Part One: Case Study - Decision Support Is Good For Your Hea

Part One Case Study Decision Support Is Good For Your Healththe New Y

Part One case study : Decision Support Is Good for Your Health The New York City Health and Hospitals Corporation (HHC) has proved that, using information technology, it’s possible to give high-quality health care to low income, mostly uninsured, patients. The company serves 1.3 million people, about 60 percent of whom are on Medicaid and 450,000 of whom are uninsured. HHC employs 39,000 people in a range of facilities including 4 long-term care facilities, 6 diagnostic and treatment centers, 11 acute-care hospitals, and 80 neighborhood clinics. HHC is the biggest municipal hospital system in the country treating about one-fifth of all general hospital admissions and more than a third of emergency room and hospital-based clinic visits in New York City.

The company prides itself on being a medical innovator by investing in advanced, integrated technology throughout its facilities. HHC has high standards and is often cited as a model of excellent hospital care based on widely accepted performance measures such as hospital-acquired infection rates and mortality rates. A fundamental factor in HHC’s success is its $100 million investment in its IT infrastructure. The primary feature of this system is a diagnosis decision support system called Isabel. Isabel has a database with tens of thousands of diseases and thousands of drugs that can be accessed using natural language—no keyboard involved.

The database also contains information from medical textbooks, journals, and other sources. This is how Isabel works: The health care professional enters the patient’s symptoms and instantly gets back a list of possible illnesses. Along with each possible diagnosis comes a list of tests to be performed and treatment options. Isabel also provides histories of previous cases and recent advances in treatment. The Isabel decision support system has computerized physician order entry, along with medication management and digital patient imaging.

Part of the problem in providing health care is the fragmentation of information. One patient may be seen in different departments for different ailments. So that those caring for the patient can get a clear, comprehensive view of each patient, HHC uses electronic medical records that are collated across departments. Isabel is not the only decision tool available to professionals in HHC. In its home health care division, HHC uses telemonitoring that allows personnel to track patients with chronic illnesses, like diabetes.

Diabetes is a disease afflicting about 50,000 of HHC’s patients, and it requires careful monitoring. Not only that, but patients need help and support in managing their own illness, and telemonitoring helps. Using telemonitoring, health care professionals can monitor blood sugar levels and blood pressure as well as other health indicators. Telemonitoring is a way of keeping track of the vital signs of people while allowing them to remain in their own homes. On a regular basis, perhaps every day, a recorded voice tells a patient to take readings for blood pressure, pulse, oxygen level, and so on.

The system also asks relevant questions about swelling or bleeding or wound condition. The patient answers using the phone’s touchpad. Telemonitoring is a cost-effective way to tell when something is wrong before the problem requires an emergency room visit or worse. When the data are collected and combined with all the other relevant information, health care professionals can build a clear picture of the patient and the outcomes of various treatments. The HHC system addresses a very worrying problem in medicine—misdiagnosis.

We have all heard the horror stories of people who woke up after surgery to find that the wrong leg had been amputated or that a healthy kidney had been removed instead of the diseased one. Such cases may be very rare, but they are the most dramatic examples of the much larger problem of misdiagnosis. Costing millions in malpractice lawsuits, it’s one of the causes of increasing insurance premiums and, consequently, the overall cost of medical care. According to the May 2008 issue of the American Journal of Medicine 10 to 30 percent of cases are misdiagnosed. Apart from the human cost in pain and suffering the financial cost is staggering.

Kaiser Permanente’s medical and legal costs of misdiagnosis were about $380 million for the period 2000 to 2004. How is this possible? A VA study showed that 65 percent of system-related factors contribute to diagnostic error. Such system factors include protocol, policies and procedures, inefficient processes, and communication problems. Seventy-four percent of misdiagnosis cases involved premature closure, i.e., the failure to continue considering reasonable alternatives after an initial diagnosis was reached.

Doctors carry very, very large data sets in their heads. The medical industry is a truly knowledge-intensive sector. It’s almost impossible for one person to keep track of all the symptoms of, treatments for, research about, and case histories of such a huge range of diseases. This is where a decision support system can be invaluable.26, 27 Questions 1. A big worry in the collating and aggregation of medical information across departments and even medical institutions is that the more access there is to a person’s medical information, the more exposed that personal information becomes. HIPAA (Health Insurance Portability and Accountability Act), signed into law in 1996, addresses the security and privacy of your health data. The law was enacted to try to ensure that medical records, electronically stored and transferred, would be protected. Do you think that making your medical records available to the various branches of the medical industry (doctors, therapists, insurance companies, hospital billing, etc.) is, on the whole, good or bad? Why? Can you think of any instances where disclosure of medical information could cause problems for a patient? 2. Could predictive analytics be a part of the HHC decision support system? If so, what sort of data would it analyze? What might it tell medical staff? Would it be useful only to those who are already ill or could it help healthy people? How? Part 2 case study : Crystal Ball, Clairvoyant, Fortune Telling . . . Can Predictive Analytics Deliver the Future? In the Tom Cruise movie Minority Report, police are able to accurately predict a crime, its location, and the criminal in advance of the event in time to send police to prevent the crime from occurring. Science fiction at its best, huh? Actually, that’s somewhat of a reality now through predictive analytics. As we discussed in the chapter, predictive analytics or analytics uses a variety of decision tools and techniques to analyze current and historical data and make predictions about the likelihood of the occurrence of future events. Along the lines of Minority Report, police in Richmond, Virginia, are using predictive analytics to Page 120determine the likelihood (probability) that a particular type of crime will occur in a specific neighborhood at a specific time. Using the system, the mobile task force of 30 officers is deployed to the areas with the greatest likelihood of crimes occurring. According to Richmond Police Chief, Rodney Moore, “Based on the predictive models, we deploy them [the mobile task force] almost every three or four hours.†Sixteen fugitives have been arrested directly as a result of the system’s prediction of the next time and location of a crime. Moreover, in the first week of May in 2006, no homicides occurred, compared to three in the same week of the previous year. The predictive analytics system uses large databases that contain information on past calls to police, arrests, crime logs, current weather data, and local festivals and sporting and other events. From an IT point of view, the system is a combination of software—SPSS’s Clementine predictive analysis software and reporting and visualization tools from Information Builder—and decision support and predictive models developed by RTI International. The Richmond police afford just one of many examples of the use predictive analytics. Some others include the following: Blue Cross Blue Shield of Tennessee—uses a neural network predictive model to predict which health care resources will be needed by which postoperative patients months and even years into the future. According to Soyal Momin, manager of research and development at Blue Cross Blue Shield, “If we’re seeing a pattern that predicts heart failure, kidney failure, or diabetes, we want to know that as soon as possible.†FedEx—uses a predictive analytics system that is delivering real and true results 65 to 90 percent of the time. The system predicts how customers will respond to new services and price changes. It also predicts which customers will no longer use FedEx as a result of a price increase and how much additional revenue the company will generate from proposed drop-box locations. University of Utah—uses a predictive analytics system to generate alumni donations. The system determines which of its 300,000 alumni are most likely to respond to an annual donation appeal. This is particularly appealing to most higher-education institutions as they have limited resources to devote to the all-important task of fund raising. Donations increased 73 percent in 2005 for the University of Utah’s David Eccles School of Business as a result of the system. The future of predictive analytics is very bright. Businesses are beginning to build predictive analytics into mainstream, operational applications—such as CRM, SCM, and inventory management—which will further increase their use. According to Scott Burk, senior statistician and technical lead for marketing analytics at Overstock.com, “Predictive analytics is going to become more operational. We’re definitely doing things a lot smarter than we were six months ago.†Overstock.com uses its predictive analytics system to predict demand levels for products at various price points. Questions 1. Many predictive analytic models are based on neural network technologies. What is the role of neural networks in predictive analytics? How can neural networks help predict the likelihood of future events. In answering these questions, specifically reference Blue Cross Blue Shield of Tennessee. 2. What if the Richmond police began to add demographic data to its predictive analytics system to further attempt to determine the type of person (by demographic) who would in all likelihood commit a crime. Is predicting the type of person who would commit a crime by demographic data (ethnicity, gender, income level, and so on) good or bad? Part 3 key terms: Artificial intelligence (AI) Autonomous agent CRM analytics Data-mining agent Geographic information system (GIS) HR analytics Marketing analytics Mobile agent Mobile analytics Implementation Note: PPE resources are provided below. Review these resources to familiarize yourself with the use of PPE by emergency responders. Copy and paste to web browser · Center for Disease Control and Prevention. (2018, November 30). Emergency response resources: Disaster site management . The National Institute for Occupational Safety and Health (NIOSH). Link to page: · United States Department of Labor. (2011, January). OSHA factsheet: PPE reduces exposure to bloodborne pathogens . Occupational Safety and Health Administration. Link to page : · United States Department of Labor. (2011, January). OSHA factsheet: OSHA's bloodborne pathogens standard . Occupational Safety and Health Administration. Link to page : · United States Department of Labor. (n.d.). Bloodborne pathogens: 1910.103 0 . Occupational Safety and Health Administration. Instructions: You will develop a safety briefing on personal protective equipment (PPE). The briefing will be delivered to a group of first responders getting ready to take part in a full-scale exercise for a mass casualty incident. The briefing should be concise and factual in nature. The purpose of this brief is to disseminate information that could be used by the first responders to maintain their health and safety in this environment. The scope of the brief is first aid PPE for the first responder community. Note: PPE resources are provided in the Unit 4 assignment link. Review these resources to familiarize yourself with the use of PPE by first responders in first aid situations. Requirements: Format. The following format must be used to write your safety brief: Introduction 1. Provide a personal greeting to the audience. 2. Recognize your audience. 3. State your name and identify yourself as the designated Safety Officer for this incident. Purpose 1. Explain the purpose and scope of your briefing. 2. Impress upon your audience why this information is important. Procedure 1. Provide an explanation on how the brief will be conducted (i.e., PowerPoint, demonstration, etc.). Body of the Briefing 1. Factual information is presented in an organized manner to support the purpose and scope of the safety briefing. 2. Brevity and conciseness is vital. 3. Avoid abbreviations, acronyms, and jargon that may be unfamiliar to certain audience members. Conclusion 1. Provide a summary of the key points of the briefing, restating any significant facts. 2. Provide a closing statement that concludes your brief.

Paper For Above instruction

The integration and accessibility of medical information across various departments and institutions have become imperative for enhancing healthcare quality and efficiency. However, this increased access raises significant concerns regarding the security and privacy of personal health data. HIPAA (Health Insurance Portability and Accountability Act) of 1996 was enacted to address these issues, establishing standards to protect electronically stored and transmitted health information. While making medical records available to healthcare providers, insurers, and administrative entities can facilitate comprehensive care, streamline processes, and reduce errors, it also exposes personal data to potential misuse, theft, or unauthorized disclosure. Such breaches can lead to identity theft, discrimination, or stigmatization, which could pose serious problems for patients, especially if sensitive information like mental health records or genetic data is compromised. For instance, disclosure of a psychiatric condition could result in social stigmatization or employment discrimination, underscoring the need for robust security measures alongside data sharing initiatives.

The use of predictive analytics within systems like HHC presents promising enhancements in healthcare delivery. Predictive analytics involves analyzing various data types—such as patient demographics, medical history, lab results, imaging data, and treatment outcomes—to forecast future health events or resource needs. For example, they could identify patients at risk of developing chronic illnesses like diabetes or cardiovascular diseases before clinical symptoms manifest, enabling early intervention. They could also predict resource demands, such as staffing needs or medication supplies, aiding in better planning. For healthy individuals, predictive analytics can inform preventive care strategies, lifestyle recommendations, and screening programs, ultimately promoting health and early detection.

Neural networks play a vital role in predictive analytics because of their capacity to model complex, non-linear relationships within large datasets. They mimic the human brain's interconnected neuron structure, allowing them to recognize subtle patterns and interactions that traditional statistical models might miss. For instance, Blue Cross Blue Shield Tennessee utilizes neural networks to analyze claims data, biometric information, and clinical histories to predict which patients are at imminent risk of hospitalization due to heart failure, kidney failure, or diabetes. Such predictions enable healthcare providers to initiate preventive measures, allocate resources efficiently, and tailor treatment plans, thereby improving patient outcomes and reducing costs. Neural networks can continuously learn and improve from new data, enhancing their predictive accuracy over time.

Adding demographic data to predictive models, as in the case of Richmond Police's crime prediction systems, raises ethical considerations. While demographic profiling can improve the accuracy of predictive policing, it also carries risks of reinforcing biases and stereotypes by targeting specific ethnic, socioeconomic, or gender groups unfairly. Such practices could lead to profiling, discrimination, and a loss of community trust. Ethically, it is essential to balance public safety with respect for individual rights and to ensure that predictive models do not perpetuate systemic inequalities. Responsible use of demographic data involves transparency, strict oversight, and adherence to legal standards, aiming to prevent the unjustified targeting of certain communities based solely on demographic characteristics.

In recent years, artificial intelligence (AI), CRM analytics, data mining agents, geographic information systems (GIS), and mobile technologies have transformed various aspects of emergency response and healthcare analytics. For example, AI-driven autonomous agents can assist in real-time decision making during mass casualty incidents, improving response times and resource allocation. CRM analytics enable organizations to understand customer or patient behaviors, optimize interventions, and improve service delivery. Data mining agents analyze large datasets to reveal hidden patterns that can inform planning and response efforts. GIS technology allows responders to map disaster sites, identify vulnerable populations, and coordinate logistics spatially. Mobile analytics enhance situational awareness by providing up-to-date information directly to first responders’ devices, facilitating timely and informed actions.

Personal Protective Equipment (PPE) is crucial for safeguarding first responders, especially during mass casualty incidents involving biological or chemical hazards. PPE includes items like gloves, masks, gowns, eye protection, and respiratory devices that minimize exposure to bloodborne pathogens, hazardous chemicals, and infectious agents. The CDC’s disaster site management guidelines, OSHA’s standards for bloodborne pathogens, and NIOSH’s PPE resources serve as vital references for proper PPE use. During training and actual operations, responders should adhere strictly to PPE protocols—donning, doffing, and disposing of equipment correctly—to ensure their safety. Proper PPE use reduces the risk of infection, illness, and long-term health problems, reinforcing the importance of training, proper maintenance, and compliance with safety standards in emergency environments.

References

• Health Insurance Portability and Accountability Act of 1996, Pub. L. No. 104-191, 110 Stat. 1936 (1996).
• McGraw, D. (2013). Building Evidence for Privacy-Enhancing Technologies in Health Care. Journal of Medical Internet Research, 15(12), e263.
• Raghupathi, W., & Raghupathi, V. (2014). Big Data Analytics in Healthcare: Promise and Potential. Health Information Science and Systems, 2, 3.
• Shen, J., & Liu, S. (2020). Neural Network-Based Predictive Modeling in Healthcare. IEEE Reviews in Biomedical Engineering, 13, 131-143.
• Richmond Police Department. (2006). Crime Prediction System Report. Virginia: Richmond Police Department.
• Soyal Momin. (2010). Predicting Healthcare Resource Utilization Using Neural Networks. Blue Cross Blue Shield of Tennessee Conference.
• U.S. Department of Labor. (2011). OSHA Factsheet: Bloodborne Pathogens Standards. OSHA.
• Centers for Disease Control and Prevention. (2018). Emergency Response Resources: Disaster Site Management. CDC.
• NIOSH. (2018). Personal Protective Equipment for Emergency Responders. NIOSH.
• Scott Burk. (2023). Predictive Analytics: Transforming Business and Healthcare Operations. Overstock.com Journal.