Public Health Information Systems

Prof. Philip de Melo, Ph.D.

**** ********* ****, *** ***

Glenarden, Maryland 20706

Tel: 571-***-****

US citizen

Education

****, ***, *.**. ****** health informatics and bioinformatics. Thesis “Impact of climate change on population health” (Diploma N 456640, 05/13/1974) 1978, MSU, Doctorate degree in biology. Thesis “Predictive modeling in complex biological systems”, (Diploma N 000216, 11/19/1993) 1993, UCL, Ph.D. Information and computer science. Thesis “Information systems in biomedical applications”, (Diploma N 021991, 05/31/1978) Employment history

1978-1980, Columbia University in the City of New York. Post-doctoral research associate. 1980-1985 Columbia University in the City of New York. Assistant professor 1985-2000 Georgia Tech (Atlanta, GA). Associate Professor. 1982-2000 Joint appointment with the US Navy lab (New London, CT) 2000-2010 Federal University of Bahia (Brazil). Full professor (United Nations Development Program).

2010-2015, DoD research lab (Panama City, Fl)

2015 to 2020, EURIPRED Project director and the PI of an international project on public health informatics for poverty-related diseases.

2021current, Research Professor, Bowie State University. 2021-2023 the PI for the ONC workforce program and teaching faculty.

Teaching experience:

Dr. de Melo taught:

1) public health informatics and technology,

2) machine learning in healthcare,

3) artificial intelligence,

4) informatics for health equity and disparities.

5) big data in healthcare,

6) information systems including FHIR data interoperability using web services, 7) predictive analytics for biological threats.

8) advanced course on Python programming

Strengths:

Dr. de Melo is highly recognized as one of the leading authorities in biomedical research and general data science. He has vast experience working with government funding agencies including DoD, NIH, ONC, NSF, DoE, and USDA. He served as PI of government projects that amount to $26 million, assisted in finding and closing opportunities, and enabling growth and delivery in academic and industrial institutions. Being the PI, he managed proposals from start to finish to include solution development, Basis of Estimates, risks and mitigations in collaboration with the proposal management team to ensure all elements are presented in a successful fashion. He successfully collaborated with client-facing teams, extracting the most pressing project. His strength is to develop and maintain effective internal and external business relationships in clients and industry partners.

Dr. de Melo is one of the leaders in prediction of outbreaks and pandemics. He worked on this topic with the Maryland Department of Health during COVID-19 pandemic. Currently, he serves as an NSF expert on PIPP program (Predictive Intelligence for Pandemic Prevention). Dr. de Melo is also a professional Python programmer. In 2022, he developed with his students the FHIR/API platform for data interoperability. The platform was demonstrated to the ONC officials in March 2022. In 2024 he developed a training platform for big data analytics in public health. The platform trains students in using real-world big public health data in a streaming mode. Using this platform. students get solid background in processing conventional, batch and streaming public health data.

Research experience:

1) ECG research: developed a new approach for ECG recording. It mitigates noise in ECG signal detection and stabilizes the problem of electrode misplacement, 2) Once the ECG is preprocessed (this phase is called ECG signal exploration) the signal is fed into the Machine Learning algorithm (optimized SVM) to predict the occurrence of coronary heart diseases (CHD) with the accuracy of more than 94% (compare with the 50-60% using prediction on conventional ECG).

2) Cancer research: Breast cancer is considered a multifactorial disease and the most common cancer in women worldwide (about 1.5 million women are diagnosed with breast cancer each year, and on average 500,000 women die from this disease in the world). I developed a new classification algorithm with accuracy of 96.33%. 3) Biological threats prediction: Developed an algorithm for predict outbreak and pandemics through diverse data integration and processing (big data and real-time processing) The work pushes beyond the boundaries of modern prediction techniques by closing the loop between data collection, control, and modeling - creating a unique and cross-disciplinary architecture for building accurate and interpretable pandemic prediction models of complex dynamic systems from time series data.

4) Impact of air quality on population respiratory diseases (with NASA): The COVID-19 experience demonstrated the exceptional capability of satellite remote sensing of atmospheric composition to track adoption and adherence to physical distancing, a vital public health strategy that varied in time, place, duration, and population acceptance across the US and globally. Physical distancing and other behavioral changes that reduce fuel combustion (e.g., in the transportation sector) affect air pollution emissions. During COVID-19, my research indicated that NO2 dropped by different amounts in US cities, even after we accounted for location-specific effects of meteorology and seasonality on NO2. Varying degrees of adherence to COVID-19 stay-at-home measures across global cities led to uneven changes in traffic patterns, and we found correlations between satellite-derived traffic-related air pollution during COVID and changes in mobility. It was also demonstrated that the COVID-19 natural experiment, in which passenger vehicle traffic dropped by about 50% while other emission sources were largely unaffected, revealed persistent disparities in NO2 pollution across the US. Specifically, it was found that communities of color and those with lower educational achievement and income levels experienced higher NO2 concentrations during the pandemic. 5) Neighborhoods and Health Disparities (with Maryland Department of Health) The expansion in health disparity research includes everything from examinations of an individual’s own behavioral effects on health to incorporations of relevant neighborhood characteristics to explain geographic health disparities. Studies have suggested that economic, social, and physical conditions influence the health status of residents, such as access to healthy and affordable food, recreational facilities, and safe, clean environments. Thus, to advance our basic knowledge of social determinants of health and include these highly relevant data in predictive modeling, we will target four key datasets that include both historical and ongoing data collection, namely socioeconomic and demographic, built environment, health care, and food access. By integrating these SDOH data with our other data streams, we will make transformative SDOH informed predictions for targeted intervention that can consider local community-specific features for more impactful pre-emergence detection and prevention. Our team has expertise in multilevel modeling of neighborhoods and using these models to study health disparities across neighborhoods.

Competed Projects and Grants:

Euripred (2015-2020), PI, (viprd.net) Public health informatics for poverty-related diseases

(HIV, Malaria, HP) ($12,400,00)

PHIT project (2021-2023), PI, (https://hbcubuzz.com/2021/09/bowie-state-receives-10m-public- health-grant-its-largest-gift-in-2-decades). Workforce development focusing on underrepresented communities ($10,650,00).

MIDAS project (1980-1985), Co-PI with Dr. Kuo ) ($1,650,000) Dr. de Melo served as the PI for projects financed by the NSF ($180,000) and ($75,000), AFOSR

($360,000), ONR($420,000), and USDA ($935,000).

Total ($26,670,000)

Awards:

US Navy Service Award,

Gold medal, European Scientific-Industrial Chamber, Presidential Teaching Award.

The best book to read in public health in 2024 (https://bookauthority.org/books/new-public- health-ebooks)

Best publication award on cancer informatics

Recent publications:

Publications: Over 100 papers in peer-reviewed journals, 3 patents, and 6 books. Latest publications:

2024. Philip de Melo, “Public Health Informatics and Technology”, (ISBN 979-889372953-5). 2024. Philip de Melo, “High accuracy diagnostics of breast cancer using optimized SVM technology”, ICC-2024

2024. Philip de Melo, “Introduction to Big data in public health” Google publication and online lecture (https://www.youtube.com/watch?v=zj9IV2FVpSg&t=297s) 2024. Philip de Melo, “Big data as an information system”, APHA conference 2024. Philip de Melo, “ Can we predict outbreaks and pandemics?” Google publication and online lecture (https://www.youtube.com/watch?v=T8L4k_B8jEc&t=1097s) 2023 Philip de Melo and Mane Davtyan, “High Accuracy Classification of Populations with Breast Cancer: SVM Approach, Cancer Research Journal, OI:10.11648/j.crj.20231103.13 2023 Philip de Melo, “Air quality and public health”, Environmental science and pollution research”, (in press).

2023. Philip de Melo, “Introduction to Public Health informatics: web services for data interoperability, Google publication and online lecture

(https://www.youtube.com/watch?v=ASFcuGtuLVY)

2023. Philip de Melo, “Data quality in public health”, CHITA-2024 2023. Philip de Melo, “Accurate predictive modeling in population health based on the wavelet transformed ECG recordings”, ACC-2023.

Thesis supervision:

Ph.D. Thesis advisor for S. Hassanzadeh, Columbia University, 1985, Ph.D. Thesis advisor for D. Foster, Columbia University,1985 M.Sc. Thesis advisor for H. Boizidi, Columbia University,1983 M.Sc. Thesis advisor, Columbia University A. Shamsi, 1983 M.Sc. Thesis advisor, Georgia Tech M. Craig, 1987

Ph.D. Thesis advisor for S. Carneiro, Federal University of Bahia, 1990 Ph.D. Thesis advisor for M. Botteglio, Federal University of Bahia,1992 M.Sc. Thesis advisor for G. da Silva, Federal University of Bahia,1996 Ph.D. Thesis advisor for R.Pestana, Federal University of Bahia, 2000 M.Sc. Thesis advisor for S. Mahato, Bowie State University, 2022 Ph.D. Thesis advisor for G. Agbo Idoko, Bowie State University, 2022 Ph.D. Thesis advisor for A. Reehl, Bowie State University, 2023

Contact this candidate