Automatic identification of incidents involving potential serious injuries and fatalities (PSIF).

Safety incidents have always been a crucial risk in work spaces, especially industrial sites. In the last few decades, significant efforts have been dedicated to incident control measures to reduce the rate of safety incidents. Despite all these efforts, the rate of decline in serious injuries and fatalities (SIFs) has been considerably lower than the rate of decline for non-critical incidents. This observation has led to a change of risk reduction paradigm for safety incidents. Under the new paradigm, more focus has been allocated to reducing the rate of critical/SIF incidents, as opposed to reducing the count of all incidents. One of the challenges in reducing the number of SIF incidents is the proper identification of the risk prior to materialization. One of the reasons for risk identification being a challenge is that companies usually only focus on incidents where SIF did occur reactively, and incidents that did not cause SIF but had the potential to do so go unnoticed. Identifying these potentially significant incidents, referred to as potential serious injuries and fatalities (PSIF), would enable companies to work on identifying critical risk and taking steps to prevent them preemptively. However, flagging PSIF incidents requires all incident reports to be analyzed individually by experts and hence significant investment, which is often not affordable, especially for small and medium sized companies. This study is aimed at addressing this problem through machine learning powered automation. We propose a novel approach based on binary classification for the identification of such incidents involving PSIF (potential serious injuries and fatalities). This is the first work towards automatic risk identification from incident reports. Our approach combines a pre-trained transformer model with XGBoost. We utilize advanced natural language processing techniques to encode an incident record comprising heterogeneous fields into a vector representation fed to XGBoost for classification. Moreover, given the scarcity of manually labeled incident records available for training, we leverage weak labeling to augment the label coverage of the training data. We utilize the F2 metric for hyperparameter tuning using Tree-structured Parzen Estimator to prioritize the detection of PSIF records over the avoidance of non-PSIF records being mis-classified as PSIF. The proposed methods outperform several baselines from other studies on a significantly large test dataset.

A machine learning driven automated system for safety data sheet indexing.

Safety Data Sheets (SDS) are foundational to chemical management systems and are used in a wide variety of applications such as green chemistry, industrial hygiene, and regulatory compliance, among others within the Environment, Health, and Safety (EHS) and the Environment, Social, and Governance (ESG) domains. Companies usually prefer to have key pieces of information extracted from these datasheets and stored in an easy to access structured repository. This process is referred to as SDS "indexing". Historically, SDS indexing has always been done manually, which is labor-intensive, time-consuming, and costly. In this paper, we present an automated system to index the composition information of chemical products from SDS documents using a multi-stage ensemble method with a combination of machine learning models and rule-based systems stacked one after the other. The system specifically indexes the ingredient names, their corresponding Chemical Abstracts Service (CAS) numbers, and weight percentages. It takes the SDS document in PDF format as the input and gives the list of ingredient names along with their corresponding CAS numbers and weight percentages in a tabular format as the output. The system achieves a precision of 0.93 at the document level when evaluated on 20,000 SDS documents annotated for this purpose.