Enhancing breath-based diagnostics through eXplainable Artificial Intelligence

Andrea Lo Sasso, Nicola Amoroso, Domenico Diacono, Marianna La Rocca, Alfonso Monaco, Ester Pantaleo, Sabina Tangaro, Loredana Bellantuono · 2026

Read Enhancing breath-based diagnostics through eXplainable Artificial Intelligence by Andrea Lo Sasso, Nicola Amoroso, Domenico Diacono, Marianna La Rocca, Alfonso Monaco, Ester Pantaleo, Sabina Tangaro, Loredana Bellantuono (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351833.txt.

Description

Andrea Lo Sasso and seven colleagues diagnose disease from breath, and insist the machine show its reasoning. Their 2026 study uses three open datasets of exhaled breath chemistry. Volatile compounds in breath carry traces of the body's metabolic state. Targets included lung cancer, other respiratory diseases, and gut diseases. Artificial intelligence models learned to separate the diagnostic labels. Lopsided class sizes, a chronic problem in medical data, were handled explicitly during training.

The decisive step came after prediction. Explainable AI techniques ranked which compounds drove each model's verdicts. Those drivers were then checked for stability across runs. A breath test will never enter clinics as an unexplained oracle. Doctors need to know which molecules matter, and whether that answer survives retesting. This framework supplies both the prediction and the audit trail, while honestly naming sampling and standardisation as the field's unsolved chores.

Catalog record

CREATORAndrea Lo Sasso, Nicola Amoroso, Domenico Diacono, Marianna La Rocca, Alfonso Monaco, Ester Pantaleo, Sabina Tangaro, Loredana Bellantuono
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE53297
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351833

Browse the full library · About the Tower of Babel