, O., Cockell, S., Tiniakos, D., Bedossa, P., Burt, A., Oakley, F., Cordell, H. J., Day, C. P., Wonders, K., Missier, P., Mcteer, M., Vale, L., Oluboyede, Y., Breckons, M., Bossuyt, P. M., Zafarmand, H., Vali, Y., Lee, J., Nieuwdorp, M., Holleboom, A. G., Verheij, J., Ratziu, V., Clément, K., Patino-Navarrete, R., Pais, R., Paradis, V., Schuppan, D., Schattenberg, J. M., Surabattula, R., Myneni, S., Straub, B. K., Vidal-Puig, T., Vacca, M., Rodrigues-Cuenca, S., Allison, M., Kamzolas, I., Petsalaki, E., Campbell, M., Lelliott, C. J., Davies, S., Orešič, M., Hyötyläinen, T., Mcglinchey, A., Mato, J. M., Millet, Ó., Dufour, J., Berzigotti, A., Masoodi, M., Pavlides, M., Harrison, S., Neubauer, S., Cobbold, J., Mozes, F., Akhtar, S., Olodo-Atitebi, S., Banerjee, R., Kelly, M., Shumbayawonda, E., Dennis, A., Andersson, A., Wigley, I., Romero-Gómez, M., Gómez-González, E., Ampuero, J., Castell, J., Gallego-Durán, R., Fernández, I., Montero-Vallejo, R., Karsdal, M., Guldager Kring Rasmussen, D., Leeming, D. J., Sinisi, A., Musa, K., Sandt, E., Tonini, M., Bugianesi, E., Rosso, C., Armandi, A., Marra, F., Gastaldelli, A., Svegliati, G., Boursier, J., Francque, S., Vonghia, L., Driessen, A., Ekstedt, M., Kechagias, S., Yki-Järvinen, H., Porthan, K., Arola, J., Van Mil, S., Papatheodoridis, G., Cortez-Pinto, H., Rodrigues, C. M. P., Valenti, L., Pelusi, S., Petta, S., Pennisi, G., Miele, L., Geier, A., Trautwein, C., Aithal, G. P., Francis, S., Hockings, P., Schneider, M., Newsome, P., Hübscher, S., Wenn, D., Rosenquist, C., Trylesinski, A., Mayo, R., Alonso, C., Duffin, K., Perfield, J. W., Chen, Y., Yunis, C., Tuthill, T., Harrington, M. A., Miller, M., Chen, Y., Mcleod, E. J., Ross, T., Bernardo, B., Schölch, C., Ertle, J., Younes, R., Oldenburger, A., Ostroff, R., Alexander, L., Biegel, H., Skalshøi Kjær, M., Mørch Harder, L., Davidsen, P., Mikkelsen, L. F., Balp, M., Brass, C., Jennings, L., Martic, M., Löffler, J., Applegate, D., Shankar, S., Torstenson, R., Fournier-Poizat, C., Llorca, A., Kalutkiewicz, M., Pepin, K., Ehman, R., Horan, G., Ho, G., Tai, D., Chng, E., Patterson, S. D., Billin, A., Doward, L., Twiss, J., Thakker, P., Landgren, H., Lackner, C., Gouw, A., Hytiroglou, P., Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study, <<HEPATOLOGY>>, 2023; 78 (1): 258-271. [doi:10.1097/HEP.0000000000000364] [https://hdl.handle.net/10807/245055]
Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study
Background and aims: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. Approach and results: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). Conclusions: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.
Jenny, L., Max, W., Yasaman, V., Jerome, B., Salvatorre, P., Rachel, O., Leigh, A., Yu, C., Celine, F., Andreas, G., Sven, F., Kristy, W., Dina, T., Pierre, B., Mike, A., Georgios, P., Helena, C., Raluca, P., Jean-Francois, D., Diana Julie, L., Stephen, H., Jeremy, C., Adriaan G, H., Hannele, Y., Javier, C., Mattias, E., Guruprasad P, A., Elisabetta, B., Manuel, R., Richard, T., Morten, K., Carla, Y., Jörn M, S., Detlef, S., Vlad, R., Clifford, B., Kevin, D., Koos, Z., Michael, P., Quentin M, A., Patrick M, B., Anstee, Q. M., Daly, A. K., Govaere, O., Cockell, S., Tiniakos, D., Bedossa, P., Burt, A., Oakley, F., Cordell, H. J., Day, C. P., Wonders, K., Missier, P., Mcteer, M., Vale, L., Oluboyede, Y., Breckons, M., Bossuyt, P. M., Zafarmand, H., Vali, Y., Lee, J., Nieuwdorp, M., Holleboom, A. G., Verheij, J., Ratziu, V., Clément, K., Patino-Navarrete, R., Pais, R., Paradis, V., Schuppan, D., Schattenberg, J. M., Surabattula, R., Myneni, S., Straub, B. K., Vidal-Puig, T., Vacca, M., Rodrigues-Cuenca, S., Allison, M., Kamzolas, I., Petsalaki, E., Campbell, M., Lelliott, C. J., Davies, S., Orešič, M., Hyötyläinen, T., Mcglinchey, A., Mato, J. M., Millet, Ó., Dufour, J., Berzigotti, A., Masoodi, M., Pavlides, M., Harrison, S., Neubauer, S., Cobbold, J., Mozes, F., Akhtar, S., Olodo-Atitebi, S., Banerjee, R., Kelly, M., Shumbayawonda, E., Dennis, A., Andersson, A., Wigley, I., Romero-Gómez, M., Gómez-González, E., Ampuero, J., Castell, J., Gallego-Durán, R., Fernández, I., Montero-Vallejo, R., Karsdal, M., Guldager Kring Rasmussen, D., Leeming, D. J., Sinisi, A., Musa, K., Sandt, E., Tonini, M., Bugianesi, E., Rosso, C., Armandi, A., Marra, F., Gastaldelli, A., Svegliati, G., Boursier, J., Francque, S., Vonghia, L., Driessen, A., Ekstedt, M., Kechagias, S., Yki-Järvinen, H., Porthan, K., Arola, J., Van Mil, S., Papatheodoridis, G., Cortez-Pinto, H., Rodrigues, C. M. P., Valenti, L., Pelusi, S., Petta, S., Pennisi, G., Miele, L., Geier, A., Trautwein, C., Aithal, G. P., Francis, S., Hockings, P., Schneider, M., Newsome, P., Hübscher, S., Wenn, D., Rosenquist, C., Trylesinski, A., Mayo, R., Alonso, C., Duffin, K., Perfield, J. W., Chen, Y., Yunis, C., Tuthill, T., Harrington, M. A., Miller, M., Chen, Y., Mcleod, E. J., Ross, T., Bernardo, B., Schölch, C., Ertle, J., Younes, R., Oldenburger, A., Ostroff, R., Alexander, L., Biegel, H., Skalshøi Kjær, M., Mørch Harder, L., Davidsen, P., Mikkelsen, L. F., Balp, M., Brass, C., Jennings, L., Martic, M., Löffler, J., Applegate, D., Shankar, S., Torstenson, R., Fournier-Poizat, C., Llorca, A., Kalutkiewicz, M., Pepin, K., Ehman, R., Horan, G., Ho, G., Tai, D., Chng, E., Patterson, S. D., Billin, A., Doward, L., Twiss, J., Thakker, P., Landgren, H., Lackner, C., Gouw, A., Hytiroglou, P., Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study, <<HEPATOLOGY>>, 2023; 78 (1): 258-271. [doi:10.1097/HEP.0000000000000364] [https://hdl.handle.net/10807/245055]
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/245055
Citazioni
0
ND
ND
social impact
Conferma cancellazione
Sei sicuro che questo prodotto debba essere cancellato?
simulazione ASN
Il report seguente simula gli indicatori relativi alla propria produzione scientifica in relazione alle soglie ASN 2021-2023 del proprio SC/SSD. Si ricorda che il superamento dei valori soglia (almeno 2 su 3) è requisito necessario ma non sufficiente al conseguimento dell'abilitazione. La simulazione si basa sui dati IRIS e sugli indicatori bibliometrici alla data indicata e non tiene conto di eventuali periodi di congedo obbligatorio, che in sede di domanda ASN danno diritto a incrementi percentuali dei valori. La simulazione può differire dall'esito di un’eventuale domanda ASN sia per errori di catalogazione e/o dati mancanti in IRIS, sia per la variabilità dei dati bibliometrici nel tempo. Si consideri che Anvur calcola i valori degli indicatori all'ultima data utile per la presentazione delle domande.
La presente simulazione è stata realizzata sulla base delle specifiche raccolte sul tavolo ER del Focus Group IRIS coordinato dall’Università di Modena e Reggio Emilia e delle regole riportate nel DM 589/2018 e allegata Tabella A. Cineca, l’Università di Modena e Reggio Emilia e il Focus Group IRIS non si assumono alcuna responsabilità in merito all’uso che il diretto interessato o terzi faranno della simulazione. Si specifica inoltre che la simulazione contiene calcoli effettuati con dati e algoritmi di pubblico dominio e deve quindi essere considerata come un mero ausilio al calcolo svolgibile manualmente o con strumenti equivalenti.
