Prediction of Epidemic Disease Outbreaks, Using Machine Learning

2021 ◽  
pp. 123-144
Author(s):  
Vaishali Gupta ◽  
Sanjeev Prasad
Keyword(s):  
Machine Learning ◽  
Disease Outbreaks ◽  
Epidemic Disease

scholarly journals Plague and the Fall of Baghdad (1258)

2021 ◽  
Vol 65 (2) ◽  
pp. 157-177
Author(s):  
Nahyan Fancy ◽  
Monica H. Green
Keyword(s):  
Fourteenth Century ◽  
Thirteenth Century ◽  
Disease Outbreaks ◽  
Epidemic Disease ◽  
Late Medieval ◽  
Western Asia ◽  
Abbasid Caliphate ◽  
Historical Accounts ◽  
A Minor

AbstractThe recent suggestion that the late medieval Eurasian plague pandemic, the Black Death, had its origins in the thirteenth century rather than the fourteenth century has brought new scrutiny to texts reporting ‘epidemics’ in the earlier period. Evidence both from Song China and Iran suggests that plague was involved in major sieges laid by the Mongols between the 1210s and the 1250s, including the siege of Baghdad in 1258 which resulted in the fall of the Abbasid caliphate. In fact, re-examination of multiple historical accounts in the two centuries after the siege of Baghdad shows that the role of epidemic disease in the Mongol attacks was commonly known among chroniclers in Syria and Egypt, raising the question why these outbreaks have been overlooked in modern historiography of plague. The present study looks in detail at the evidence in Arabic sources for disease outbreaks after the siege of Baghdad in Iraq and its surrounding regions. We find subtle factors in the documentary record to explain why, even though plague received new scrutiny from physicians in the period, it remained a minor feature in stories about the Mongol invasion of western Asia. In contemporary understandings of the genesis of epidemics, the Mongols were not seen to have brought plague to Baghdad; they caused plague to arise by their rampant destruction. When an even bigger wave of plague struck the Islamic world in the fourteenth century, no association was made with the thirteenth-century episode. Rather, plague was now associated with the Mongol world as a whole.

scholarly journals COVID-19: Examining the case growth-rate due to Visitor vs Local Mobility using Machine Learning: A Study in the United States

2021 ◽  
Author(s):  
satya katragadda ◽  
ravi teja bhupatiraju ◽  
vijay raghavan ◽  
ziad ashkar ◽  
raju gottumukkala
Keyword(s):  
United States ◽  
Machine Learning ◽  
Statistical Significance ◽  
Disease Outbreaks ◽  
The United States ◽  
Mobile Phone Data ◽  
Infectious Disease Outbreaks ◽  
Local Mobility ◽  
Local Risk ◽  
The Impact

Abstract Background: Travel patterns of humans play a major part in the spread of infectious diseases. This was evident in the geographical spread of COVID-19 in the United States. However, the impact of this mobility and the transmission of the virus due to local travel, compared to the population traveling across state boundaries, is unknown. This study evaluates the impact of local vs. visitor mobility in understanding the growth in the number of cases for infectious disease outbreaks. Methods: We use two different mobility metrics, namely the local risk and visitor risk extracted from trip data generated from anonymized mobile phone data across all 50 states in the United States. We analyzed the impact of just using local trips on infection spread and infection risk potential generated from visitors' trips from various other states. We used the Diebold-Mariano test to compare across three machine learning models. Finally, we compared the performance of models, including visitor mobility for all the three waves in the United States and across all 50 states. Results: We observe that visitor mobility impacts case growth and that including visitor mobility in forecasting the number of COVID-19 cases improves prediction accuracy by 34. We found the statistical significance with respect to the performance improvement resulting from including visitor mobility using the Diebold-Mariano test. We also observe that the significance was much higher during the first peak March to June 2020. Conclusion: With presence of cases everywhere (i.e. local and visitor), visitor mobility (even within the country) is shown to have significant impact on growth in number of cases. While it is not possible to account for other factors such as the impact of interventions, and differences in local mobility and visitor mobility, we find that these observations can be used to plan for both reopening and limiting visitors from regions where there are high number of cases.

scholarly journals Are Artificial Intelligence (AI) And Machine Learning (ML) Having An Effective Role In Helping Humanity Address The New Coronavirus Pandemic?

2020 ◽  
Vol 17 ◽  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Disease Outbreaks ◽  
Hospital Capacity ◽  
Data Engineering ◽  
Clinical Presentations ◽  
The Face ◽  
Effective Role ◽  
Using Data ◽  
The Right

COVID-19 has become a pandemic affecting the most of countries in the world. One of the most difficult decisions doctors face during the Covid-19 epidemic is determining which patients will stay in hospital, and which are safe to recover at home. In the face of overcrowded hospital capacity and an entirely new disease with little data-based evidence for diagnosis and treatment, the old rules for determining which patients should be admitted have proven ineffective. But machine learning can help make the right decision early, save lives and lower healthcare costs. So, there is therefore an urgent and imperative need to collect data describing clinical presentations, risks, epidemiology and outcomes. On the other side, artificial intelligence(AI) and machine learning(ML) are considered a strong firewall against outbreaks of diseases and epidemics due to its ability to quickly detect, examine and diagnose these diseases and epidemics.AI is being used as a tool to support the fight against the epidemic that swept the entire world since the beginning of 2020.. This paper presents the potential for using data engineering, ML and AI to confront the Coronavirus, predict the evolution of disease outbreaks, and conduct research in order to develop a vaccine or effective treatment that protects humanity from these deadly diseases.

scholarly journals The Influence of Time-Limited Immunity on a COVID-19 Epidemic: A Simulation Study

2020 ◽  
Author(s):  
Robert J. Kosinski
Keyword(s):  
Simulation Study ◽  
Recurrent Disease ◽  
Disease Outbreaks ◽  
Disease Prevalence ◽  
Epidemic Disease ◽  
One Year

AbstractA series of spreadsheet simulations using SEIS, SEIR, and SEIRS models showed that different durations of effective immunity could have important consequences for the prevalence of an epidemic disease with COVID-19 characteristics. Immunity that lasted four weeks, twelve weeks, six months, one year, and two years was tested with pathogen R0 values of 1.5, 2.3, and 3.0. Shorter durations of immunity resulted in oscillations in disease prevalence. Immunity that lasted from three months to two years produced recurrent disease outbreaks triggered by the expiration of immunity. If immunity “faded out” gradually instead of persisting at full effectiveness to the end of the immune period, the recurrent outbreaks became more frequent. The duration of effective immunity is an important consideration in the epidemiology of a disease like COVID-19.

scholarly journals Farmers' perception of the epidemic of African Swine Fever in Nigeria

2021 ◽  
Vol 29 (2) ◽  
pp. 217-225
Author(s):  
K. Adebayo ◽  
O. S. Sorungbe
Keyword(s):  
Significant Relationship ◽  
Disease Outbreaks ◽  
African Swine Fever ◽  
Sampling Technique ◽  
Primary Data ◽  
Extension Agents ◽  
Epidemic Disease ◽  
Chi Square ◽  
Pig Farms ◽  
Chi Square Analysis

Livestock diseases constitute a great threat to protein availability in Nigeria. It is thus necessary to eramine how much farmers know about some deadly diseases prevalent in their stock as it would afford the farmer a timely re-adjustment to prevent foreseeable losses. The focus of this study was to determine farmers' level of awareness of African Swine Fever (ASF) in Agege Area of Lagos State, Nigeria. Primary data were collected with the use of a questionnaire administered to one hundred and twenty (120) respondents selected using the purposive sampling technique. Twenty seven (27) pig farms were also visited to obtain 017-farm data on pig mortality during the ASF epidemic. It was revealed that there was inadequate awareness of the early symptoms and characteristic signs of ASF among the respondents. As such mortality of about 95 percent was recorded. The Chi square analysis showed no significant relationship between farmers' level of awareness of ASF and the location of their pig farms. There was also no significant relationship between pig stock population and farmers' contact with Extension agents. The study then concluded that extension services to pig farmers are currently inadequate. It therefore recommends that it be developed to ensure institutional support in cases of epidemic disease outbreaks. More so, possible ways should be sought to ensure a steady flow of agricultural information from the research institutes and universities to the ultimate users. Preventive measures should however be taught to farmers to avoid the incidence of future disease outbreaks. Lastly, pig farmers are also advised to form associations that could serve as a pressure group in such cases of sector specific emergencies. 

scholarly journals Comparing Machine Learning Algorithms for Predicting ICU Admission and Mortality in COVID-19

2020 ◽  
Author(s):  
Sonu Subudhi ◽  
Ashish Verma ◽  
Ankit B. Patel ◽  
C. Corey Hardin ◽  
Melin J. Khandekar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Decision Making ◽  
Learning Algorithms ◽  
Disease Outbreaks ◽  
Clinical Decision ◽  
Machine Learning Algorithms ◽  
Healthcare Database ◽  
Icu Admission ◽  
Infectious Disease Outbreaks ◽  
Better Than

AbstractAs predicting the trajectory of COVID-19 disease is challenging, machine learning models could assist physicians determine high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) healthcare database, we developed and internally validated models using patients presenting to Emergency Department (ED) between March-April 2020 (n = 1144) and externally validated them using those individuals who encountered ED between May-August 2020 (n = 334). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and procalcitonin levels were important for ICU admission models whereas eGFR <60 ml/min/1.73m2, ventilator use, and potassium levels were the most important variables for predicting mortality. Implementing such models would help in clinical decision-making for future COVID-19 and other infectious disease outbreaks.

Mississippi's Infectious Disease Hotline: A Surveillance and Education Model for Future Disasters

2009 ◽  
Vol 24 (1) ◽  
pp. 11-17 ◽  
Author(s):  
Andrew M. J. Cavey ◽  
Jonathan M. Spector ◽  
Derek Ehrhardt ◽  
Theresa Kittle ◽  
Mills McNeill ◽  
...  
Keyword(s):  
Infectious Disease ◽  
Hurricane Katrina ◽  
Surveillance System ◽  
Respiratory Infections ◽  
Disease Outbreaks ◽  
Health Concern ◽  
Watery Diarrhea ◽  
Epidemic Disease ◽  
Infectious Disease Outbreaks ◽  
Telephone Hotline

AbstractIntroduction:The potential for outbreaks of epidemic disease among displaced residents was a significant public health concern in the aftermath of Hurricane Katrina. In response, the Mississippi Department of Health (MDH) and the American Red Cross (ARC) implemented a novel infectious disease surveillance system, in the form of a telephone “hotline”, to detect and rapidly respond to health threats in shelters.Methods:All ARC-managed shelters in Mississippi were included in the surveillance system. A symptom-based, case reporting method was developed and distributed to shelter staff, who were linked with MDH and ARC professionals by a toll-free telephone service. Hotline staff investigated potential infectious disease outbreaks, provided assistance to shelter staff regarding optimal patient care, and helped facilitate the evaluation of ill evacuees by local medical personnel.Results:Forty-three shelters sheltering 3,520 evacuees participated in the program. Seventeen shelters made 29 calls notifying the hotline of the following cases: (1) fever (6 cases); (2) respiratory infections (37 cases); (3) bloody diarrhea (2 cases); (4) watery diarrhea (15 cases); and (5) other, including rashes (33 cases). Thirty-four of these patients were referred to a local physician or hospital for further diagnosis and disease management. Three cases of chickenpox were identified. No significant infectious disease outbreaks occurred and no deaths were reported.Conclusions:The surveillance system used direct verbal communication between shelter staff and hotline managers to enable more rapid reporting, mapping, investigation, and intervention, far beyond the capabilities of a more passive or paper-based system. It also allowed for immediate feedback and education for staff unfamiliar with the diseases and reporting process. Replication of this program should be considered during future disasters when health surveillance of a large, disseminated shelter population is necessary.

Machine Learning Techniques in Healthcare—A Survey

2020 ◽  
Vol 17 (9) ◽  
pp. 4276-4279
Author(s):  
K. Aiswariya Milan ◽  
Niharika P. Kumar
Keyword(s):  
Machine Learning ◽  
Medical Diagnosis ◽  
Urban Areas ◽  
Treatment Plan ◽  
Disease Outbreaks ◽  
Data Access ◽  
Disease Diagnosis ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Personalized Healthcare

The development of science and technology has led to a very busy lifestyle among urban people across the globe. Due to the advent of cutting-edge technologies, connectivity and networking is a boon to the people living in urban areas. Thus, a vast amount of patient data from admission, treatment and discharge is collected across the clinical community. These rich data being available online has been under-utilized and the question arises on how best the data can be utilized. With the centralized data and powerful data analytical algorithms are running in powerful machines, until recent past, the machine learning is yet to be used for improving the diagnosis, prediction and secure data access process in healthcare. In this proposal, machine learning algorithms are used for enhanced medical diagnosis, personalized healthcare, predicting disease outbreaks in certain regions and measures for securing healthcare data from malicious attacks. The work focuses on 3 major chronic diseases such as Heart Attack, Stroke and Diabetics. Enhanced medical diagnosis involves the methods for predicting readmissions to hospital after X days of their discharge. Personalized healthcare involves methods for disease diagnosis and building treatment plan. The predictions are based upon on the patient’s medical reports and living habits. Disease outbreaks in an area involves methods for monitoring and predicting epidemic outbreaks in an area, during certain period of time based on information from social media.

Sign in / Sign up

Export Citation Format

Share Document