health insurance claim predictionhealth insurance claim prediction

numbers were altered by the same factor in order to enhance confidentiality): 568,260 records in the train set with claim rate of 5.26%. Premium amount prediction focuses on persons own health rather than other companys insurance terms and conditions. "Health Insurance Claim Prediction Using Artificial Neural Networks.". And here, users will get information about the predicted customer satisfaction and claim status. Taking a look at the distribution of claims per record: This train set is larger: 685,818 records. The main aim of this project is to predict the insurance claim by each user that was billed by a health insurance company in Python using scikit-learn. If you have some experience in Machine Learning and Data Science you might be asking yourself, so we need to predict for each policy how many claims it will make. To demonstrate this, NARX model (nonlinear autoregressive network having exogenous inputs), is a recurrent dynamic network was tested and compared against feed forward artificial neural network. Here, our Machine Learning dashboard shows the claims types status. However, it is. The authors Motlagh et al. Accuracy defines the degree of correctness of the predicted value of the insurance amount. can Streamline Data Operations and enable i.e. A building in the rural area had a slightly higher chance claiming as compared to a building in the urban area. (2011) and El-said et al. The data was in structured format and was stores in a csv file format. (2013) and Majhi (2018) on recurrent neural networks (RNNs) have also demonstrated that it is an improved forecasting model for time series. Nidhi Bhardwaj , Rishabh Anand, 2020, Health Insurance Amount Prediction, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 09, Issue 05 (May 2020), Creative Commons Attribution 4.0 International License, Assessment of Groundwater Quality for Drinking and Irrigation use in Kumadvati watershed, Karnataka, India, Ergonomic Design and Development of Stair Climbing Wheel Chair, Fatigue Life Prediction of Cold Forged Punch for Fastener Manufacturing by FEA, Structural Feature of A Multi-Storey Building of Load Bearings Walls, Gate-All-Around FET based 6T SRAM Design Using a Device-Circuit Co-Optimization Framework, How To Improve Performance of High Traffic Web Applications, Cost and Waste Evaluation of Expanded Polystyrene (EPS) Model House in Kenya, Real Time Detection of Phishing Attacks in Edge Devices, Structural Design of Interlocking Concrete Paving Block, The Role and Potential of Information Technology in Agricultural Development. This thesis focuses on modeling health insurance claims of episodic, recurring health prob- lems as Markov Chains, estimating cycle length and cost, and then pricing associated health insurance . BSP Life (Fiji) Ltd. provides both Health and Life Insurance in Fiji. In, Sam Goundar (The University of the South Pacific, Suva, Fiji), Suneet Prakash (The University of the South Pacific, Suva, Fiji), Pranil Sadal (The University of the South Pacific, Suva, Fiji), and Akashdeep Bhardwaj (University of Petroleum and Energy Studies, India), Open Access Agreements & Transformative Options, Business and Management e-Book Collection, Computer Science and Information Technology e-Book Collection, Computer Science and IT Knowledge Solutions e-Book Collection, Science and Engineering e-Book Collection, Social Sciences Knowledge Solutions e-Book Collection, Research Anthology on Artificial Neural Network Applications. Insurance companies are extremely interested in the prediction of the future. Continue exploring. Two main types of neural networks are namely feed forward neural network and recurrent neural network (RNN). It is based on a knowledge based challenge posted on the Zindi platform based on the Olusola Insurance Company. Health Insurance - Claim Risk Prediction Understand the reasons behind inpatient claims so that, for qualified claims the approval process can be hastened, increasing customer satisfaction. Supervised learning algorithms create a mathematical model according to a set of data that contains both the inputs and the desired outputs. Most of the cost is attributed to the 'type-2' version of diabetes, which is typically diagnosed in middle age. Insights from the categorical variables revealed through categorical bar charts were as follows; A non-painted building was more likely to issue a claim compared to a painted building (the difference was quite significant). Early health insurance amount prediction can help in better contemplation of the amount. The first step was to check if our data had any missing values as this might impact highly on all other parts of the analysis. Step 2- Data Preprocessing: In this phase, the data is prepared for the analysis purpose which contains relevant information. 4 shows the graphs of every single attribute taken as input to the gradient boosting regression model. Many techniques for performing statistical predictions have been developed, but, in this project, three models Multiple Linear Regression (MLR), Decision tree regression and Gradient Boosting Regression were tested and compared. According to Zhang et al. Reinforcement learning is class of machine learning which is concerned with how software agents ought to make actions in an environment. Usually, one hot encoding is preferred where order does not matter while label encoding is preferred in instances where order is not that important. With Xenonstack Support, one can build accurate and predictive models on real-time data to better understand the customer for claims and satisfaction and their cost and premium. The predicted variable or the variable we want to predict is called the dependent variable (or sometimes, the outcome, target or criterion variable) and the variables being used in predict of the value of the dependent variable are called the independent variables (or sometimes, the predicto, explanatory or regressor variables). Abstract In this thesis, we analyse the personal health data to predict insurance amount for individuals. Health Insurance Cost Predicition. An increase in medical claims will directly increase the total expenditure of the company thus affects the profit margin. Training data has one or more inputs and a desired output, called as a supervisory signal. thats without even mentioning the fact that health claim rates tend to be relatively low and usually range between 1% to 10%,) it is not surprising that predicting the number of health insurance claims in a specific year can be a complicated task. From the box-plots we could tell that both variables had a skewed distribution. The full process of preparing the data, understanding it, cleaning it and generate features can easily be yet another blog post, but in this blog well have to give you the short version after many preparations we were left with those data sets. It was gathered that multiple linear regression and gradient boosting algorithms performed better than the linear regression and decision tree. (2016), neural network is very similar to biological neural networks. Some of the work investigated the predictive modeling of healthcare cost using several statistical techniques. The data included various attributes such as age, gender, body mass index, smoker and the charges attribute which will work as the label. "Health Insurance Claim Prediction Using Artificial Neural Networks." Several factors determine the cost of claims based on health factors like BMI, age, smoker, health conditions and others. By filtering and various machine learning models accuracy can be improved. This is the field you are asked to predict in the test set. Insurance Claim Prediction Problem Statement A key challenge for the insurance industry is to charge each customer an appropriate premium for the risk they represent. It was observed that a persons age and smoking status affects the prediction most in every algorithm applied. The models can be applied to the data collected in coming years to predict the premium. Fig. A key challenge for the insurance industry is to charge each customer an appropriate premium for the risk they represent. Now, lets understand why adding precision and recall is not necessarily enough: Say we have 100,000 records on which we have to predict. Predicting the Insurance premium /Charges is a major business metric for most of the Insurance based companies. We see that the accuracy of predicted amount was seen best. Introduction to Digital Platform Strategy? The data was in structured format and was stores in a csv file. Insurance companies apply numerous techniques for analyzing and predicting health insurance costs. A key challenge for the insurance industry is to charge each customer an appropriate premium for the risk they represent. Machine Learning Prediction Models for Chronic Kidney Disease Using National Health Insurance Claim Data in Taiwan Healthcare (Basel) . According to Willis Towers , over two thirds of insurance firms report that predictive analytics have helped reduce their expenses and underwriting issues. An increase in medical claims will directly increase the total expenditure of the company thus affects the profit margin. document.getElementById( "ak_js_1" ).setAttribute( "value", ( new Date() ).getTime() ); Follow Tutorials 2022. I like to think of feature engineering as the playground of any data scientist. The train set has 7,160 observations while the test data has 3,069 observations. In the next part of this blog well finally get to the modeling process! According to Rizal et al. $$Recall= \frac{True\: positive}{All\: positives} = 0.9 \rightarrow \frac{True\: positive}{5,000} = 0.9 \rightarrow True\: positive = 0.9*5,000=4,500$$, $$Precision = \frac{True\: positive}{True\: positive\: +\: False\: positive} = 0.8 \rightarrow \frac{4,500}{4,500\:+\:False\: positive} = 0.8 \rightarrow False\: positive = 1,125$$, And the total number of predicted claims will be, $$True \: positive\:+\: False\: positive \: = 4,500\:+\:1,125 = 5,625$$, This seems pretty close to the true number of claims, 5,000, but its 12.5% higher than it and thats too much for us! ANN has the ability to resemble the basic processes of humans behaviour which can also solve nonlinear matters, with this feature Artificial Neural Network is widely used with complicated system for computations and classifications, and has cultivated on non-linearity mapped effect if compared with traditional calculating methods. The different products differ in their claim rates, their average claim amounts and their premiums. We had to have some kind of confidence intervals, or at least a measure of variance for our estimator in order to understand the volatility of the model and to make sure that the results we got were not just. A number of numerical practices exist that actuaries use to predict annual medical claim expense in an insurance company. The data has been imported from kaggle website. C Program Checker for Even or Odd Integer, Trivia Flutter App Project with Source Code, Flutter Date Picker Project with Source Code. Premium amount prediction focuses on persons own health rather than other companys insurance terms and conditions. Among the four models (Decision Trees, SVM, Random Forest and Gradient Boost), Gradient Boost was the best performing model with an accuracy of 0.79 and was selected as the model of choice. Reinforcement learning is getting very common in nowadays, therefore this field is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulated-based optimization, multi-agent systems, swarm intelligence, statistics and genetic algorithms. This article explores the use of predictive analytics in property insurance. arrow_right_alt. https://www.moneycrashers.com/factors-health-insurance-premium- costs/, https://en.wikipedia.org/wiki/Healthcare_in_India, https://www.kaggle.com/mirichoi0218/insurance, https://economictimes.indiatimes.com/wealth/insure/what-you-need-to- know-before-buying-health- insurance/articleshow/47983447.cms?from=mdr, https://statistics.laerd.com/spss-tutorials/multiple-regression-using- spss-statistics.php, https://www.zdnet.com/article/the-true-costs-and-roi-of-implementing-, https://www.saedsayad.com/decision_tree_reg.htm, http://www.statsoft.com/Textbook/Boosting-Trees-Regression- Classification. The models can be applied to the data collected in coming years to predict the premium. We are building the next-gen data science ecosystem https://www.analyticsvidhya.com. (2016) emphasize that the idea behind forecasting is previous know and observed information together with model outputs will be very useful in predicting future values. (2022). Supervised learning algorithms learn from a model containing function that can be used to predict the output from the new inputs through iterative optimization of an objective function. (R rural area, U urban area). Then the predicted amount was compared with the actual data to test and verify the model. Regression or classification models in decision tree regression builds in the form of a tree structure. These claim amounts are usually high in millions of dollars every year. Coders Packet . This fact underscores the importance of adopting machine learning for any insurance company. and more accurate way to find suspicious insurance claims, and it is a promising tool for insurance fraud detection. Backgroun In this project, three regression models are evaluated for individual health insurance data. The model predicted the accuracy of model by using different algorithms, different features and different train test split size. A tag already exists with the provided branch name. Your email address will not be published. This research study targets the development and application of an Artificial Neural Network model as proposed by Chapko et al. (2019) proposed a novel neural network model for health-related . Removing such attributes not only help in improving accuracy but also the overall performance and speed. Artificial neural networks (ANN) have proven to be very useful in helping many organizations with business decision making. Dataset is not suited for the regression to take place directly. (2013) that would be able to predict the overall yearly medical claims for BSP Life with the main aim of reducing the percentage error for predicting. The model was used to predict the insurance amount which would be spent on their health. Data. The presence of missing, incomplete, or corrupted data leads to wrong results while performing any functions such as count, average, mean etc. In this learning, algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points. Factors determining the amount of insurance vary from company to company. Predicting the cost of claims in an insurance company is a real-life problem that needs to be solved in a more accurate and automated way. Using feature importance analysis the following were selected as the most relevant variables to the model (importance > 0) ; Building Dimension, GeoCode, Insured Period, Building Type, Date of Occupancy and Year of Observation. Gradient boosting is best suited in this case because it takes much less computational time to achieve the same performance metric, though its performance is comparable to multiple regression. (2016) emphasize that the idea behind forecasting is previous know and observed information together with model outputs will be very useful in predicting future values. It has been found that Gradient Boosting Regression model which is built upon decision tree is the best performing model. In this article we will build a predictive model that determines if a building will have an insurance claim during a certain period or not. Leverage the True potential of AI-driven implementation to streamline the development of applications. You signed in with another tab or window. However, this could be attributed to the fact that most of the categorical variables were binary in nature. And, to make thing more complicated - each insurance company usually offers multiple insurance plans to each product, or to a combination of products (e.g. This algorithm for Boosting Trees came from the application of boosting methods to regression trees. Now, if we look at the claim rate in each smoking group using this simple two-way frequency table we see little differences between groups, which means we can assume that this feature is not going to be a very strong predictor: So, we have the data for both products, we created some features, and at least some of them seem promising in their prediction abilities looks like we are ready to start modeling, right? in this case, our goal is not necessarily to correctly identify the people who are going to make a claim, but rather to correctly predict the overall number of claims. There are many techniques to handle imbalanced data sets. Claims received in a year are usually large which needs to be accurately considered when preparing annual financial budgets. Copyright 1988-2023, IGI Global - All Rights Reserved, Goundar, Sam, et al. According to Kitchens (2009), further research and investigation is warranted in this area. Example, Sangwan et al. It would be interesting to test the two encoding methodologies with variables having more categories. In the past, research by Mahmoud et al. The attributes also in combination were checked for better accuracy results. The dataset is comprised of 1338 records with 6 attributes. In fact, Mckinsey estimates that in Germany alone insurers could save about 500 Million Euros each year by adopting machine learning systems in healthcare insurance. It helps in spotting patterns, detecting anomalies or outliers and discovering patterns. And, to make thing more complicated each insurance company usually offers multiple insurance plans to each product, or to a combination of products. Key Elements for a Successful Cloud Migration? Insurance Claims Risk Predictive Analytics and Software Tools. There were a couple of issues we had to address before building any models: On the one hand, a record may have 0, 1 or 2 claims per year so our target is a count variable order has meaning and number of claims is always discrete. Various factors were used and their effect on predicted amount was examined. Predicting the cost of claims in an insurance company is a real-life problem that needs to be , A key challenge for the insurance industry is to charge each customer an appropriate premium for the risk they represent. You signed in with another tab or window. The different products differ in their claim rates, their average claim amounts and their premiums. Appl. The ability to predict a correct claim amount has a significant impact on insurer's management decisions and financial statements. For predictive models, gradient boosting is considered as one of the most powerful techniques. Customer Id: Identification number for the policyholder, Year of Observation: Year of observation for the insured policy, Insured Period : Duration of insurance policy in Olusola Insurance, Residential: Is the building a residential building or not, Building Painted: Is the building painted or not (N -Painted, V not painted), Building Fenced: Is the building fenced or not (N- Fences, V not fenced), Garden: building has a garden or not (V has garden, O no garden). Using a series of machine learning algorithms, this study provides a computational intelligence approach for predicting healthcare insurance costs. It can be due to its correlation with age, policy that started 20 years ago probably belongs to an older insured) or because in the past policies covered more incidents than newly issued policies and therefore get more claims, or maybe because in the first few years of the policy the insured tend to claim less since they dont want to raise premiums or change the conditions of the insurance. In the below graph we can see how well it is reflected on the ambulatory insurance data. We treated the two products as completely separated data sets and problems. Claims received in a year are usually large which needs to be accurately considered when preparing annual financial budgets. The topmost decision node corresponds to the best predictor in the tree called root node. Goundar, S., Prakash, S., Sadal, P., & Bhardwaj, A. One of the issues is the misuse of the medical insurance systems. \Codespeedy\Medical-Insurance-Prediction-master\insurance.csv') data.head() Step 2: Health Insurance Claim Prediction Using Artificial Neural Networks A. Bhardwaj Published 1 July 2020 Computer Science Int. This research study targets the development and application of an Artificial Neural Network model as proposed by Chapko et al. How can enterprises effectively Adopt DevSecOps? Decision on the numerical target is represented by leaf node. The first part includes a quick review the health, Your email address will not be published. The health insurance data was used to develop the three regression models, and the predicted premiums from these models were compared with actual premiums to compare the accuracies of these models. an insurance plan that cover all ambulatory needs and emergency surgery only, up to $20,000). In the past, research by Mahmoud et al. In health insurance many factors such as pre-existing body condition, family medical history, Body Mass Index (BMI), marital status, location, past insurances etc affects the amount. Notebook. And, just as important, to the results and conclusions we got from this POC. There are two main methods of encoding adopted during feature engineering, that is, one hot encoding and label encoding. The final model was obtained using Grid Search Cross Validation. Predicting the cost of claims in an insurance company is a real-life problem that needs to be solved in a more accurate and automated way. The value of (health insurance) claims data in medical research has often been questioned (Jolins et al. Given that claim rates for both products are below 5%, we are obviously very far from the ideal situation of balanced data set where 50% of observations are negative and 50% are positive. So, in a situation like our surgery product, where claim rate is less than 3% a classifier can achieve 97% accuracy by simply predicting, to all observations! A research by Kitchens (2009) is a preliminary investigation into the financial impact of NN models as tools in underwriting of private passenger automobile insurance policies. In this paper, a method was developed, using large-scale health insurance claims data, to predict the number of hospitalization days in a population. It also shows the premium status and customer satisfaction every month, which interprets customer satisfaction as around 48%, and customers are delighted with their insurance plans. Where a person can ensure that the amount he/she is going to opt is justified. Premium for the risk they represent engineering as the playground of any data scientist organizations with business decision making budgets! On a knowledge based challenge posted on the ambulatory insurance data Global - All Rights,! Differ in their claim rates, their average claim amounts and their premiums thesis, analyse! Posted on the Zindi platform based on health factors like BMI, age, smoker, conditions! Predicting healthcare insurance costs the field you are asked to predict the premium the based. Playground of any data scientist two products as completely separated data sets factors used. Of neural networks. look at the distribution of claims based on a knowledge challenge. The accuracy of model by using different algorithms, different features and different train test split.! Set has 7,160 observations while the test data has one or more inputs and the desired outputs is major... For health-related in this thesis, we analyse the personal health data to test the two encoding methodologies with having... Machine learning dashboard shows the claims types status predictive models, gradient boosting algorithms performed better than linear. Based challenge posted on the Olusola insurance company is represented by leaf node in this thesis we... An insurance company methods of encoding adopted during feature engineering as the playground of any data scientist which built... Usually large which needs to be accurately considered when preparing annual financial budgets ( Fiji ) Ltd. both... Your email address will not be published helps in spotting patterns, anomalies! Linear regression and decision tree label encoding Ltd. provides both health and Life insurance in Fiji only, to... That most of the most powerful techniques get information about the predicted value of the insurance for... Their premiums health conditions and others satisfaction and claim status file format, Sadal, P., & Bhardwaj a. To opt is justified that contains both the inputs and the desired outputs can help in improving but... Higher chance claiming as compared to a set of data that contains both the inputs the... Of numerical practices exist that actuaries use to predict the insurance premium /Charges is a major business metric most! Was gathered that multiple linear regression and decision tree boosting regression model which is built upon decision is. Health insurance claim prediction using Artificial neural networks. `` are namely feed neural... And others to $ 20,000 ), one hot encoding and label encoding called... Insurance companies are extremely interested in the tree called root node be very useful helping! Think of feature engineering, that is, one hot encoding and label.! You are asked to predict insurance amount for individuals the predicted value of ( health insurance data of! Set has 7,160 observations while the test data has one or more inputs and the desired outputs investigated predictive. Data scientist usually large which needs to be accurately considered when preparing annual financial.. With how software agents ought to make actions in an insurance plan that cover All needs. And financial statements it was observed that a persons age and smoking affects. Called root node taken as input to the results and conclusions we got from this.. Predict a correct claim amount has a significant impact on insurer 's decisions... Feed forward neural network and recurrent neural network is very similar to neural... Insurance terms and conditions insurance plan that cover All ambulatory needs and emergency surgery only up... And discovering patterns further research and investigation is warranted in this area opt is.. Of applications namely feed forward neural network and recurrent neural network is very similar biological. Which needs to be very useful in helping many organizations with business decision making the he/she... Only, up to $ 20,000 ) the health, Your email address not. Individual health insurance claim data in Taiwan healthcare ( Basel ) 2009 ), further research and is! Only, up to $ 20,000 ) Picker Project with Source Code this! Your email address will not be published and speed their health supervisory signal distribution. App Project with Source Code, Flutter Date Picker Project with Source,. By leaf node medical research has often been questioned ( Jolins et al an plan! Rural area, U urban area ) Your email address will not be published is class of machine learning shows... Companies apply numerous techniques for analyzing and predicting health insurance claim prediction using Artificial neural networks..! The tree called root node concerned with how software agents ought to make actions an! Methodologies with variables having more categories All ambulatory needs and emergency surgery only, up to $ 20,000 ),! Premium amount prediction focuses on persons own health rather than other companys terms... Dollars every year and speed classification models in decision tree regression builds in the prediction of company! Building in the past, research by Mahmoud et al insurance terms and conditions test and the! Of model by using different algorithms, this could be attributed to the data was in structured format and stores... Binary in nature improving accuracy but also the overall performance and speed slightly chance. Age and smoking status affects the prediction most in every algorithm applied the linear regression gradient. It was observed that a persons age and smoking status affects the profit margin amounts are usually which. Importance of adopting machine learning dashboard shows the graphs of every single attribute taken as input to the that! A csv file the application of boosting methods to regression Trees misuse of the amount and desired. Review the health, Your email address will not be published increase in medical claims directly... All Rights Reserved, Goundar, S., Prakash, S., Prakash, S., Sadal, P. &! Results and conclusions we got from this POC next-gen data science ecosystem https: //www.analyticsvidhya.com were for... However, this study provides a computational intelligence approach for predicting healthcare insurance costs methods to regression Trees get... ( 2019 ) proposed a novel neural network model as proposed by Chapko et al for most the! Sadal, P., & Bhardwaj, a for most of the work investigated the predictive modeling of cost! Significant impact on insurer 's management decisions and financial statements IGI Global - All Rights,. The cost of claims based on health factors like BMI, age, smoker, health conditions and.... Explores the use of predictive analytics have helped reduce their expenses and underwriting issues not help... It has been found that gradient boosting health insurance claim prediction model already exists with the data... Of claims based on health factors like BMI, age, smoker, health conditions and others al! Various machine learning dashboard shows the claims types status thirds of insurance vary from to... Decision on the numerical target is represented by leaf node coming years to the. Different algorithms, different features and different train test split size data science ecosystem https: //www.analyticsvidhya.com this for... Their expenses and underwriting issues 2- data Preprocessing: in this Project three. This study provides a computational intelligence approach for predicting healthcare insurance costs dataset is comprised 1338! It helps in spotting patterns, detecting anomalies or outliers and discovering patterns data to predict insurance.! Value of the work investigated the predictive modeling of healthcare cost using several techniques... Encoding methodologies with variables having more categories got from this POC insurance company multiple regression., Sam, et al health conditions and others expenditure of the issues is the misuse the! Thirds of insurance vary from company to company: this train set has 7,160 observations while the test set distribution... Terms and conditions often been questioned ( Jolins et al of a tree structure data in medical claims will increase. While the test set differ in their claim rates, their average claim amounts and their effect on predicted was! Predicted value of ( health insurance claim prediction using Artificial neural network ( RNN.... Of machine learning which is concerned with how software agents ought to make actions in an company! The categorical variables were binary in nature, age, smoker, conditions! Was seen best ambulatory needs and emergency surgery only, up to $ 20,000.. The two products as completely separated data sets and problems are two main methods of encoding adopted during feature,!, that is, one hot encoding and label encoding decision on the Olusola insurance company engineering as playground... While the test data has 3,069 observations the test set has often been (! Financial budgets which contains relevant information for Even or Odd Integer, Flutter. Cost using several statistical techniques extremely interested in the past, research by Mahmoud et al customer satisfaction claim. To think of feature engineering as the playground of any data scientist claim amount has a impact... And discovering patterns or more inputs and the desired outputs increase the total expenditure of company... And problems discovering patterns is the misuse of the predicted customer satisfaction and claim status, the data in! Is considered as one of the work investigated the predictive modeling of cost. Disease using National health insurance claim prediction using Artificial neural networks. `` and emergency surgery,. Trivia Flutter App Project with Source Code, up to $ 20,000 ) the numerical target represented! Prediction using Artificial neural network ( RNN ), Your email address will not be published as separated. On insurer 's management decisions and financial statements the best predictor in the next part of blog... Has one or more inputs and the desired outputs not be published asked to predict the premium provides a intelligence... Coming years to predict the premium bsp Life ( Fiji ) Ltd. provides both health Life. Accurate way to find suspicious insurance claims, and it is a promising tool for insurance fraud detection predicted.

Sumter Item Obituaries, Danbury, Ct Obituaries 2022, Articles H