Harish Neelam

Mr. Harish Neelam

Michigan State University, East Lansing, Michigan, USA
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 August 2025 in The American Journal of Emergency Medicine
Verified
Journal Article
Open access
SGSatheesh Gunaga
Satheesh Gunaga
AAAbe Al-Hage
Abe Al-Hage
ABAlyssa Buchheister
Alyssa Buchheister
HNHarish Neelam
Harish Neelam
JCJessica Corcoran
Jessica Corcoran
FMFabrice Mowbray
Fabrice Mowbray
Emergency departments (EDs) play a central role in end-of-life care, yet the early integration of hospice and palliative care (HPC) is often underutilized. Early access to HPC improves outcomes, aligns care with patient goals, and reduces costs. However, incorporating primary and specialized palliative care resources in the ED remains inconsistent, and utilization trends are not well understood. Our study evaluates the incidence and trends of ED-initiated HPC consults over 8 years within a large metropolitan health system. We conducted a retrospective cohort study of electronic health records from 5 EDs between 2016 and 2023. Our cohort included all ED visits where HPC consults were ordered. We examined the annual number of HPC consults, patient demographics, and health outcomes. A subgroup analysis evaluated HPC consults per 1000 ED patients aged 60 or older admitted for inpatient care. A total of 8055 HPC consults were ordered for 6370 unique patients. The average age was 78.1 years, with 56.4 % female and 75.0 % White. Of the cohort, 91.7 % were admitted, 5.3 % discharged home, and 53.2 % died in-hospital. HPC consults increased from 369 in 2016 to 1355 in 2023 (367 % increase, p < 0.001). The ratio of hospice to palliative care consults reversed from 1.5:1 in 2016 to 1:1.9 in 2023. Post-COVID-19, daily HPC consults rose by 173.6 % compared to pre-pandemic levels. ED-initiated HPC consults increased significantly over time, suggesting an evolving role for EDs in delivering primary palliative care. Further research is needed to determine national trends and identify barriers to broader implementation.

12 July 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
HNHarish Neelam
Harish Neelam
KVKoushik Sai Veerella
Koushik Sai Veerella
SBSouradip Biswas
Souradip Biswas
This paper presents an innovative approach to dimensionality reduction and feature extraction in high-dimensional datasets, with a specific application focus on wood surface defect detection. The proposed framework integrates sparse modeling techniques, particularly Lasso and proximal gradient methods, into a comprehensive pipeline for efficient and interpretable feature selection. Leveraging pre-trained models such as VGG19 and incorporating anomaly detection methods like Isolation Forest and Local Outlier Factor, our methodology addresses the challenge of extracting meaningful features from complex datasets. Evaluation metrics such as accuracy and F1 score, alongside visualizations, are employed to assess the performance of the sparse modeling techniques. Through this work, we aim to advance the understanding and application of sparse modeling in machine learning, particularly in the context of wood surface defect detection.

23 July 2024 in arXiv
Verified
Preprint
Open access
PDF file
HNHarish Neelam
Harish Neelam
This paper presents a multilevel hierarchical framework for the classification of weather conditions and hazard prediction. In recent years, the importance of data has grown significantly, with various types like text, numbers, images, audio, and videos playing a key role. Among these, images make up a large portion of the data available. This application shows promise for various purposes, especially when combined with decision support systems for traffic management, afforestation, and weather forecasting. It's particularly useful in situations where traditional weather predictions are not very accurate, such as ensuring the safe operation of self driving cars in dangerous weather. While previous studies have looked at this topic with fewer categories, this paper focuses on eleven specific types of weather images. The goal is to create a model that can accurately predict weather conditions after being trained on a large dataset of images. Accuracy is crucial in real-life situations to prevent accidents, making it the top priority for this paper. This work lays the groundwork for future applications in weather prediction, especially in situations where human expertise is not available or may be biased. The framework, capable of classifying images into eleven weather categories: dew, frost, glaze, rime, snow, hail, rain, lightning, rainbow, and sandstorm, provides real-time weather information with an accuracy of 0.9329. The proposed framework addresses the growing need for accurate weather classification and hazard prediction, offering a robust solution for various applications in the field.


1 June 2026 in Cancer Causes & Control
Verified
Journal Article
Open access
PDF file
HNHarish Neelam
Harish Neelam
FIFurqan Irfan
Furqan Irfan
RWRobert Wahl
Robert Wahl
Kelly A. HirkoKelly A. Hirko
Kelly A. Hirko
Purpose: We examined the associations between county-level endocrine-disrupting pesticide usage and breast cancer incidence, overall and by metropolitan status. Methods: This ecological study used publicly available data from the United States Geological Survey on county-level agricultural pesticide usage (in kilograms). We focused on 38 pesticides with endocrine-disrupting properties relevant in breast cancer etiology, which were categorized by chemical class as follows: carbamates, neonicotinoids, organochlorines, organophosphates, phosphonates, pyrethroids, triazines, and other miscellaneous compounds. The analysis included 2,457 U.S. counties with data on pesticide usage (2001–2015) and age-adjusted breast cancer incidence rates (2016–2020), accounting for a latency period. Metropolitan status was assessed using the 2013 Rural–Urban Continuum Codes. Gamma regression models with a log-link function were used to estimate rate ratios (RR) and 95% confidence intervals (CI) between pesticides (per interquartile range increase) and age-adjusted breast cancer incidence rates, adjusting for county-level covariates including % smoking, % poverty, % unemployed, % no high school diploma, % uninsured, and residential mobility. Results: Total median pesticide use was higher in rural vs. urban counties (17,523 kg vs. 14,743 kg; p < 0.05), with some variation by pesticide class. Pesticide use was associated with slightly higher breast cancer incidence in rural counties (RR = 1.02 (95% CI 1.01, 1.03)), but not in urban counties (RR = 1.00 (95% CI 1.00, 1.00)) ( p int < 0.001). Associations differed by pesticide type. Conclusion: Results suggest modest positive associations between county-level endocrine-disrupting pesticide use and breast cancer incidence in rural U.S. counties, with variation by pesticide type. These findings highlight the need for further research to inform targeted prevention efforts.

1 October 2026 in Addictive Behaviors
Verified
Journal Article
Closed access
CTChristabelle Toso
Christabelle Toso
BABan Al-Sahab
Ban Al-Sahab
HNHarish Neelam
Harish Neelam
SHSophia A. Hussen
Sophia A. Hussen
DMDawn Misra
Dawn Misra
CGCarmen Giurgescu
Carmen Giurgescu