Search

BackgroundNovel and highly sensitive point-of-care malaria diagnostic and surveillance tools that are rapid and affordable are urgently needed to support malaria control and elimination.MethodsWe demonstrated the potential of near-infrared spectroscopy (NIRS) technique to detect malaria parasites both, in vitro, using dilutions of infected red blood cells obtained from Plasmodium falciparum cultures and in vivo, in mice infected with P. berghei using blood spotted on slides and non-invasively, by simply scanning various body areas (e.g., feet, groin and ears). The spectra were analysed using machine learning to develop predictive models for infection.FindingsUsing NIRS spectra of in vitro cultures and machine learning algorithms, we successfully detected low densities (InterpretationThese data highlights the potential of NIRS technique as rapid, non-invasive and affordable tool for surveillance of malaria cases. Further work to determine the potential of NIRS to detect malaria in symptomatic and asymptomatic malaria cases in the field is recommended including its capacity to guide current malaria elimination strategies.

BackgroundTrichuris trichiura (whipworm) is one of the most prevalent soil transmitted helminths (STH) affecting 604-795 million people worldwide. Diagnostic tools that are affordable and rapid are required for detecting STH. Here, we assessed the performance of the near-infrared spectroscopy (NIRS) technique coupled with machine learning algorithms to detect Trichuris muris in faecal, blood, serum samples and non-invasively through the skin of mice.MethodologyWe orally infected 10 mice with 30 T. muris eggs (low dose group), 10 mice with 200 eggs (high dose group) and 10 mice were used as the control group. Using the NIRS technique, we scanned faecal, serum, whole blood samples and mice non-invasively through their skin over a period of 6 weeks post infection. Using artificial neural networks (ANN) and spectra of faecal, serum, blood and non-invasive scans from one experiment, we developed 4 algorithms to differentiate infected from uninfected mice. These models were validated on mice from a second independent experiment.Principal findingsNIRS and ANN differentiated mice into the three groups as early as 2 weeks post infection regardless of the sample used. These results correlated with those from concomitant serological and parasitological investigations.SignificanceTo our knowledge, this is the first study to demonstrate the potential of NIRS as a diagnostic tool for human STH infections. The technique could be further developed for large scale surveillance of soil transmitted helminths in human populations.

Conclusions/significanceThe potential of RS as a surveillance tool for malaria and arbovirus vectors and MIRS for the diagnosis and surveillance of arboviruses is yet to be assessed. NIRS capacity as a surveillance tool for malaria and arbovirus vectors should be validated under field conditions, and its potential as a diagnostic tool for malaria and arboviruses needs to be evaluated. It is recommended that all 3 techniques evaluated simultaneously using multiple machine learning techniques in multiple epidemiological settings to determine the most accurate technique for each application. Prior to their field application, a standardised protocol for spectra collection and data analysis should be developed. This will harmonise their application in multiple field settings allowing easy and faster integration into existing disease control platforms. Ultimately, development of rapid and cost-effective point-of-care diagnostic tools for malaria and arboviruses based on spectroscopy techniques may help combat current and future outbreaks of these infectious diseases.

After mating, female mosquitoes need animal blood to develop their eggs. In the process of acquiring blood, they may acquire pathogens, which may cause different diseases in humans such as malaria, zika, dengue, and chikungunya. Therefore, knowing the parity status of mosquitoes is useful in control and evaluation of infectious diseases transmitted by mosquitoes, where parous mosquitoes are assumed to be potentially infectious. Ovary dissections, which are currently used to determine the parity status of mosquitoes, are very tedious and limited to few experts. An alternative to ovary dissections is near-infrared spectroscopy (NIRS), which can estimate the age in days and the infectious state of laboratory and semi-field reared mosquitoes with accuracies between 80 and 99%. No study has tested the accuracy of NIRS for estimating the parity status of wild mosquitoes. In this study, we train an artificial neural network (ANN) models on NIR spectra to estimate the parity status of wild mosquitoes. We use four different datasets: An. arabiensis collected from Minepa, Tanzania (Minepa-ARA); An. gambiae s.s collected from Muleba, Tanzania (Muleba-GA); An. gambiae s.s collected from Burkina Faso (Burkina-GA); and An.gambiae s.s from Muleba and Burkina Faso combined (Muleba-Burkina-GA). We train ANN models on datasets with spectra preprocessed according to previous protocols. We then use autoencoders to reduce the spectra feature dimensions from 1851 to 10 and re-train the ANN models. Before the autoencoder was applied, ANN models estimated parity status of mosquitoes in Minepa-ARA, Muleba-GA, Burkina-GA and Muleba-Burkina-GA with out-of-sample accuracies of 81.9±2.8 (N = 274), 68.7±4.8 (N = 43), 80.3±2.0 (N = 48), and 75.7±2.5 (N = 91), respectively. With the autoencoder, ANN models tested on out-of-sample data achieved 97.1±2.2% (N = 274), 89.8 ± 1.7% (N = 43), 93.3±1.2% (N = 48), and 92.7±1.8% (N = 91) accuracies for Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA, respectively. These results show that a combination of an autoencoder and an ANN trained on NIR spectra to estimate the parity status of wild mosquitoes yields models that can be used as an alternative tool to estimate parity status of wild mosquitoes, especially since NIRS is a high-throughput, reagent-free, and simple-to-use technique compared to ovary dissections.

BackgroundNear infrared spectroscopy (NIRS) is currently complementing techniques to age-grade mosquitoes. NIRS classifies lab-reared and semi-field raised mosquitoes into < or ≥ 7 days old with an average accuracy of 80%, achieved by training a regression model using partial least squares (PLS) and interpreted as a binary classifier.Methods and findingsWe explore whether using an artificial neural network (ANN) analysis instead of PLS regression improves the current accuracy of NIRS models for age-grading malaria transmitting mosquitoes. We also explore if directly training a binary classifier instead of training a regression model and interpreting it as a binary classifier improves the accuracy. A total of 786 and 870 NIR spectra collected from laboratory reared An. gambiae and An. arabiensis, respectively, were used and pre-processed according to previously published protocols. The ANN regression model scored root mean squared error (RMSE) of 1.6 ± 0.2 for An. gambiae and 2.8 ± 0.2 for An. arabiensis; whereas the PLS regression model scored RMSE of 3.7 ± 0.2 for An. gambiae, and 4.5 ± 0.1 for An. arabiensis. When we interpreted regression models as binary classifiers, the accuracy of the ANN regression model was 93.7 ± 1.0% for An. gambiae, and 90.2 ± 1.7% for An. arabiensis; while PLS regression model scored the accuracy of 83.9 ± 2.3% for An. gambiae, and 80.3 ± 2.1% for An. arabiensis. We also find that a directly trained binary classifier yields higher age estimation accuracy than a regression model interpreted as a binary classifier. A directly trained ANN binary classifier scored an accuracy of 99.4 ± 1.0 for An. gambiae and 99.0 ± 0.6% for An. arabiensis; while a directly trained PLS binary classifier scored 93.6 ± 1.2% for An. gambiae and 88.7 ± 1.1% for An. arabiensis. We further tested the reproducibility of these results on different independent mosquito datasets. ANNs scored higher estimation accuracies than when the same age models are trained using PLS. Regardless of the model architecture, directly trained binary classifiers scored higher accuracies on classifying age of mosquitoes than regression models translated as binary classifiers.ConclusionWe recommend training models to estimate age of An. arabiensis and An. gambiae using ANN model architectures (especially for datasets with at least 70 mosquitoes per age group) and direct training of binary classifier instead of training a regression model and interpreting it as a binary classifier.

BACKGROUND:Near infrared spectroscopy (NIRS) is a high throughput technique that measures absorbance of specific wavelengths of light by biological samples and uses this information to classify the age of lab-reared mosquitoes as younger or older than seven days with an average accuracy greater than 80%. For NIRS to estimate ages of wild mosquitoes, a sample of wild mosquitoes with known age in days would be required to train and test the model. Mark-release-recapture is the most reliable method to produce wild-caught mosquitoes of known age in days. However, it is logistically demanding, time inefficient, subject to low recapture rates, and raises ethical issues due to the release of mosquitoes. Using labels from Detinova dissection results in a mathematical model with poor accuracy. Alternatively, a model trained on spectra from laboratory-reared mosquitoes where age in days is known can be applied to estimate the age of wild mosquitoes, but this would be appropriate only if spectra collected from laboratory-reared and wild mosquitoes are similar. METHODS AND FINDINGS:We performed k-means (k = 2) cluster analysis on a mixture of spectra collected from lab-reared and wild Anopheles arabiensis to determine if there is any significant difference between these two groups. While controlling the numbers of mosquitoes included in the model at each age, we found two clusters with no significant difference in distribution of spectra collected from lab-reared and wild mosquitoes (p = 0.25). We repeated the analysis using hierarchical clustering, and similarly, no significant difference was observed (p = 0.13). CONCLUSION:We find no difference between spectra collected from laboratory-reared and wild mosquitoes of the same age and species. The results strengthen and support the on-going practice of applying the model trained on spectra collected from laboratory-reared mosquitoes, especially first-generation laboratory-reared mosquitoes.

Estimating the age distribution of mosquito populations is crucial for assessing their capacity to transmit disease and for evaluating the efficacy of available vector control programs. This study reports on the capacity of the near-infrared spectroscopy (NIRS) technique to rapidly predict the ages of the principal dengue and Zika vector, Aedes aegypti. The age of wild-type males and females, and males and females infected with wMel and wMelPop strains of Wolbachia pipientis were characterized using this method. Calibrations were developed using spectra collected from their heads and thoraces using partial least squares (PLS) regression. A highly significant correlation was found between the true and predicted ages of mosquitoes. The coefficients of determination for wild-type females and males across all age groups were R2 = 0.84 and 0.78, respectively. The coefficients of determination for the age of wMel and wMelPop infected females were 0.71 and 0.80, respectively (P< 0.001 in both instances). The age of wild-type female Ae. aegypti could be identified as < or ≥ 8 days old with an accuracy of 91% (N = 501), whereas female Ae. aegypti infected with wMel and wMelPop were differentiated into the two age groups with an accuracy of 83% (N = 284) and 78% (N = 229), respectively. Our results also indicate NIRS can distinguish between young and old male wild-type, wMel and wMelPop infected Ae. aegypti with accuracies of 87% (N = 253), 83% (N = 277) and 78% (N = 234), respectively. We have demonstrated the potential of NIRS as a predictor of the age of female and male wild-type and Wolbachia infected Ae. aegypti mosquitoes under laboratory conditions. After field validation, the tool has the potential to offer a cheap and rapid alternative for surveillance of dengue and Zika vector control programs.

The release of Wolbachia infected mosquitoes is likely to form a key component of disease control strategies in the near future. We investigated the potential of using near-infrared spectroscopy (NIRS) to simultaneously detect and identify two strains of Wolbachia pipientis (wMelPop and wMel) in male and female laboratory-reared Aedes aegypti mosquitoes. Our aim is to find faster, cheaper alternatives for monitoring those releases than the molecular diagnostic techniques that are currently in use. Our findings indicate that NIRS can differentiate females and males infected with wMelPop from uninfected wild type samples with an accuracy of 96% (N = 299) and 87.5% (N = 377), respectively. Similarly, females and males infected with wMel were differentiated from uninfected wild type samples with accuracies of 92% (N = 352) and 89% (N = 444). NIRS could differentiate wMelPop and wMel transinfected females with an accuracy of 96.6% (N = 442) and males with an accuracy of 84.5% (N = 443). This non-destructive technique is faster than the standard polymerase chain reaction diagnostic techniques. After the purchase of a NIRS spectrometer, the technique requires little sample processing and does not consume any reagents.