Automatic structuring of radiology reports with on-premise open-source large language models.

OBJECTIVES: Structured reporting enhances comparability, readability, and content detail. Large language models (LLMs) could convert free text into structured data without disrupting radiologists' reporting workflow. This study evaluated an on-premise, privacy-preserving LLM for automatically structuring free-text radiology reports. MATERIALS AND METHODS: We developed an approach to controlling the LLM output, ensuring the validity and completeness of structured reports produced by a locally hosted Llama-2-70B-chat model. A dataset with de-identified narrative chest radiograph (CXR) reports was compiled retrospectively. It included 202 English reports from a publicly available MIMIC-CXR dataset and 197 German reports from our university hospital. Senior radiologist prepared a detailed, fully structured reporting template with 48 question-answer pairs. All reports were independently structured by the LLM and two human readers. Bayesian inference (Markov chain Monte Carlo sampling) was used to estimate the distributions of Matthews correlation coefficient (MCC), with [-0.05, 0.05] as the region of practical equivalence (ROPE). RESULTS: The LLM generated valid structured reports in all cases, achieving an average MCC of 0.75 (94% HDI: 0.70-0.80) and F1 score of 0.70 (0.70-0.80) for English, and 0.66 (0.62-0.70) and 0.68 (0.64-0.72) for German reports, respectively. The MCC differences between LLM and humans were within ROPE for both languages: 0.01 (-0.05 to 0.07), 0.01 (-0.05 to 0.07) for English, and -0.01 (-0.07 to 0.05), 0.00 (-0.06 to 0.06) for German, indicating approximately comparable performance. CONCLUSION: Locally hosted, open-source LLMs can automatically structure free-text radiology reports with approximately human accuracy. However, the understanding of semantics varied across languages and imaging findings. KEY POINTS: Question Why has structured reporting not been widely adopted in radiology despite clear benefits and how can we improve this? Findings A locally hosted large language model successfully structured narrative reports, showing variation between languages and findings. Critical relevance Structured reporting provides many benefits, but its integration into the clinical routine is limited. Automating the extraction of structured information from radiology reports enables the capture of structured data while allowing the radiologist to maintain their reporting workflow.

Impact of AI on radiology: a EuroAIM/EuSoMII 2024 survey among members of the European Society of Radiology.

In order to assess the perceptions and expectations of the radiology staff about artificial intelligence (AI), we conducted an online survey among ESR members (January-March 2024). It was designed considering that conducted in 2018, updated according to recent advancements and emerging topics, consisting of seven questions regarding demographics and professional background and 28 AI questions. Of 28,000 members contacted, 572 (2%) completed the survey. AI impact was predominantly expected on breast and oncologic imaging, primarily involving CT, mammography, and MRI, and in the detection of abnormalities in asymptomatic subjects. About half of responders did not foresee an impact of AI on job opportunities. For 273/572 respondents (48%), AI-only reports would not be accepted by patients; and 242/572 respondents (42%) think that the use of AI systems will not change the relationship between the radiological team and the patient. According to 255/572 respondents (45%), radiologists will take responsibility for any AI output that may influence clinical decision-making. Of 572 respondents, 274 (48%) are currently using AI, 153 (27%) are not, and 145 (25%) are planning to do so. In conclusion, ESR members declare familiarity with AI technologies, as well as recognition of their potential benefits and challenges. Compared to the 2018 survey, the perception of AI's impact on job opportunities is in general slightly less optimistic (more positive from AI users/researchers), while the radiologist's responsibility for AI outputs is confirmed. The use of large language models is declared not only limited to research, highlighting the need for education in AI and its regulations. CRITICAL RELEVANCE STATEMENT: This study critically evaluates the current impact of AI on radiology, revealing significant usage patterns and clinical implications, thereby guiding future integration strategies to enhance efficiency and patient care in clinical radiology. KEY POINTS: The survey examines ESR member's views about the impact of AI on radiology practice. AI use is relevant in CT and MRI, with varying impacts on job roles. AI tools enhance clinical efficiency but require radiologist oversight for patient acceptance.

A global chromoblastomycosis strategy and development of the global chromoblastomycosis working group.

Chromoblastomycosis, an implantation mycosis, is a neglected tropical disease that causes decreased quality of life, stigma, and disability. The global burden of disease is unknown and data on disease epidemiology and outcomes are severely limited by a lack of access to needed diagnostic tools and therapeutics. The World Health Organization outlined targets for chromoblastomycosis in the Road Map for Neglected Tropical Diseases 2021-2030, but little progress has been made in initiating and implementing an effective control program globally. This lack of guiding policy and progress led to the recent formation of a Global Chromoblastomycosis Working Group which has developed a global chromoblastomycosis strategy. We describe this strategy, which outlines specific steps needed to improve technical progress, strategy and service delivery, and enablers. Clinicians, researchers, public and government officials, patients, and policy makers can align their time, expertise, and resources to improve the lives of communities affected by chromoblastomycosis through this strategy.

Histopathological and immunohistochemical analysis of a suspected extraskeletal osteosarcoma in a rabbit (Oryctolagus cuniculus).

An 8-year-old male rabbit (Oryctolagus cuniculus) presented with a subcutaneous mass in the proximal region of the fourth and accessory digit measuring 5.5 x 3.5 x 5.2cm. The mass was non-alopecic and exhibited irregular surface, ulceration and necrosis with predominantly pale and light brown coloring. Radiography revealed no involvement of bone and adjacent periosteum. The mass was marginally resected and the electrochemotherapy (ECT) was performed on the surgical bed. Histopathology and immunohistochemical analysis revealed positive reactions for Vimentin, Runx-2 and ki-67, leading to a diagnosis of extraskeletal osteosarcoma (ESOS). This report described a case of ESOS in a rabbit, thereby delineating its clinical presentation, anatomopathological characteristics, diagnostic modalities and recommended therapeutic interventions.

Um coelho macho de 8 anos (Oryctolagus cuniculus) apresentava uma massa subcutânea na região proximal do quarto e acessório dígitos medindo 5,5 x 3,5 x 5,2 cm. A massa não era alopécica e exibia superfície irregular, ulceração e necrose com coloração predominantemente pálida e marrom clara. A radiografia não revelou envolvimento de tecido ósseo ou periósteo adjacente. A massa foi submetida à excisão marginal e foi realizada eletroquimioterapia do leito cirúrgico. Histopatologia e análise imuno-histoquímica revelaram reações positivas para vimentina, Runx-2 e ki-67, levando ao diagnóstico de osteossarcoma extraesquelético. Este relato descreve um caso de osteossarcoma extraesquelético em um coelho, delineando sua apresentação clínica, características anatomopatológicas, modalidades diagnósticas e intervenções terapêuticas recomendadas.

Over twenty years of publications in Ecology: Over-contribution of women reveals a new dimension of gender bias.

Biographical features like social and economic status, ethnicity, sexuality, care roles, and gender unfairly disadvantage individuals within academia. Authorship patterns should reflect the social dimension behind the publishing process and co-authorship dynamics. To detect potential gender biases in the authorship of papers and examine the extent of women's contribution in terms of the substantial volume of scientific production in Ecology, we surveyed papers from the top-ranked journal Ecology from 1999 to 2021. We developed a Women's Contribution Index (WCI) to measure gender-based individual contributions. Considering gender, allocation in the author list, and the total number of authors, the WCI calculates the sum of each woman's contribution per paper. We compared the WCI with women's expected contributions in a non-gender-biased scenario. Overall, women account for 30% of authors of Ecology, yet their contribution to papers is higher than expected by chance (i.e., over-contribution). Additionally, by comparing the WCI with an equivalent Men's Contribution Index, we found that women consistently have higher contributions compared to men. We also observed a temporal trend of increasing women's authorship and mixed-gender papers. This suggests some progress in addressing gender bias in the field of ecology. However, we emphasize the need for a better understanding of the pattern of over-contribution, which may partially stem from the phenomenon of over-compensation. In this context, women might need to outperform men to be perceived and evaluated as equals. The WCI provides a valuable tool for quantifying individual contributions and understanding gender biases in academic publishing. Moreover, the index could be customized to suit the specific question of interest. It serves to uncover a previously non-quantified type of bias (over-contribution) that, we argue, is the response to the inequitable structure of the scientific system, leading to differences in the roles of individuals within a scientific publishing team.

Oral Chagas disease outbreak by bacaba juice ingestion: A century after Carlos Chagas' discovery, the disease is still hard to manage.

BACKGROUND: Orally transmitted acute Chagas disease (ACD) primarily affects low-visibility and low-income individuals in tropical and subtropical zones. Managing ACD remains challenging even after more than 100 years of its discovery. Its spread to non-endemic areas has made it a global health issue. The aim of this work is to demonstrate the difficulties encountered in handling a real-life situation. METHODOLOGY AND FINDINGS: This report examines an outbreak of 39 cases of ACD due to oral transmission by bacaba juice ingestion that occurred in Pedro do Rosário, Maranhão, Brazil. A clinical and epidemiological investigation, including an entomological search, was conducted. Diagnosis criteria included positive peripheral blood smear (PBS), seroconversion of IgG, and a two-fold increase in IgG titer (laboratory criteria); and clinical findings, epidemiological exposure, and at least one positive IgG test (clinical-epidemiological criteria). In-house conventional polymerase chain reaction (PCR) was performed on 33 samples. All patients were treated with benznidazole. After 4.5 years, IgG levels were reassessed in 26 individuals. The mean age was 33.6 years, with no gender difference. The mean incubation period was 13.8 days, and the mean between symptom onset and treatment was 16.6 days. The most common symptoms were fever and lymphadenopathy (90%). Diagnostic success rates were 66.6% (laboratory criteria), 23% (clinical-epidemiological criteria), and 10.2% (high clinical suspicion despite negative tests). Test positivity rates were 69.7% (PBS), 91.4% (serology), and 100% (PCR). There were no deaths. Serological cure was achieved in 34.6% of cases, and IgG titers decreased in 15.3%. CONCLUSIONS AND SIGNIFICANCE: We encountered several barriers in managing ACD, including population vulnerability, reliance on outdated diagnostic techniques, lack of standardized molecular biology methods, and limited therapeutic options. This report underscores the importance of rapid surveillance and early treatment to prevent fatalities. We recommend the standardization of conventional PCR in diagnostic routines.

A systematic review and meta-analysis of the prevalence of Parkinson's disease in lower to upper-middle-income countries.

Parkinson's disease (PD) is a common neurodegenerative disease that is a growing public health challenge. Estimates of the burden of PD have focused on data from high-income countries, with lower-income countries poorly described. We reviewed and examined the prevalence of PD reported by studies in low- to upper-middle-income countries. A systematic literature search was performed in the Medline/PubMed, Embase, LILACS, and Web of Science databases. Age group, sex, and geographic region were considered when analyzing the data. Of the 4327 assessed articles, 57 met the inclusion criteria for qualitative review, and 36 were included in the meta-analysis. Heterogeneity measures were high both as a whole and in each geographic region. Data analysis by geographic region showed that reported prevalence differed across regions, ranging from 49 per 100,000 (Sub-Saharan Africa) to 1081 per 100,000 (Latin America and the Caribbean). There was an increasing prevalence of PD with advancing age (per 100,000): 7 in 40-49 years, 158 in 50-59 years, 603 in 60-69 years, 1251 in 70-79 years, and 2181 in over the age of 80. The prevalence of PD in men and women was similar. There was a greater PD prevalence in populations with a higher 5-year GDP per capita and a higher life expectancy. Our findings suggest a higher prevalence of PD in lower and upper-middle-income countries than previously reported. Comparisons between regions are difficult, as the sociocultural differences and lack of methodological standardization hinder understanding key epidemiological data in varied populations.

Susceptibility of Bemisia tabaci Gennadius (Hemiptera: Aleyrodidae) Mediterranean Populations Found in São Paulo, Brazil to 11 Insecticides and Characterization of Their Endosymbionts.

The silverleaf whitefly, Bemisia tabaci Gennadius (Hemiptera: Aleyrodidae), is a significant agricultural pest worldwide, impacting a variety of crop yields. Since the introduction of B. tabaci Mediterranean (MED) species in Brazil, limited research has measured the relative efficacy of the primary insecticides used in whitefly management. This study evaluated the susceptibility of three distinct B. tabaci MED populations to 11 insecticide active ingredients and characterized the bacterial endosymbionts within each population. The insecticides tested were acetamiprid, bifenthrin, cyantraniliprole, diafenthiuron, spiromesifen, imidacloprid, pymetrozine, pyriproxyfen, sulfoxaflor, and thiamethoxam. Results showed varying LC50 and LC90 values among tested insecticides and populations. Notably, populations varied in response to imidacloprid and thiamethoxam with some populations having a 6× higher tolerance. Sequencing data of endosymbionts revealed that individuals from the most susceptible B. tabaci population harbored Rickettsia and Arsenophonus, whereas these bacteria were not detected in the resistant populations. These findings highlight the need for frequent insecticide toxicity bioassays of distinct B. tabaci populations and the adoption of integrated pest management strategies to preserve the efficacy of insecticides for B. tabaci control. Additionally, the role of infection by endosymbionts to alter susceptibility should be further explored.

Enhancing Forensic Diagnostics: Structured Reporting of Post-Mortem CT versus Autopsy for Laryngohyoid Complex Fractures in Strangulation.

BACKGROUND: The purpose of this study was to establish a standardized structured workflow to compare findings from high-resolution, optimized reconstructions from post-mortem computed tomography (pmCT) with autopsy results in the detection of fractures of the laryngohyoid complex in strangulation victims. METHOD: Forty-two strangulation cases were selected, and pmCT scans of the laryngohyoid complex were obtained. Both pmCT scans and autopsy reports were analyzed using a structured template and compared using Cohen's kappa coefficient (κ) and the McNemar test. The study also compared the prevalence of ossa sesamoidea and non-fusion of the major and minor horns of the hyoid bone between both diagnostic methods. RESULTS: The detection of fractures showed a very good correlation between autopsy and pmCT results (κ = 0.905), with the McNemar test showing no statistically significant difference between the two methods. PmCT identified 28 sesamoid bones, 45 non-fusions of the major horns, and 47 non-fusions of the minor horns of the hyoid bone, compared to four, six, and zero, respectively, identified by autopsy (p < 0.0001). CONCLUSIONS: Autopsy and pmCT findings correlate well and can be used in a complementary manner. PmCT is superior to autopsy in identifying dislocations and detecting anatomical variations in the laryngohyoid complex, which can lead to misinterpretations during autopsy. Therefore, we do not advocate replacing autopsy with pmCT but propose using a structured workflow, including our standardized reporting template, for evaluating lesions in the laryngohyoid complex.

Primordial Odontogenic Tumor: A Review of the Literature and Report of Three New Patients.

The primordial odontogenic tumor (POT) is a rare mixed odontogenic tumor composed of mesenchymal cells, columnar odontogenic epithelium, and fibromyxoid stroma affecting the posterior mandible of children and adolescents. Herein, we report 3 patients with POT and the clinicopathological features of POT previously reported in the literature. A 12-year-old, 19-year-old, and 4-year-old patient presented an asymptomatic swelling in the posterior maxilla and posterior mandible. Imaging exams revealed radiolucent lesions associated with unerupted teeth. The lesions were surgically removed, and the histopathological examination revealed spindle-to-ovoid mesenchymal cells in a fibromyxoid stroma surfaced by columnar odontogenic epithelial cells with reverse nuclear polarization. Deposition of mineralized tissue was observed. The final diagnosis was POT, and patients did not exhibit signs of recurrence. POT should be included in the differential diagnoses of intraosseous lesions in the posterior mandible in pediatric patients.

AI-derived body composition parameters as prognostic factors in patients with HCC undergoing TACE in a multicenter study.

Background & Aims: Body composition assessment (BCA) parameters have recently been identified as relevant prognostic factors for patients with hepatocellular carcinoma (HCC). Herein, we aimed to investigate the role of BCA parameters for prognosis prediction in patients with HCC undergoing transarterial chemoembolization (TACE). Methods: This retrospective multicenter study included a total of 754 treatment-naïve patients with HCC who underwent TACE at six tertiary care centers between 2010-2020. Fully automated artificial intelligence-based quantitative 3D volumetry of abdominal cavity tissue composition was performed to assess skeletal muscle volume (SM), total adipose tissue (TAT), intra- and intermuscular adipose tissue, visceral adipose tissue, and subcutaneous adipose tissue (SAT) on pre-intervention computed tomography scans. BCA parameters were normalized to the slice number of the abdominal cavity. We assessed the influence of BCA parameters on median overall survival and performed multivariate analysis including established estimates of survival. Results: Univariate survival analysis revealed that impaired median overall survival was predicted by low SM (p <0.001), high TAT volume (p = 0.013), and high SAT volume (p = 0.006). In multivariate survival analysis, SM remained an independent prognostic factor (p = 0.039), while TAT and SAT volumes no longer showed predictive ability. This predictive role of SM was confirmed in a subgroup analysis of patients with BCLC stage B. Conclusions: SM is an independent prognostic factor for survival prediction. Thus, the integration of SM into novel scoring systems could potentially improve survival prediction and clinical decision-making. Fully automated approaches are needed to foster the implementation of this imaging biomarker into daily routine. Impact and implications: Body composition assessment parameters, especially skeletal muscle volume, have been identified as relevant prognostic factors for many diseases and treatments. In this study, skeletal muscle volume has been identified as an independent prognostic factor for patients with hepatocellular carcinoma undergoing transarterial chemoembolization. Therefore, skeletal muscle volume as a metaparameter could play a role as an opportunistic biomarker in holistic patient assessment and be integrated into decision support systems. Workflow integration with artificial intelligence is essential for automated, quantitative body composition assessment, enabling broad availability in multidisciplinary case discussions.

Staphylococcus spp. as part of the microbiota and as opportunistic pathogen in free-ranging black-tuffed marmosets (Callithrix penicillata) from urban areas: Epidemiology, antimicrobial resistance, and pathology.

BACKGROUND: Marmosets (Callithrix sp.), including black-tuffed marmosets (C. penicillata), are neotropical primates that can be highly adapted to urban environments, especially parks and forested areas near cities. Staphylococcus spp. are part of the microbiota of many different hosts and lead to opportunistic severe infection. Isolates from wild animals can be resistant to antimicrobial drugs. However, there are a few studies that evaluated Staphylococcus spp. in neotropical primates. The goal of this study was to evaluate Staphylococcus spp. isolated from free-ranging black-tuffed marmosets. METHODS: Marmosets were captured in six urban parks. After sedation, skin and rectal swabs and feces were sampled. Staphylococcus spp. isolates were identified by MALDI-ToF and their antimicrobial susceptibility was determined. RESULTS: Over 30% of captured individuals were positive for Staphylococcus spp., and S. aureus was the most isolated species followed by Mammaliicoccus (Staphylococcus) sciuri. With the exception of the marmoset subjected to necropsy, none of the other had lesions, which supports that notion that Staphylococcus spp. are members of the microbiota, but also opportunistic pathogens. Most isolates were susceptible to all antimicrobials tested; however, one isolate of S. epidermidis was resistant to multiple antimicrobials (penicillin, cefoxitin, ciprofloxacin, clindamycin, and erythromycin). We considered S. aureus as the main staphylococci to colonize black-tuffed marmosets. CONCLUSIONS: Black-tuffed marmosets can be colonized by several Staphylococcus species, most frequently by S. aureus, and the majority of isolates were sensible to the antimicrobials tested. One S. epidermidis isolate was considered multidrug resistant.

Microplate-based 3D-printed image box for urea determination in milk by digital image colorimetry.

In this study, we describe a rapid and high-throughput smartphone-based digital colorimetric method for determining urea in milk. A compact and cost-effective 3D-printed image box microplate-based system was designed to measure multiple samples simultaneously, using minimal sample and reagent volumes. The apparatus was applied for the quantification of urea in milk based on its reaction with p-dimethylaminobenzaldehyde (DMAB). The predictive performance of calibration was evaluated using RGB and different colour models (CMYK, HSV, and CIELAB), with the average blue (B) values of the RGB selected as the analytical signal for urea quantification. Under optimized conditions, a urea concentration linear range from 50 to 400 mg L-1 was observed, with a limit of detection (LOD) of 15 mg L-1. The values found with the smartphone-based DIC procedure are in good agreement with spectrophotometric (spectrophotometer and microplate treader) and reference method (mid-infrared spectroscopy) values. This proposed approach offers an accessible and efficient solution for digital image colorimetry, with potential applications for various target analytes in milk and other fields requiring high-throughput colorimetric analysis.

Advancing Global Pose Refinement: A Linear, Parameter-Free Model for Closed Circuits via Quaternion Interpolation.

Global pose refinement is a significant challenge within Simultaneous Localization and Mapping (SLAM) frameworks. For LIDAR-based SLAM systems, pose refinement is integral to correcting drift caused by the successive registration of 3D point clouds collected by the sensor. A divergence between the actual and calculated platform paths characterizes this error. In response to this challenge, we propose a linear, parameter-free model that uses a closed circuit for global trajectory corrections. Our model maps rotations to quaternions and uses Spherical Linear Interpolation (SLERP) for transitions between them. The intervals are established by the constraint set by the Least Squares (LS) method on rotation closure and are proportional to the circuit's size. Translations are globally adjusted in a distinct linear phase. Additionally, we suggest a coarse-to-fine pairwise registration method, integrating Fast Global Registration and Generalized ICP with multiscale sampling and filtering. The proposed approach is tested on three varied datasets of point clouds, including Mobile Laser Scanners and Terrestrial Laser Scanners. These diverse datasets affirm the model's effectiveness in 3D pose estimation, with substantial pose differences and efficient pose optimization in larger circuits.

Influence of the agrochemical benomyl on Cryptococcus gattii-plant interaction in vitro and in vivo.

Cryptococcus gattii, an environmental fungus, is one of the agents of cryptococcosis. The influence of agrochemicals on fungal resistance to antifungals is widely discussed. However, the effects of benomyl (BEN) on fungal interaction with different hosts is still to be understood. Here we studied the influence of adaptation to BEN in the interaction with a plant model, phagocytes and with Tenebrio molitor. First, the strain C. gattii L24/01 non-adapted (NA), adapted (A) to BEN, and adapted with further culture on drug-free media (10p) interact with Nicotiana benthamiana, with a peak in the yeast burden on the 7th day post-inoculation. C. gattii L24/01 A and 10p provided lower fungal burden, but these strains increased cell diameter and capsular thickness after the interaction, together with decreased fungal growth. The strains NA and A showed reduced ergosterol levels, while 10p exhibited increased activity of laccase and urease. L24/01 A recovered from N. benthamiana was less engulfed by murine macrophages, with lower production of reactive oxygen species. This phenotype was accompanied by increased ability of this strain to grow inside macrophages. Otherwise, L24/01 A showed reduced virulence in the T. molitor larvae model. Here, we demonstrate that the exposure to BEN, and interaction with plants interfere in the morphophysiology and virulence of the C. gattii.

Spondylodiscitis: Understanding pathophysiology, surgical strategies, and postoperative management - A single-center study.

Background: Spondylodiscitis (SD) is an inflammatory condition affecting the intervertebral discs and adjacent structures, often leading to serious complications, including epidural abscesses. This study aimed to differentiate postoperative SD from spontaneous cases caused by osteoporotic defects and associated pathologies, evaluating the frequency of SD in spinal diseases at a single center. Materials and Methods: A retrospective observational study involving 25 patients was conducted, analyzing variations between postoperative revisions in SD patients and spontaneous SD due to concurrent pathology and osteoporotic defects. The effects of postoperative wound healing following transforaminal lumbar interbody fusion and decompressive hemilaminectomy with pedicle screws were also investigated. Ethical guidelines were strictly followed during the study, conducted from January 2023 to September 2023 at Moscow City Clinical Hospital No. 68, Demikhova V.P. Results: Among the 25 patients with spontaneous SD, 15 females and 10 males were included, with only two undergoing surgical revision. Predominant purulent inflammatory foci were observed at specific spinal levels, and demographics revealed prevalent comorbidities such as arterial hypertension (80%) and type 2 diabetes mellitus (60%). Postoperative complications included paravertebral abscesses and wound-related issues. Structural observations indicated vertebral destruction, joint gaps, and localized spinal canal narrowing, revealing complexities in SD cases. Conclusion: Surgical intervention remains crucial for addressing SD-related vertebral complications, while antimicrobial therapy tailored to specific pathogens is pivotal. Concurrent conditions necessitate comprehensive management, often involving cardiological interventions. Postoperatively, a combined approach of conservative therapy and calcium phosphate adjuncts is recommended, especially considering the observed low bone density, aiming to optimize patient recovery and spinal stability.

Near-infrared spectroscopy and multivariate analysis as effective, fast, and cost-effective methods to discriminate Candida auris from Candida haemulonii.

Candida auris and Candida haemulonii are two emerging opportunistic pathogens that have caused an increase in clinical cases in the recent years worldwide. The differentiation of some Candida species is highly laborious, difficult, costly, and time-consuming depending on the similarity between the species. Thus, this study aimed to develop a new, faster, and less expensive methodology for differentiating between C. auris and C. haemulonii based on near-infrared (NIR) spectroscopy and multivariate analysis. C. auris CBS10913 and C. haemulonii CH02 were separated in 15 plates per species, and three isolated colonies of each plate were selected for Fourier transform near-infrared (FT-NIR) analysis, totaling 90 spectra. Subsequently, principal component analysis (PCA) and variable selection algorithms, including the successive projections algorithm (SPA) and genetic algorithm (GA) coupled with linear discriminant analysis (LDA), were employed to discern distinctive patterns among the samples. The use of PCA, SPA, and GA algorithms associated with LDA achieved 100% sensitivity and specificity for the discriminations. The SPA-LDA and GA-LDA algorithms were essential in selecting the variables (infrared wavelengths) of most importance for the models, which could be attributed to binding of cell wall structures such as polysaccharides, peptides, proteins, or molecules resulting from yeasts' metabolism. These results show the high potential of combined FT-NIR and multivariate analysis techniques for the classification of Candida-like fungi, which can contribute to faster and more effective diagnosis and treatment of patients affected by these microorganisms.