Study of machine learning techniques for outcome assessment of leptospirosis patients.

Leptospirosis is a global disease that impacts people worldwide, particularly in humid and tropical regions, and is associated with significant socio-economic deficiencies. Its symptoms are often confused with other syndromes, which can compromise clinical diagnosis and the failure to carry out specific laboratory tests. In this respect, this paper presents a study of three algorithms (Decision Tree, Random Forest and Adaboost) for predicting the outcome (cure or death) of individuals with leptospirosis. Using the records contained in the government National System of Aggressions and Notification (SINAN, in portuguese) from 2007 to 2017, for the state of Pará, Brazil, where the temporal attributes of health care, symptoms (headache, vomiting, jaundice, calf pain) and clinical evolution (renal failure and respiratory changes) were used. In the performance evaluation of the selected models, it was observed that the Random Forest exhibited an accuracy of 90.81% for the training dataset, considering the attributes of experiment 8, and the Decision Tree presented an accuracy of 74.29 for the validation database. So, this result considers the best attributes pointed out by experiment 10: time first symptoms medical attention, time first symptoms ELISA sample collection, medical attention hospital admission time, headache, calf pain, vomiting, jaundice, renal insufficiency, and respiratory alterations. The contribution of this article is the confirmation that artificial intelligence, using the Decision Tree model algorithm, depicting the best choice as the final model to be used in future data for the prediction of human leptospirosis cases, helping in the diagnosis and course of the disease, aiming to avoid the evolution to death.

Leptospira transport medium (LTM): A practical tool for leptospires isolation.

The isolation of Leptospira is challenging, since the bacteria of this genus are susceptible to adverse environmental conditions and may not remain viable for extend periods in urine samples. This study attempted to develop and evaluate a simple and practical method to isolate leptospires from bovine urine samples. A culture medium for sample transport, named Leptospira Transport Medium (LTM), was described and validated using reference serovars of Leptospira spp. in addition to autochthonous strains isolated in Brazil. We evaluated LTM in the field, by collecting 215 urine samples from slaughtered cattle and immediately seeding them in LTM and Fletcher's medium, used as control. The cultures were sent to a laboratory within 10 days for further processing. Moreover, 16S PCR was also performed on the urine samples directly to detect Leptospira DNA. Using LTM enabled 52 isolates (24.2%) to be obtained in pure culture, and contamination was only observed in 15/215 samples (7.0%). Regarding the samples in Fletcher's medium, 10 (4.6%) isolates were obtained. With 16S PCR performed in the urine samples, 31 samples (14.4%) were determined to be positive. LTM was developed and used in a simple and practical way and can significantly improve the isolation of leptospires from urine samples, as well as being highly useful in remote areas, not only in Brazil but also in other countries where few easily accessible laboratories are available. Furthermore, LTM can be prepared by laboratories and provided to veterinarians and technicians for urine collection in the field.

Development of a pooled antigen for use in the macroscopic slide agglutination test (MSAT) to detect Sejroe serogroup exposure in cattle.

This study aimed to develop and evaluate a pooled antigen for use in the macroscopic slide agglutination test (MSAT) to detect cattle positive for the Sejroe serogroup. To this end, 193 bovine serum samples from different Pará State regions (Amazonia) were subjected to a reference microscopic agglutination test (MAT) for the serological diagnosis of leptospirosis using 11 serovars representing the Sejroe serogroup: Hardjo-prajitno; Hardjo-bovis; Sejroe; Wolffi; Guaricura (Bov.G.); Guaricura (M4/98); Ricardi; Gorgas; Recreo; Polonica and Medanensis. The three most prevalent serovars in the MAT were selected for the development of a pooled antigen for use in MSAT; subsequently, the 193 serum were assessed with the macroscopic slide agglutination test (MSAT) containing the developed antigen. The Kappa test was used to determine the general agreement between the MAT and MSAT results. As a result, of the 193 serum samples, 155 (80.3%) were reactive, and 38 (19.7%) were non-reactive in the MAT; Hardjo-prajitno, Wolffi and Medanensis were the three most prevalent serovars. Of the 193 serum samples tested in the MSAT using the developed pooled antigen, 114 were reactive (59.0%), and 79 (41.0%) were non-reactive; the Kappa coefficient was 0.52 (CI 95%, 0.40-0.63), indicating moderate agreement between the two tests. The MSAT with the pooled antigen including the most prevalent serovars detected bovines with the Sejroe serogroup exposure, mainly in animals with high titters in the MAT, and could be used to screen herds suspected of acute infection by this serogroup in Pará State.

Antibodies to Leishmania spp. in domestic felines.

Leishmaniasis is a vector-borne zoonotic disease caused by protozoa in the genus Leishmania, typical of rural and peri-urban environments. The causative agent of American visceral leishmaniasis is Leishmania (Leishmania) infantum chagasi and the main insect vector in Brazil is Lutzomyia longipalpis. Dogs (Canis familiaris) are important in the transmission of the disease, as a reservoir closely related to humans and an infection source for phlebotomine vectors. Since 1990, an increasing number of feline leishmaniasis cases have been reported, suggesting that domestic cats (Felis catus) might be involved in the epidemiology of the disease. The present study analyzed the prevalence of anti-Leishmania spp. antibodies in naturally infected domestic cats from various neighborhoods in the municipality of Belém, Pará, Brazil, using the indirect immunofluorescence assay (IFA) and the direct agglutination test (DAT). Among the 443 samples tested, 18 (4.06%) presented positive reactions in the IFA. The observed titers were 40 IU in 4.97% of the samples and 80 IU in 0.90%. In the DAT test, positive results were found in 25 (5.64%) of the samples. The observed titers were also 40 IU (4.97%) and 80 IU (0.68%). The agreement rate between the two tests was considered low (Kappa coefficient = 0.10).