Malaria time series in the extra-Amazon region of Brazil: epidemiological scenario and a two-year prediction model

Garcia, Klauss Kleydmann Sabino; Abrahão, Amanda Amaral; Oliveira, Ana Flávia de Morais; Henriques, Karina Medeiros de Deus; Pina-Costa, Anielle de; Siqueira, André; Ramalho, Walter Massa

doi:10.1186/s12936-022-04162-1

Cited by 5 publications

(2 citation statements)

References 23 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have utilized the delivery of forecasted results through notifications in various domains. For example, messages sent via notifications to feed animals and manage dairy cows [ 22 ], notifying farmers about preventive actions and disinfectant spraying in agriculture [ 32 ], weather forecasting notifications [ 25 , 32 , 67 , 68 ], malaria notifications [ 30 , 31 , 69 , 70 ], honeybee activity with an alarm [ 71 ], bus delay notifications [ 72 ], and air quality notifications [ 73 , 74 , 75 ] as predictive information or utilize notifications to collect preliminary data on air quality [ 76 ]. However, most researchers primarily focused on consent to forecasting, considering notifications merely as information regarding the forecasted results.…”

Section: Related Workmentioning

confidence: 99%

Optimizing Forecasted Activity Notifications with Reinforcement Learning

Fikry

Inoue

2023

Sensors

View full text Add to dashboard Cite

In this paper, we propose the notification optimization method by providing multiple alternative times as a reminder for a forecasted activity with and without probabilistic considerations for the activity that needs to be completed and needs notification. It is important to consider various factors when sending notifications to people after obtaining the results of the forecasted activity. We should not send notifications only when we have forecasted results because future daily activities are unpredictable. Therefore, it is important to strike a balance between providing useful reminders and avoiding excessive interruptions, especially for low probabilities of forecasted activity. Our study investigates the impact of the low probability of forecasted activity and optimizes the notification time with reinforcement learning. We also show the gaps between forecasted activities that are useful for self-improvement by people for the balance of important tasks, such as tasks completed as planned and additional tasks to be completed. For evaluation, we utilize two datasets: the existing dataset and data we collected in the field with the technology we have developed. In the data collection, we have 23 activities from six participants. To evaluate the effectiveness of these approaches, we assess the percentage of positive responses, user response rate, and response duration as performance criteria. Our proposed method provides a more effective way to optimize notifications. By incorporating the probability level of activity that needs to be done and needs notification into the state, we achieve a better response rate than the baseline, with the advantage of reaching 27.15%, as well as than the other criteria, which are also improved by using probability.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimizing Forecasted Activity Notifications with Reinforcement Learning

Fikry

Inoue

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Because the occurrence of malaria in the non-endemic region is uncommon, diagnosis and treatment may occur late [ 12 ]. Possibly due to these factors that are related to surveillance and assistance matters, the non-endemic region can present fatality rates varying between 0.8% and 3.3% [ 13 ]. In 2019, the fatality rate in the non-endemic region was 123 times greater than the lethality rate in the Amazon region, which was under 0.02% [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Record Linkage for Malaria Deaths Data Recovery and Surveillance in Brazil

Garcia,

Xavier,

Soremekun

et al. 2023

TropicalMed

Self Cite

View full text Add to dashboard Cite

Objective: The objective is to describe the results and the methodological processes of record linkage for matching deaths and malaria cases. Methods: A descriptive cross-sectional study was conducted with probabilistic record linkage of death and malaria cases data in Brazil from 2011 to 2020 using death records from the Mortality Information System (SIM) and epidemiological data from the Notifiable Diseases Information System (Sinan) and Epidemiological Surveillance Information Systems for malaria (Sivep-Malaria). Three matching keys were used: patient’s name, date of birth, and mother’s name, with an analysis of cosine and Levenshtein dissimilarity measures. Results: A total of 490 malaria deaths were recorded in Brazil between 2011 and 2020. The record linkage resulted in the pairing of 216 deaths (44.0%). Pairings where all three matching keys were identical accounted for 30.1% of the total matched deaths, 39.4% of the matched deaths had two identical variables, and 30.5% had only one of the three key variables identical. The distribution of the variables of the matched deaths (216) was similar to the distribution of all recorded deaths (490). Out of the 216 matched deaths, 80 (37.0%) had poorly specified causes of death in the SIM. Conclusions: The record linkage allowed for the detailing of the data with additional information from other epidemiological systems. Record linkage enables data linkage between information systems that lack interoperability and is an extremely useful tool for refining health situation analyses and improving malaria death surveillance in Brazil.

show abstract