Prediction of influenza outbreaks in Fuzhou, China: comparative analysis of forecasting models.

BACKGROUND: Influenza is a highly contagious respiratory disease that presents a significant challenge to public health globally. Therefore, effective influenza prediction and prevention are crucial for the timely allocation of resources, the development of vaccine strategies, and the implementation of targeted public health interventions. METHOD: In this study, we utilized historical influenza case data from January 2013 to December 2021 in Fuzhou to develop four regression prediction models: SARIMA, Prophet, Holt-Winters, and XGBoost models. Their predicted performance was assessed by using influenza data from the period from January 2022 to December 2022 in Fuzhou. These models were used for fitting and prediction analysis. The evaluation metrics, including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), were employed to compare the performance of these models. RESULTS: The results indicate that the epidemic of influenza in Fuzhou exhibits a distinct seasonal and cyclical pattern. The influenza cases data displayed a noticeable upward trend and significant fluctuations. In our study, we employed SARIMA, Prophet, Holt-Winters, and XGBoost models to predict influenza outbreaks in Fuzhou. Among these models, the XGBoost model demonstrated the best performance on both the training and test sets, yielding the lowest values for MSE, RMSE, and MAE among the four models. CONCLUSION: The utilization of the XGBoost model significantly enhances the prediction accuracy of influenza in Fuzhou. This study makes a valuable contribution to the field of influenza prediction and provides substantial support for future influenza response efforts.

Human Genetics of Hypoplastic Left Heart Syndrome.

Hypoplastic left heart syndrome (HLHS) is a severe congenital cardiovascular malformation characterized by hypoplasia of the left ventricle, aorta, and other structures on the left side of the heart. The pathologic definition includes atresia or stenosis of both the aortic and mitral valves. Despite considerable progress in clinical and surgical management of HLHS, mortality and morbidity remain concerns. One barrier to progress in HLHS management is poor understanding of its cause. Several lines of evidence point to genetic origins of HLHS. First, some HLHS cases have been associated with cytogenetic abnormalities (e.g., Turner syndrome). Second, studies of family clustering of HLHS and related cardiovascular malformations have determined HLHS is heritable. Third, genomic regions that encode genes influencing the inheritance of HLHS have been identified. Taken together, these diverse studies provide strong evidence for genetic origins of HLHS and related cardiac phenotypes. However, using simple Mendelian inheritance models, identification of single genetic variants that "cause" HLHS has remained elusive, and in most cases, the genetic cause remains unknown. These results suggest that HLHS inheritance is complex rather than simple. The implication of this conclusion is that researchers must move beyond the expectation that a single disease-causing variant can be found. Utilization of complex models to analyze high-throughput genetic data requires careful consideration of study design.

Human Genetics of Tetralogy of Fallot and Double-Outlet Right Ventricle.

Tetralogy of Fallot (TOF) and double-outlet right ventricle (DORV) are conotruncal defects resulting from disturbances of the second heart field and the neural crest, which can occur as isolated malformations or as part of multiorgan syndromes. Their etiology is multifactorial and characterized by overlapping genetic causes. In this chapter, we present the different genetic alterations underlying the two diseases, which range from chromosomal abnormalities like aneuploidies and structural mutations to rare single nucleotide variations affecting distinct genes. For example, mutations in the cardiac transcription factors NKX2-5, GATA4, and HAND2 have been identified in isolated TOF cases, while mutations of TBX5 and 22q11 deletion, leading to haploinsufficiency of TBX1, cause Holt-Oram and DiGeorge syndrome, respectively. Moreover, genes involved in signaling pathways, laterality determination, and epigenetic mechanisms have also been found mutated in TOF and/or DORV patients. Finally, genome-wide association studies identified common single nucleotide polymorphisms associated with the risk for TOF.

Human Genetics of Semilunar Valve and Aortic Arch Anomalies.

Lesions of the semilunar valve and the aortic arch can occur either in isolation or as part of well-described clinical syndromes. The polygenic cause of calcific aortic valve disease will be discussed including the key role of NOTCH1 mutations. In addition, the complex trait of bicuspid aortic valve disease will be outlined, both in sporadic/familial cases and in the context of associated syndromes, such as Alagille, Williams, and Kabuki syndromes. Aortic arch abnormalities particularly coarctation of the aorta and interrupted aortic arch, including their association with syndromes such as Turner and 22q11 deletion, respectively, are also discussed. Finally, the genetic basis of congenital pulmonary valve stenosis is summarized, with particular note to Ras-/mitogen-activated protein kinase (Ras/MAPK) pathway syndromes and other less common associations, such as Holt-Oram syndrome.

Human Genetics of Atrial Septal Defect.

Although atrial septal defects (ASD) can be subdivided based on their anatomical location, an essential aspect of human genetics and genetic counseling is distinguishing between isolated and familiar cases without extracardiac features and syndromic cases with the co-occurrence of extracardiac abnormalities, such as developmental delay. Isolated or familial cases tend to show genetic alterations in genes related to important cardiac transcription factors and genes encoding for sarcomeric proteins. By contrast, the spectrum of genes with genetic alterations observed in syndromic cases is diverse. Currently, it points to different pathways and gene networks relevant to the dysregulation of cardiomyogenesis and ASD pathogenesis. Therefore, this chapter reflects the current knowledge and highlights stable associations observed in human genetics studies. It gives an overview of the different types of genetic alterations in these subtypes, including common associations based on genome-wide association studies (GWAS), and it highlights the most frequently observed syndromes associated with ASD pathogenesis.

Human Genetics of Ventricular Septal Defect.

Ventricular septal defects (VSDs) are recognized as one of the commonest congenital heart diseases (CHD), accounting for up to 40% of all cardiac malformations, and occur as isolated CHDs as well as together with other cardiac and extracardiac congenital malformations in individual patients and families. The genetic etiology of VSD is complex and extraordinarily heterogeneous. Chromosomal abnormalities such as aneuploidy and structural variations as well as rare point mutations in various genes have been reported to be associated with this cardiac defect. This includes both well-defined syndromes with known genetic cause (e.g., DiGeorge syndrome and Holt-Oram syndrome) and so far undefined syndromic forms characterized by unspecific symptoms. Mutations in genes encoding cardiac transcription factors (e.g., NKX2-5 and GATA4) and signaling molecules (e.g., CFC1) have been most frequently found in VSD cases. Moreover, new high-resolution methods such as comparative genomic hybridization enabled the discovery of a high number of different copy number variations, leading to gain or loss of chromosomal regions often containing multiple genes, in patients with VSD. In this chapter, we will describe the broad genetic heterogeneity observed in VSD patients considering recent advances in this field.

Prediction of volatility and seasonality vegetation by using the GARCH and Holt-Winters models.

Seasonality and volatility of vegetation in the ecosystem are associated with climatic sensitivity, which can have severe consequences for the environment as well as on the social and economic well-being of the nation. Monitoring and forecasting vegetation growth patterns in ecosystems significantly rely on remotely sensed vegetation indices, such as Normalized Difference Vegetation Index (NDVI). A novel integration of the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and the Holt-Winters (H-W) models was used to simulate the seasonality and volatility of the three different agro-climatic zones in Jharkhand, India: the central north-eastern, eastern, and south-eastern agro-climatic zones. MODIS Terra Vegetation Indices NDVI data MOD13Q1, from 2001 to 2021, was used to create NDVI time series volatility and seasonality modeled by the GARCH and the H-W models, respectively. GARCH-based Exponential GARCH (EGARCH) [1,1] and Standard GARCH (SGARCH) [1,1] models were used to check the volatility of vegetation growth in three different agro-climatic zones of Jharkhand. The SGARCH [1,1] and EGARCH [1,1] models for the western agro-climatic zone experienced the best indicator as it has maximum likelihood and minimal Schwarz-Bayesian criterion and Akaike information criterion. The seasonality results showed that the additive H-W model showed better results in the eastern agro-climatic zone with the optimized values of MAE (16.49), MAPE (0.49), NSE (0.86), RMSE (0.49), and R2 (0.82) followed by the south-eastern and central north-eastern agro-climatic zones. By utilizing the H-W and GARCH models, the finding demonstrates that vegetation orientation and monitoring seasonality can be predicted using NDVI.

Comparison of SARIMA model, Holt-winters model and ETS model in predicting the incidence of foodborne disease.

BACKGROUND: According to the World Health Organization, foodborne disease is a significant public health issue. We will choose the best model to predict foodborne disease by comparison, to provide evidence for government policies to prevent foodborne illness. METHODS: The foodborne disease monthly incidence data from June 2017 to April 2022 were obtained from the Chongqing Nan'an District Center for Disease Prevention and Control. Data from June 2017 to June 2021 were used to train the model, and the last 10 months of incidence were used for prediction and validation The incidence was fitted using the seasonal autoregressive integrated moving average (SARIMA) model, Holt-Winters model and Exponential Smoothing (ETS) model. Besides, we used MSE, MAE, RMSE to determine which model fits better. RESULTS: During June 2017 to April 2022, the incidence of foodborne disease showed seasonal changes, the months with the highest incidence are June to November. The optimal model of SARIMA is SARIMA (1,0,0) (1,1,0)12. The MSE, MAE, RMSE of the Holt-Winters model are 8.78, 2.33 and 2.96 respectively, which less than those of the SARIMA and ETS model, and its prediction curve is closer to the true value. The optimal model has good predictive performance. CONCLUSION: Based on the results, Holt-Winters model produces better prediction accuracy of the model.

Identification of a novel TBX5 c.755 + 1 G > A variant and related pathogenesis in a family with Holt-Oram syndrome.

The proband with congenital heart disease and abnormal thumb was clinically diagnosed as Holt-Oram syndrome (HOS). A novel variant, T-box transcription factor 5 (TBX5) c.755 + 1 G > A, was identified in the proband via whole exome sequencing and validated using Sanger sequencing. Pedigree analysis and clinical examinations revealed three/seven individuals over three generations within the family, with features suggestive of HOS. Deep amplicon sequencing confirmed that the allele frequencies of the novel variant in the proband (III-1), her brother (III-2), and her mother (II-2) were 50%, 48.3%, and 38.1%, respectively, indicating that III-1 and III-2 harbored heterozygous variants, while II-2 harbored mosaic heterozygous variants. The minigene splicing assay showed that the novel variant affected the normal splicing of exon 7, resulting in the production of abnormal TBX5 transcripts. Reverse transcription-quantitative polymerase chain reaction and western blot analyses revealed that the novel variant upregulated TBX5 expression at the transcriptional and translational levels. Nuclear localization assay demonstrated impaired nuclear localization of the mutant TBX5. Cell viability assay revealed the inhibition of cell activity by the mutant TBX5. Our findings indicate that the novel variant was potentially induced HOS, probably by causing aberrant splicing, reducing the enrichment of nuclear TBX5 protein, and inhibiting cellular proliferation.

Square root identities for harvested Beverton-Holt models.

We introduce the term net-proliferation rate for a class of harvested single species models, where harvest is assumed to reduce the survival probability of individuals. Following the classical maximum sustainable yield calculations, we establish relations between the proliferation and net-proliferation that are economically and sustainably favored. The resulting square root identities are analytically derived for species following the Beverton-Holt recurrence considering three levels of complexity. To discuss the generalization of the results, we compare the square root result to the optimal survival rate of the Pella-Tomlinson model. Furthermore, to test the practical relevance of the square root identities, we fit a stochastic Pella-Tomlinson model to observed Barramundi fishery data from the Southern Gulf of Carpentaria, Australia. The results show that for the estimated model parameters, the equilibrium biomass levels resulting from the MSY harvest and the square root harvest are similar, supporting the claim that the square root harvest can serve as a rule-of-thumb. This application, with its inherited model uncertainty, sparks a risk sensitivity analysis regarding the probability of populations falling below an unsustainable threshold. Characterization of such sensitivity helps in the understanding of both dangers of overfishing and potential remedies.

Prediction of congenital heart disease for newborns: comparative analysis of Holt-Winters exponential smoothing and autoregressive integrated moving average models.

OBJECTIVE: To describe the temporal trend of the number of new congenital heart disease (CHD) cases among newborns in Jinhua from 2019 to 2020 and explored an appropriate model to fit and forecast the tendency of CHD. METHODS: Data on CHD from 2019 to 2020 was collected from a health information system. We counted the number of newborns with CHD weekly and separately used the additive Holt-Winters ES method and ARIMA model to fit and predict the number of CHD for newborns in Jinhua. By comparing the mean square error, rooted mean square error and mean absolute percentage error of each approach, we evaluated the effects of different approaches for predicting the number of CHD in newborns. RESULTS: A total of 1135 newborns, including 601 baby girls and 534 baby boys, were admitted for CHD from HIS in Jinhua during the 2-year study period. The prevalence of CHD among newborns in Jinhua in 2019 was 0.96%. Atrial septal defect was diagnosed the most frequently among all newborns with CHD. The number of CHD cases among newborns remained stable in 2019 and 2020. There were fewer cases in spring and summer, while cases peaked in November and December. The ARIMA(2,1,1) model relatively offered advantages over the additive Holt-winters ES method in predicting the number of newborns with CHD, while the accuracy of ARIMA(2,1,1) was not very ideal. CONCLUSIONS: The diagnosis of CHD is related to many risk factors, therefore, when using temporal models to fit and predict the data, we must consider such factors' influence and try to incorporate them into the models.

What Was Known About Childhood Diabetes Mellitus Before the Discovery of Insulin?

It has been widely reported by historians that physicians were aware of two distinct types of diabetes mellitus by the 1880s, and that these were both similar to and the direct forerunners of type 1, juvenile-onset and type 2, adult-onset diabetes. The writings of prominent specialist physicians practicing just prior to the discovery of insulin in 1921-1922 were reviewed and there is little evidence that experts believed that adult and childhood diabetes were different. In fact, more than a decade passed after the discovery of insulin before diabetes in children and adults even began to be distinguished. Childhood diabetes was exceedingly rare in the early 20th century and diabetes was believed to be primarily a chronic disease of adults. It is interesting to speculate about what might have happened if the first pancreatic extract tests had been performed on adult-onset diabetics with insulin-resistant diabetes mellitus. Clearly, the results would have been disappointing and the discovery of insulin delayed. This essay explores how the test subject decision was made. It is fortuitous that a 14 year old boy with what was unequivocally type 1 diabetes was selected to be the first insulin recipient, and the rest is history.

Combined clinic and home-based therapeutic approach for the treatment of bilateral radial deficiency for a young child with Holt-Oram syndrome: A case report.

BACKGROUND: Holt-Oram syndrome (HOS) is a rare, genetic condition characterized by the combination of congenital heart defect and hypoplasia in one or both upper extremities. Children with HOS commonly present with varied joint and limb involvement including radial longitudinal deficiency impacting hand function. Evidence-based guidelines regarding orthotic wear and therapeutic techniques are lacking. PURPOSE: The aim of this case report was to present the results of a long-term occupational therapy program for a patient with HOS pre and postpollicization. STUDY DESIGN: Case report. METHODS: A 4-month-old patient with bilateral radial longitudinal deficiencies began outpatient occupational therapy for custom orthosis fabrication and treatment which included long term clinic and home-based intervention. Techniques included passive range of motion, orthosis wear, therapeutic taping, and modified constraint induced movement therapy. Longitudinal assessment of musculoskeletal alignment and functional hand use was performed using goniometry for passive and active range of motion, the Assisting Hand Assessment (AHA), and The Thumb Grasp and Pinch Assessment (T-GAP). RESULTS: Improvement in passive and active range of motion was achieved as well as improved activity level function as measured by the AHA and T-GAP postpollicization and intervention. CONCLUSIONS: A combined clinic and home-based therapeutic approach can be effective for children with HOS to improve alignment and function pre and postpollicization to further enhance hand function. Comprehensive, long-term assessment is necessary to fully evaluate and communicate improvement.

Functional analysis of two novel TBX5 variants present in individuals with Holt-Oram syndrome with different clinical manifestations.

Holt-Oram syndrome (HOS) is a rare disorder characterized by cardiac and upper-limb defects. Pathogenic variants in TBX5-a gene encoding a transcription factor important for heart and skeletal development-are the only known cause of HOS. Here, we present the identification and functional analysis of two novel TBX5 pathogenic variants found in two individuals with HOS presenting distinct phenotypes. The individual with the c.905delA variant has a severe cardiac phenotype but mild skeletal defects, unlike the individual with the c.246_249delGATG variant who has no cardiac problems but severe upper limbs malformations, including phocomelia. Both frameshift variants, c.246_249delGATG and c.905delA, generate mRNAs harbouring premature stop codons which, if not degraded by nonsense mediated decay, will lead to the production of shorter TBX5 proteins, p.Gln302Argfs*92 and p.Met83Phefs*6, respectively. Immunocytochemistry results suggest that both mutated proteins are produced and furthermore, like the wild-type protein, p.Gln302Argfs*92 mutant appears to be mainly localized in the nucleus, in contrast with p.Met83Phefs*6 mutant that displays a higher level of cytoplasmic localization. In addition, luciferase activity analysis revealed that none of the TBX5 mutants are capable of transactivating the NPPA promoter. In conclusion, our results provide evidence that both pathogenic variants cause a severe TBX5 loss-of-function, dramatically reducing its biological activity. The absence of cardiac problems in the individual with the p.Met83Phefs*6 variant supports the existence of other mechanisms/genes underlying the pathogenesis of HOS and/or the existence of an age-related delay in the development of a more serious cardiac phenotype. Further studies are required to understand the differential effects observed in the phenotypes of both individuals.

Quantifying the nature and strength of intraspecific density dependence in Arctic mosquitoes.

Processes that change with density are inherent in all populations, yet quantifying density dependence with empirical data remains a challenge. This is especially true for animals recruiting in patchy landscapes because heterogeneity in habitat quality in combination with habitat choice can obscure patterns expected from density dependence. Mosquitoes (Diptera: Culicidae) typically experience strong density dependence when larvae compete for food, however, effects vary across species and contexts. If populations experience intense intraspecific density-dependent mortality then overcompensation can occur, where the number of survivors declines at high densities producing complex endogenous dynamics. To seek generalizations about density dependence in a widespread species of Arctic mosquito, Aedes nigripes, we combined a laboratory experiment, field observations, and modeling approaches. We evaluated alternative formulations of discrete population models and compared best-performing models from our lab study to larval densities from ponds in western Greenland. Survivorship curves from the lab were the best fit by a Hassell model with compensating density dependence (equivalent to a Beverton-Holt model) where peak recruitment ranged from 8 to 80 mosquitoes per liter depending on resource supply. In contrast, our field data did not show a signal of strong density dependence, suggesting that other processes such as predation may lower realized densities in nature, and that expected patterns may be obscured because larval abundance covaries with resources (cryptic density dependence). Our study emphasizes the importance of covariation between the environment, habitat choice, and density dependence in understanding population dynamics across landscapes, and demonstrates the value of pairing lab and field studies.

miR-182-5p is an evolutionarily conserved Tbx5 effector that impacts cardiac development and electrical activity in zebrafish.

To dissect the TBX5 regulatory circuit, we focused on microRNAs (miRNAs) that collectively contribute to make TBX5 a pivotal cardiac regulator. We profiled miRNAs in hearts isolated from wild-type, CRE, Tbx5lox/+and Tbx5del/+ mice using a Next Generation Sequencing (NGS) approach. TBX5 deficiency in cardiomyocytes increased the expression of the miR-183 cluster family that is controlled by Kruppel-like factor 4, a transcription factor repressed by TBX5. MiR-182-5p, the most highly expressed miRNA of this family, was functionally analyzed in zebrafish. Transient overexpression of miR-182-5p affected heart morphology, calcium handling and the onset of arrhythmias as detected by ECG tracings. Accordingly, several calcium channel proteins identified as putative miR-182-5p targets were downregulated in miR-182-5p overexpressing hearts. In stable zebrafish transgenic lines, we demonstrated that selective miRNA-182-5p upregulation contributes to arrhythmias. Moreover, cardiac-specific down-regulation of miR-182-5p rescued cardiac defects in a zebrafish model of Holt-Oram syndrome. In conclusion, miR-182-5p exerts an evolutionarily conserved role as a TBX5 effector in the onset of cardiac propensity for arrhythmia, and constitutes a relevant target for mediating the relationship between TBX5, arrhythmia and heart development.

An alternative delayed population growth difference equation model.

We propose an alternative delayed population growth difference equation model based on a modification of the Beverton-Holt recurrence, assuming a delay only in the growth contribution that takes into account that those individuals that die during the delay, do not contribute to growth. The model introduced differs from a delayed logistic difference equation, known as the delayed Pielou or delayed Beverton-Holt model, that was formulated as a discretization of the Hutchinson model. The analysis of our delayed difference equation model identifies a critical delay threshold. If the time delay exceeds this threshold, the model predicts that the population will go extinct for all non-negative initial conditions. If the delay is below this threshold, the population survives and its size converges to a positive globally asymptotically stable equilibrium that is decreasing in size as the delay increases. We show global asymptotic stability of the positive equilibrium using two different techniques. For one set of parameter values, a contraction mapping result is applied, while the proof for the remaining set of parameter values, relies on showing that the map is eventually componentwise monotone.

Characterization of Temperature Gradients According to Height in a Baroque Church by Means of Wireless Sensors.

The baroque church of Saint Thomas and Saint Philip Neri (Valencia, Spain), which was built between 1727 and 1736, contains valuable paintings by renowned Spanish artists. Due to the considerable height of the central nave, the church can experience vertical temperature gradients. In order to investigate this issue, temperatures were recorded between August 2017 and February 2018 from a wireless monitoring system composed of 21 sensor nodes, which were located at different heights in the church from 2 to 13 m from the floor level. For characterizing the temperature at high, medium and low altitude heights, a novel methodology is proposed based on sparse Partial Least Squares regression (sPLS), Linear Discriminant Analysis (LDA), and the Holt-Winters method, among others, which were applied to a time series of temperature. This approach is helpful to discriminate temperature profiles according to sensor height. Once the vertical thermal gradients for each month were characterized, it was found that temperature reached the maximum correlation with sensor height in the period between August 10th and September 9th. Furthermore, the most important features from the time series that explain this correlation are the mean temperature and the mean of moving range. In the period mentioned, the vertical thermal gradient was estimated to be about 0.043 ∘C/m, which implies a difference of 0.47 ∘C on average between sensor nodes at 2 m from the floor with respect to the upper ones located at 13 m from the floor level. The gradient was estimated as the slope from a linear regression model using height and hourly mean temperature as the predictor and response, respectively. This gradient is consistent with similar reported studies. The fact that such gradient was only found in one month suggests that the mechanisms of dust deposition on walls involved in vertical thermal gradients are not important in this case regarding the preventive conservation of artworks. Furthermore, the methodology proposed here was useful to discriminate the time series at high, medium and low altitude levels. This approach can be useful when a set of sensors is installed for microclimate monitoring in churches, cathedrals, and other historical buildings, at different levels and positions.

A Methodology for Discriminant Time Series Analysis Applied to Microclimate Monitoring of Fresco Paintings.

The famous Renaissance frescoes in Valencia's Cathedral (Spain) have been kept under confined temperature and relative humidity (RH) conditions for about 300 years, until the removal of the baroque vault covering them, carried out in 2006. In the interest of longer-term preservation and in order to maintain these frescoes in good condition, a unique monitoring system was implemented to record both air temperature and RH. Sensors were installed in different points at the vault of the apse, during the restoration process. The present study proposes a statistical methodology for analyzing a subset of RH data recorded in 2008 and 2010, from the sensors. This methodology is based on fitting different functions and models to the time series, in order to classify the sensors. The methodology proposed, computes classification variables and applies a discriminant technique to them. The classification variables correspond to estimates of parameters of the models and features such as mean and maximum, among others. These features are computed using values of the functions such as spectral density, sample autocorrelation (sample ACF), sample partial autocorrelation (sample PACF), and moving range (MR). The classification variables computed were structured as a matrix. Next, Sparse Partial Least Squares Discriminant Analysis (sPLS-DA) was applied in order to discriminate sensors according to their position in the vault. It was found that the classification of sensors derived from Seasonal ARIMA-TGARCH showed the best performance (i.e., lowest classification error rate). Based on these results, the methodology applied here can be useful for characterizing the differences in RH, measured at different positions in a historical building.

Multivariate Time Series Analysis of Temperatures in the Archaeological Museum of L'Almoina (Valencia, Spain).

An earlier study carried out in 2010 at the archaeological site of L'Almoina (Valencia, Spain) found marked daily fluctuations of temperature, especially in summer. Such pronounced gradient is due to the design of the museum, which includes a skylight as a ceiling, covering part of the remains in the museum. In this study, it was found that the thermal conditions are not homogeneous and vary at different points of the museum and along the year. According to the European Standard EN10829, it is necessary to define a plan for long-term monitoring, elaboration and study of the microclimatic data, in order to preserve the artifacts. With the aforementioned goal of extending the study and offering a tool to monitor the microclimate, a new statistical methodology is proposed. For this propose, during one year (October 2019-October 2020), a set of 27 data-loggers was installed, aimed at recording the temperature inside the museum. By applying principal component analysis and k-means, three different microclimates were established. In order to characterize the differences among the three zones, two statistical techniques were put forward. Firstly, Sparse Partial Least Squares Discriminant Analysis (sPLS-DA) was applied to a set of 671 variables extracted from the time series. The second approach consisted of using a random forest algorithm, based on the same functions and variables employed by the first methodology. Both approaches allowed the identification of the main variables that best explain the differences between zones. According to the results, it is possible to establish a representative subset of sensors recommended for the long-term monitoring of temperatures at the museum. The statistical approach proposed here is very effective for discriminant time series analysis and for explaining the differences in microclimate when a net of sensors is installed in historical buildings or museums.