{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:23:55Z","timestamp":1740097435523,"version":"3.37.3"},"posted":{"date-parts":[[2024,12,6]]},"group-title":"Engineering","reference-count":0,"publisher":"MDPI AG","license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,12,6]]},"abstract":"<jats:p>The diagnosis of kidney diseases presents significant challenges, including the reliance on variable and unstable biomarkers and the necessity for laboratory tests, which is often expensive and complex. Raman spectroscopy emerges as a promising technique for detecting biomarkers of kidney disease, however, its complexity, high cost and limited accessibility outside clinical con-texts complicates its application. Moreover, analyzing Raman spectra, especially from biological fluids like urine, is a challenging and intensive task. In response to these challenges, the devel-opment of a portable, simplified and low-cost Raman system offers a practical solution for analysis of complex biological fluids. The methodology adopted for the system\u2019s development was based on the \u2018Starter Edition\u2019 from the OpenRAMAN website. The study of urine fluorescence was an essential step to determine the appropriate laser wavelength for the acquisition of urine spectra, to minimize fluorescence interference. The system\u2019s optimization involved two stages: adjusting the laser\u2019s operating temperature, by evaluating its emission spectrum under different temperatures with a spectrometer ; and optimizing the acquisition parameters of the software used, through the acquisition of ethanol spectrum to identify the settings that improve spectral quality. The system validation was performed through the acquisition of Raman spectra from five different urine samples, demonstrating its consistency and sensitivity to composition variations in urine samples. Finally, a neural network was designed and trained using methanol and ethanol solutions. The model\u2019s hyperparameters were optimized to maximize its precision and accuracy. This approach explored the model\u2019s potential for classifying Raman spectra.<\/jats:p>","DOI":"10.20944\/preprints202412.0609.v1","type":"posted-content","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T03:53:08Z","timestamp":1733716388000},"source":"Crossref","is-referenced-by-count":0,"title":["Low-Cost Raman Spectroscopy Setup Combined with a Machine Learning Model for Point-of-Care Applications"],"prefix":"10.20944","author":[{"given":"Catarina","family":"Domingos","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9938-0351","authenticated-orcid":false,"given":"Alessandro","family":"Fantoni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0765-474X","authenticated-orcid":false,"given":"Miguel","family":"Fernandes","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Fidalgo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8456-9995","authenticated-orcid":false,"given":"Sofia Azeredo","family":"Pereira","sequence":"additional","affiliation":[]}],"member":"1968","container-title":[],"original-title":[],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T12:14:40Z","timestamp":1738325680000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.preprints.org\/manuscript\/202412.0609\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"references-count":0,"URL":"https:\/\/doi.org\/10.20944\/preprints202412.0609.v1","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.3390\/s25030659","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2024,12,6]]},"subtype":"preprint"}}