A Neural Network Model Combining [-2]proPSA, freePSA, Total PSA, Cathepsin D, and Thrombospondin-1 Showed Increased Accuracy in the Identification of Clinically Significant Prostate Cancer
BACKGROUND: The Prostate Health Index (PHI) and Proclarix (PCLX) have been proposed as blood-based tests for prostate cancer (PCa). In this study, we evaluated the feasibility of an artificial neural network (ANN)-based approach to develop a combinatorial model including PHI and PCLX biomarkers to recognize clinically significant PCa (csPCa) at initial diagnosis.
METHODS: To this aim, we prospectively enrolled 344 men from two different centres. All patients underwent radical prostatectomy (RP). All men had a prostate-specific antigen (PSA) between 2 and 10 ng/mL. We used an artificial neural network to develop models that can identify csPCa efficiently. As inputs, the model uses [-2]proPSA, freePSA, total PSA, cathepsin D, thrombospondin, and age.
RESULTS: The output of the model is an estimate of the presence of a low or high Gleason score PCa defined at RP. After training on a dataset of up to 220 samples and optimization of the variables, the model achieved values as high as 78% for sensitivity and 62% for specificity for all-cancer detection compared with those of PHI and PCLX alone. For csPCa detection, the model showed 66% (95% CI 66-68%) for sensitivity and 68% (95% CI 66-68%) for specificity. These values were significantly different compared with those of PHI (p < 0.0001 and 0.0001, respectively) and PCLX (p = 0.0003 and 0.0006, respectively) alone.
CONCLUSIONS: Our preliminary study suggests that combining PHI and PCLX biomarkers may help to estimate, with higher accuracy, the presence of csPCa at initial diagnosis, allowing a personalized treatment approach. Further studies training the model on larger datasets are strongly encouraged to support the efficiency of this approach.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:15 |
---|---|
Enthalten in: |
Cancers - 15(2023), 5 vom: 21. Feb. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Gentile, Francesco [VerfasserIn] |
---|
Links: |
---|
Themen: |
Artificial neural network |
---|
Anmerkungen: |
Date Revised 13.03.2023 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3390/cancers15051355 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM354057855 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM354057855 | ||
003 | DE-627 | ||
005 | 20231226061413.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3390/cancers15051355 |2 doi | |
028 | 5 | 2 | |a pubmed24n1180.xml |
035 | |a (DE-627)NLM354057855 | ||
035 | |a (NLM)36900150 | ||
035 | |a (PII)1355 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Gentile, Francesco |e verfasserin |4 aut | |
245 | 1 | 2 | |a A Neural Network Model Combining [-2]proPSA, freePSA, Total PSA, Cathepsin D, and Thrombospondin-1 Showed Increased Accuracy in the Identification of Clinically Significant Prostate Cancer |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 13.03.2023 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a BACKGROUND: The Prostate Health Index (PHI) and Proclarix (PCLX) have been proposed as blood-based tests for prostate cancer (PCa). In this study, we evaluated the feasibility of an artificial neural network (ANN)-based approach to develop a combinatorial model including PHI and PCLX biomarkers to recognize clinically significant PCa (csPCa) at initial diagnosis | ||
520 | |a METHODS: To this aim, we prospectively enrolled 344 men from two different centres. All patients underwent radical prostatectomy (RP). All men had a prostate-specific antigen (PSA) between 2 and 10 ng/mL. We used an artificial neural network to develop models that can identify csPCa efficiently. As inputs, the model uses [-2]proPSA, freePSA, total PSA, cathepsin D, thrombospondin, and age | ||
520 | |a RESULTS: The output of the model is an estimate of the presence of a low or high Gleason score PCa defined at RP. After training on a dataset of up to 220 samples and optimization of the variables, the model achieved values as high as 78% for sensitivity and 62% for specificity for all-cancer detection compared with those of PHI and PCLX alone. For csPCa detection, the model showed 66% (95% CI 66-68%) for sensitivity and 68% (95% CI 66-68%) for specificity. These values were significantly different compared with those of PHI (p < 0.0001 and 0.0001, respectively) and PCLX (p = 0.0003 and 0.0006, respectively) alone | ||
520 | |a CONCLUSIONS: Our preliminary study suggests that combining PHI and PCLX biomarkers may help to estimate, with higher accuracy, the presence of csPCa at initial diagnosis, allowing a personalized treatment approach. Further studies training the model on larger datasets are strongly encouraged to support the efficiency of this approach | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a PCLX | |
650 | 4 | |a Phi | |
650 | 4 | |a artificial neural network | |
650 | 4 | |a prostate cancer | |
650 | 4 | |a tumor markers | |
700 | 1 | |a La Civita, Evelina |e verfasserin |4 aut | |
700 | 1 | |a Ventura, Bartolomeo Della |e verfasserin |4 aut | |
700 | 1 | |a Ferro, Matteo |e verfasserin |4 aut | |
700 | 1 | |a Bruzzese, Dario |e verfasserin |4 aut | |
700 | 1 | |a Crocetto, Felice |e verfasserin |4 aut | |
700 | 1 | |a Tennstedt, Pierre |e verfasserin |4 aut | |
700 | 1 | |a Steuber, Thomas |e verfasserin |4 aut | |
700 | 1 | |a Velotta, Raffaele |e verfasserin |4 aut | |
700 | 1 | |a Terracciano, Daniela |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Cancers |d 2009 |g 15(2023), 5 vom: 21. Feb. |w (DE-627)NLM198667213 |x 2072-6694 |7 nnns |
773 | 1 | 8 | |g volume:15 |g year:2023 |g number:5 |g day:21 |g month:02 |
856 | 4 | 0 | |u http://dx.doi.org/10.3390/cancers15051355 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 15 |j 2023 |e 5 |b 21 |c 02 |