Saturday, December 31, 2022

Annual Reflections at the End of 2022

I am keeping my tradition in this blog this year of ending the calendar year with a retrospective on the past year and some musings looking forward.

Clearly our lives were still dominated in 2022 by the COVID-19 pandemic. While a fair amount of living has returned to relative normal, there are some changes that will likely never fully reverse. Certainly a major one for myself and my immediate co-workers is the likely continuation of mostly remote work.

Looking back, my last annual year-end post from the "before times" was in 2019. It was an ordinary post, discussing the history of the blog starting from the times of the passage of the HITECH Act, along with the continued growth of my teaching and use of Twitter. I noted over 2600 people having completing the 10x10 course and my surpassing 2600 followers on Twitter. Now at the end of 2022, 10x10 has exceeded 3100 people completing the course and my Twitter followers number over 3500. Of course, with the recent acquisition of Twitter by Elon Musk, the future of this platform is uncertain. That is unfortunate, since I find activities like #ScienceTwitter and #MedTwitter very helpful for keeping up with new advances, some of which informs my teaching.

The day of that 2019 year-end post was the day that the first case of SARS-CoV2 infection was documented in China. Within a month cases started appearing in the US, and by March, the general US lockdown began, with the transition to remote work. While we have made great progress in treatments and vaccinations for COVID-19, my work is still mostly remote. In reality, this is an extension of pre-pandemic times, when I even noted then that my work was mostly asynchronous. And it is not hard to see how it will likely continue mostly that way, as there are plenty of advantages to my office commute being the walk down the stairs to my home office in my basement. I also enjoy being able to do my daily exercise (running or gym) in the late morning, followed by a healthy lunch, and then some quiet meditation after lunch before getting back to work. In the early days of pandemic, the Internet was highly overtaxed in my neighborhood of many professionals working from home, but the infrastructure has been built up such that my current home Internet is well up to the task.

Back to this year, it was a good year for my professional and personal life. I made the decision to hand off the leadership of the department I have served as the one and only Chair. The Dean of the OHSU School of Medicine will make an announcement of the appointment of a new Interim Chair next week. As noted in my kudos posting from last week, my research and teaching work was highly productive in 2022, and the activities and grant funding will keep it going for at least several more years. I aim to keep working focused on research, teaching, mentoring, and writing, and have no plans to retire any time soon. I will also maintain this blog, which with this posting now has 375 postings.

As for the future, COVID-19 will continue to impact all of what we do. But there is less fear to have now, as we understand the virus and the disease it causes much better, and we have means to blunt the worst of its effects. Many quip that I have an optimistic view of the world and future, and I am certain this will continue in 2023 including and beyond COVID-19.

Monday, December 19, 2022

Kudos for the Informatics Professor - 2022 Update

The year 2022 was a highly productive one for the Informatics Professor, and I am pleased to provide my periodic update of my recent accomplishments. This year had another big event in my decision to step down as the one and only Chair of the Oregon Health & Science University (OHSU) Department of Medical Informatics & Clinical Epidemiology. More will be posted about that when my successor is named. Meanwhile, here are my accomplishments for 2022.

I received two prominent awards this year. One was from the American Medical Informatics Association (AMIA), my main professional association, for the William Stead Award for Thought Leadership in Informatics. This award "acknowledges people who have influenced our thinking about informatics, especially improving health and health care in ways that are visionary and transformative." This year I was also elected to the second class of the ACM SIGIR Academy, which was established to "honor and recognize individuals who have made significant, cumulative contributions to the development of the field of information retrieval (IR)." I am thrilled to be honored by the two fields of which I work at the intersection between them.

This year I completed my term as the Second President of the International Academy of Health Sciences Informatics (IAHSI). I will continue for another two years as Past President.

In 2022, I was awarded several new grants, which will help sustain the research and teaching that I plan to continue as I reduce my administrative and leadership roles. Probably the most important of these was the OHSU Training Grant in Biomedical Informatics and Data Science, which was renewed for another five year cycle through 2027. This training grant from the National Library of Medicine (NLM) of the National Institutes of Health (NIH) funds predoctoral (PhD) and postdoctoral trainees in the OHSU Biomedical Informatics Graduate Program. This grant has been funded continuously at OHSU since 1992. This renewal marks the seventh consecutive five-year cycle of funding for OHSU. Its first 30 years make it the second-longest-running training grant at OHSU. The grant's total funding over that time of $21,912,538 make it the largest training grant ever at OHSU. I myself am a product of this training grant, completing my postdoctoral fellowship at Harvard University from 1987-1990.

Another grant from the NLM for which I am PI is an R25 grant to fund the OHSU Biomedical Informatics and Data Science College Undergraduate Summer Internship Program for five years. The grant is among 12 awards issued by the National Library of Medicine to prepare historically underrepresented students for biomedical informatics and data science graduate studies and research careers. The goal of the our program is to provide a rich, full-time experience to students to graduate study and careers in biomedical informatics and data science. In addition, the program aims to motivate students to pursue doctoral training in biomedical informatics and data science that leads to research careers in academia, government, healthcare, and industry. The funding from the R25 grant will be used to support summer experiences for students with backgrounds that have been historically underrepresented in biomedical informatics and data science.

A final new grant for 2022 was from the new NIH Bridge2AI Initiative. I am among a group of faculty from OHSU and Washington University who will be serving as the Skills and Workforce Development Module for one of the four funded data-acquisition projects. The project we are part of will focus on creating data sets that aim to use voice as a biomarker of health.

I also had a good year of publications in 2022, not the least of which was the release of the 8th edition of Health Informatics: Practical Guide, in which I serve as Editor and have authored about a third of the chapters. My journal publications for 2022 included the following:

In 2022, I was also a guest on a couple of podcasts. One was to provide an introduction to an episode on of the For Your Informatics podcast on the gender pay gap among physicians, including those in informatics. The other was to be interviewed for the IAHSI podcast on Exploring Healthcare Interoperability about my work in teaching about healthcare data standards and interoperability.

I also gave a number of invited talks in 2022:

  • Biomedical and Health Informatics: Impact, Challenges, and Opportunities, Nevada Institute of Personalized Medicine, University of Nevada Las Vegas (virtual), January 27, 2022 (slides and references)
  • Competencies and Curricula Across the Spectrum of Learners for Health Informatics, Keynote Talk, IEEE International Conference on Healthcare Informatics, First International Workshop on Health Informatics Education, Rochester, MN, June 11, 2022 (slides and references)
  • Translational Artificial Intelligence (AI): The Need to Translate from Basic Science to Clinical Value, University of Alabama Birmingham Informatics Institute (virtual), September 2, 2022 (slides and references and video)
  • Past, Present, and Future: A Discussion About DMICE Going Forward, OHSU Department of Medical Informatics & Clinical Epidemiology, October 6, 2022 (slides and video)
  • Applying Information Retrieval to the Electronic Health Record for Cohort Discovery and Rare Disease Detection, Brown University Center for Biomedical Informatics, Providence, RI, October 13, 2022 (slides and references)
  • Competencies and Curricula Across the Spectrum of Learners for Biomedical and Health Informatics, International Symposium on Achievements, Milestones and Challenges in Biomedical and Health Informatics, Athens, Greece, October 29, 2002 (slides)

In 2022 I also delivered my annual lecture to first-year OHSU medical students, Information is Different Now That You're a Doctor, on September 2, 2022. I also gave this talk to first-year medical students at Nova Southeastern University (virtual) on June 16, 2022.

I additionally attended my 37th consecutive AMIA Annual Symposium, where I participated in three activities:

  • Panel: Beyond Wrangling and Modeling: Data Science and Machine Learning Competencies and Curricula for The Rest of Us
  • Job Talk Panel for the AMIA Clinical Informatics Fellows (ACIF)
  • Debate: Extension of the Practice Pathway for ABMS Clinical Informatics Board Certification for Physicians in the United States

This year I also served as Co-Chair of the Scientific Program Committee of the conference hosted by Brown University, The Patient and The Practitioner in the Age of Technology: Promoting Healing Relationships.

In 2022, I also maintained my various scientific citation rankings. In the list of Best Computer Science Scientists, I now rank 694th in the US and 1183rd in the world based on a discipline-specific H-index they calculate. I also maintain a presence in the latest iteration of a database of the top 100,000 cited scientists in the world for 22 scientific fields and 176 subfields, where I rank 22,553rd based on a composite formula of citation and publishing variables. In the medical informatics subfield, I rank 13th. Of the 290 individuals affiliated with OHSU, I rank 50th. I also maintain my presence on ranking lists based on the Google Scholar h-index for biomedical informatics and information retrieval.

Finally, this blog is mentioned in various lists of best blogs, including the following:

Saturday, December 17, 2022

ChatGPT Postscript

It has been interesting to read all of the uses that colleagues of mine and others have employed to put ChatGPT to the test, in addition to my tests of learning objectives, a biography, and multiple-choice questions. In one email thread, I joked that perhaps ChatGPT is a Rorschach Test of what interests people concerning the use of artificial intelligence.

I also was pointed to an interesting site that bills itself as a ChatGPT (actually trained on an earlier version of the OpenAI model, GPT-2) Output Detector Demo. I pasted my biography from my first post and this system declared the text had a 99.98% chance of being "fake," i.e., from GPT-2. When I paste in in the biographic paragraph from my own Web page, it declares the text to having a 99.97% chance of being real.

Another interesting reflection is to compare ChatGPT with information retrieval (IR, aka search). Perhaps I am biased as an academic, or someone greatly interested in IR since it is my primary focus of research, but usually when I look for information, I not only want to know the information, but also where it comes from and how trustworthy it is. A big limitation for me of ChatGPT is that it cites no references to back up what it says.

This gets to another academic concern about ChatGPT, which is how it will impact assessment of learning. Although ChatGPT seems to work best for relatively short passages of text that do not require references, there are fortunately many other ways to assess learning.

There have also been some good overviews in the news media about ChatGPT, including an interview of ChatGPT itself. There is also a nice description from the New York Times.

Tuesday, December 13, 2022

ChatGPT, Round Two

After sending some comments about my blog post on my initial excursions with ChatGPT earlier this week, I received a great deal of interesting follow-up. One colleague lamented that we may no longer be able to assess the knowledge of students, especially when teaching in online classes, because of their ability to easily generate answers to questions using systems like ChatGPT, especially if they could add to the text by Googling a few references to add to their answers.

I am not convinced of this, at least not with the use of ChatGPT, whose answers I noted were superficial, not completely correct, and not backed up with citations. Furthermore, asking for short answers to questions is hardly the only way to assess knowledge.

So to put ChatGPT to the next test, I pasted in, one by one, the 10 multiple-choice questions I give for the same unit of my introductory informatics course as the learning objectives of my first assessment.
 
While I have to give ChatGPT some credit for figuring out these were multiple-choice questions, it performed pretty poorly compared to most students in the course. It only answered 5 of the 10 questions correctly, and for two it got wrong, it did not even try to answer the questions, giving the excuse it could not browse the Internet (despite being trained on it!).
 
Some of the incorrect answers would be embarrassing even for a beginning informatics student to not know, such as which US government agency funds informatics training, that "meaningful use" was not part of the Affordable Care Act, and that a machine learning algorithm not involving clinicians does not adhere to Friedman's Fundamental Theorem.
 
The transcript of my interactions is pasted in below. The text entered into ChatGPT did not include the question numbers nor the correct answers indicated by asterisks. The paragraph following each question is how ChatGPT replied. My conclusion is that, for now, those of us who teach informatics in virtual settings do not (yet) have to worry about ChatGPT being used to cheat in our courses.

ChatGPT Transcript - December 10, 2022

1. Which part of biomedical and health informatics is most likely to address the critical informatics issues for the practice of a family physician?
a. Bioinformatics
*b. Clinical informatics
c. Clinical research informatics
d. Imaging informatics
e. Public health informatics

Clinical informatics is most likely to address the critical informatics issues for the practice of a family physician. This subfield of biomedical and health informatics focuses on the use of information technology to support the delivery of healthcare and improve patient outcomes. Clinical informatics encompasses a wide range of topics, including electronic health records, health information exchange, clinical decision support, and population health management. It is concerned with the design, development, and implementation of systems and tools to support the clinical work of healthcare professionals, such as family physicians.

2. Before the era of widespread computer use, the typical hospital physician spent what proportion of his or her time in activities away from the patient during office practice?
*a. 23-39%
b. 50%
c. 61-76%
d. 100%

I'm sorry, but I am not able to browse the internet to answer your question as I am a large language model trained by OpenAI. My knowledge is based solely on the text that I have been trained on, which has a cutoff date of 2021. I do not have any additional information beyond what I have been trained on.

3. Which entity of the US government funds research and training in biomedical and health informatics?
a. Agency for Healthcare Research & Quality
b. Center for Medicare and Medicaid Services
c. National Committee for Vital & Health Statistics
*d. National Library of Medicine

The National Institutes of Health (NIH) is the primary entity of the US government that funds research and training in biomedical and health informatics. The NIH is a federal agency that is part of the Department of Health and Human Services. It is the largest biomedical research agency in the world and provides funding for a wide range of research and training programs in the field of biomedical and health informatics. Some examples of NIH-funded programs in this area include the National Library of Medicine's Training and Education in Biomedical Informatics program and the Clinical and Translational Science Awards program, which support research and training in clinical informatics.

4. Before the emergence of the Affordable Care Act, a number of proposed healthcare reform plans for the US would provide for the establishment of a small number of highly regulated private insurance companies in a given region or state. This type of plan would be described by JR Reid as:
a. Beveridge
*b. Bismarck
c. National health insurance
d. Out-of-pocket

The type of healthcare reform plan described in the question, which involves the establishment of a small number of highly regulated private insurance companies in a given region or state, would be described by JR Reid as a Bismarck-type plan. Bismarck-type plans are named after Otto von Bismarck, the 19th century Prussian statesman who introduced the first national health insurance program in the world. Bismarck-type plans are characterized by a high degree of government control over the healthcare system, with the state playing a central role in regulating the provision of healthcare services and financing. In these plans, private insurance companies are typically required to operate within a regulatory framework set by the government, and may be subject to price controls and other forms of regulation. This type of plan is common in many European countries.

5. What proportion of US healthcare spending is devoted to prescription drugs?
*a. 10%
b. 20%
c. 33%
d. 50%

I'm sorry, but I am not able to browse the internet to answer your question as I am a large language model trained by OpenAI. My knowledge is based solely on the text that I have been trained on, which has a cutoff date of 2021. I do not have any additional information beyond what I have been trained on.

6. Compared to most other wealthy countries, the US has which of the following?
a. More hospital days
*b. More money spent
c. More nurses
d. More physicians

Compared to most other wealthy countries, the US has more money spent on healthcare. The US spends more on healthcare as a percentage of its gross domestic product (GDP) than any other country in the world. According to data from the World Health Organization, the US spent 17.2% of its GDP on healthcare in 2018, compared to an average of 9.6% for other high-income countries. This high level of spending is due in part to the relatively high cost of healthcare services in the US, as well as the large number of uninsured and underinsured individuals in the country.

7. Which of the following is not part of the original Affordable Care Act (ACA)?
*a. Incentives for meaningful use of electronic health records
b. Mandate that individuals buy health insurance
c. Outlawing of insurance denial due to pre-existing medical conditions
d. Programs to establish Accountable Care Organizations (ACOs)

Programs to establish Accountable Care Organizations (ACOs) are not part of the original Affordable Care Act (ACA). ACOs are groups of healthcare providers who come together to coordinate care for a specific group of patients, with the goal of improving the quality of care and reducing costs. ACOs were introduced as part of the Medicare program under the Patient Protection and Affordable Care Act of 2010, but were not part of the original ACA legislation. The ACA included a number of other provisions, such as incentives for the meaningful use of electronic health records, a mandate that individuals buy health insurance, and the outlawing of insurance denial due to pre-existing medical conditions.

8. About 50% of US healthcare spending is accounted for by which proportion of the population?
a. 1%
*b. 5%
c. 25%
d. 50%

Approximately 50% of US healthcare spending is accounted for by 5% of the population. This phenomenon, known as the "5/50 rule," refers to the fact that a small proportion of the population accounts for a disproportionate amount of healthcare spending. The 5/50 rule is often used to illustrate the unequal distribution of healthcare costs in the US, with a small group of individuals with chronic conditions or complex healthcare needs accounting for a significant portion of total spending. This pattern is driven in part by the high cost of treating certain conditions, such as cancer and heart disease, as well as the high cost of specialty drugs and other medical technologies.

9. Which of the following applications does not adhere to Friedman’s fundamental theorem of informatics?
*a. A machine learning algorithm that processes radiology images and determines the diagnoses more accurately than a physician
b. A telemedicine system that allows remote interaction via videoconference
c. A reminder system to administer cancer screening exams on an appropriate schedule
d. An information retrieval (search) system that helps the user select terms to improve search results

A telemedicine system that allows remote interaction via videoconference does not adhere to Friedman's fundamental theorem of informatics. The fundamental theorem of informatics, proposed by Edward H. Friedman, states that "the value of medical information is inversely proportional to the time and place of its creation and directly proportional to the time and place of its use." This theorem suggests that the value of medical information decreases as it becomes older and less relevant, and increases when it is used at the time and place where it is needed. A telemedicine system that allows remote interaction via videoconference does not necessarily adhere to this theorem, as it allows healthcare providers to access and use medical information from different times and places. An example of an application that adheres to the theorem would be a reminder system that administers cancer screening exams on an appropriate schedule, as it uses medical information at the time and place where it is needed to improve patient care.

10. A patient undergoing an appendectomy at a hospital near his suburban home is most likely receiving what type of healthcare?
a. Primary care
*b. Secondary care
c. Tertiary care
d. Quaternary care

A patient undergoing an appendectomy at a hospital near his suburban home is most likely receiving secondary care. Secondary care refers to healthcare services that are provided by specialized medical professionals, such as surgeons, specialists, and other healthcare providers. These services are typically provided in hospitals or other specialized medical facilities, and often require referral from a primary care provider. An appendectomy, which is a surgical procedure to remove the appendix, is an example of a medical procedure that is typically performed in a hospital or other specialized medical facility, and would be classified as secondary care. Primary care, on the other hand, refers to the first level of contact between patients and the healthcare system, and typically involves services such as preventive care, routine check-ups, and treatment of minor illnesses. Tertiary care and quaternary care are higher levels of specialized care that are provided for patients with complex or chronic conditions.

Sunday, December 11, 2022

Initial Excursions with ChatGPT

Like many people, I found myself caught up this past week testing out ChatGPT, the new automated chat agent released by OpenAI. It seems like many people across the Internet are using it to test out its functioning in the kind of work they do, whether they are writers, programmers, or my fellow informatics researchers.

Naturally, I tested ChatGPT doing what I enjoy most, namely teaching. My first test was to enter the learning objectives for my well-known introductory biomedical and health informatics course, aka, 10x10 ("ten by ten"). Being the academic that I am, I was also curious what ChatGPT might report for my contributions to the informatics field. The transcript of my interaction is provided below, but first some commentary.

ChatGPT did a much better job with my learning objectives than its report of my accomplishments in informatics. In fact, it got quite a bit wrong about my own work. For example, it reported me as Editor of Journal of the American Medical Informatics Association (JAMIA) and Journal of Medical Internet Research ( JMIR), something my colleagues Sue Bakken and Gunther Eysenbach might dispute. It also gave erroneous information about books that I "authored." While I have edited and authored my textbook Health Informatics: Practical Guide, authored my textbook on information retrieval, and contributed chapters to many other books, I have no involvement whatsoever in the books listed by ChatGPT, Introduction to Health Informatics or Essentials of Health Information Systems and Technology. ChatGPT also listed first among my accomplishments in the field, "work on the development and implementation of EHRs." While I teach a great deal about the electronic health records (EHRs), it would be a stretch to say I am involved in their development and implementation. Clearly ChapGPT is an inferior alternative to Googling oneself.

For the learning objectives, ChatGPT did a little better, and gave reasonable, if incomplete, discussions on the topics in each. It still got some facts wrong, and also omitted what I might consider important details one might want to see in a succinct summary. Perhaps more importantly, ChatGPT provided no citations for what it said, which could allow a learner to check the interpretation or pursue more detail about the topic. I suppose the good news is that one still would do better to get more exhaustive text, figures, and citations covered in the 10x10 course (samples of which can be viewed at my site, informatics.health).

These are obviously early days for tools such as ChatGPT, and no doubt they will improve over time. But just as machine learning algorithms are not quite ready to replace human clinicians, they also are not quite ready to overtake other human tasks, such as teaching, at least not yet.

ChatGPT Transcript - December 10, 2022 (my text entry in italics)

Define biomedical and health informatics, the terms related to it, and its role in health, healthcare, public health, and biomedical research

Biomedical and health informatics is a field that focuses on the use of technology and information to improve the delivery of healthcare, public health, and biomedical research. It is an interdisciplinary field that combines computer science, data science, and healthcare to develop and use information systems and technology to manage, analyze, and interpret health-related data.

Some of the terms related to this field include electronic health records (EHRs), health information technology (HIT), health information management (HIM), and health informatics. These terms all refer to different aspects of using information and technology in the healthcare and public health sectors.

The role of biomedical and health informatics in healthcare is to improve the efficiency and effectiveness of care delivery by using technology and information systems to manage and analyze health-related data. This can include the use of EHRs to manage patient records, the use of HIT to monitor and manage the health of patients remotely, and the use of HIM to ensure the quality and security of health information.

In public health, biomedical and health informatics can be used to monitor and analyze population-level health data to identify trends and patterns, and to develop interventions and policies to improve the health of the population.

In biomedical research, this field can be used to manage and analyze large amounts of data from clinical trials, genetic studies, and other research to advance our understanding of health and disease.

Overall, the goal of biomedical and health informatics is to use technology and information to improve the quality, efficiency, and accessibility of healthcare, public health, and biomedical research.

Describe the major historical events of biomedical and health informatics

The field of biomedical and health informatics has a long and rich history, with many important events that have shaped its development. Some of the major historical events in this field include:

  1. The development of electronic medical records (EMRs) in the 1950s, which marked the beginning of the use of computers in healthcare to store and manage patient information.
  2. The establishment of the National Library of Medicine (NLM) in the United States in 1956, which became a major repository for health-related information and a driving force in the development of health informatics.
  3. The creation of the first Health Information Management (HIM) program at the University of Minnesota in 1967, which marked the beginning of formal education and training in health informatics.
  4. The development of the first clinical decision support system (CDSS) in the 1970s, which used computers to assist doctors in making diagnostic and treatment decisions.
  5. The introduction of the first personal health record (PHR) in the 1980s, which allowed patients to manage their own health information and access it from any location.
  6. The widespread adoption of the internet in the 1990s, which facilitated the sharing and dissemination of health-related information and the development of online health communities.
  7. The passage of the Health Insurance Portability and Accountability Act (HIPAA) in 1996, which established national standards for the privacy and security of health information.
  8. The growth of mobile health (mHealth) technologies in the 2000s, which enabled the use of smartphones and other devices to monitor and manage health-related information.

Overall, these and other historical events have played a significant role in the development and evolution of biomedical and health informatics as a field, and have had a profound impact on the way healthcare is delivered and research is conducted.

Discuss the major problems in healthcare motivating use of biomedical and health informatics

There are many challenges and problems facing the healthcare industry today that are motivating the use of biomedical and health informatics. Some of the major problems in healthcare that are driving the use of this field include:

  1. The increasing cost of healthcare: Healthcare costs are rising rapidly, and many people are struggling to afford the care they need. Biomedical and health informatics can help to reduce these costs by using technology and data analysis to improve the efficiency and effectiveness of care delivery.
  2. The growing burden of chronic diseases: Chronic diseases, such as diabetes, heart disease, and cancer, are becoming more prevalent and are a major cause of morbidity and mortality. Biomedical and health informatics can be used to monitor and manage these conditions, and to identify and intervene early to prevent their progression.
  3. The shortage of healthcare workers: There is a shortage of healthcare workers in many parts of the world, which is putting a strain on the healthcare system and making it difficult for people to access care. Biomedical and health informatics can help to alleviate this shortage by enabling healthcare workers to work more efficiently and by supporting remote care delivery.
  4. The need for better population health management: Many public health challenges, such as obesity, substance abuse, and infectious diseases, require a population-level approach to prevention and management. Biomedical and health informatics can be used to monitor and analyze population-level health data, and to develop and implement interventions to improve the health of the population.
  5. The need for better data management and analysis: The healthcare industry generates vast amounts of data, but much of it is unstructured and difficult to manage and analyze. Biomedical and health informatics can help to organize and analyze this data to extract valuable insights and inform decision-making.

Overall, the major problems in healthcare are driving the use of biomedical and health informatics to improve the quality, efficiency, and accessibility of healthcare and to address some of the most pressing challenges facing the healthcare industry.

Compare and contrast the roles of various individuals in the health information technology workforce

The health information technology (HIT) workforce includes a wide range of individuals with different roles and responsibilities. Some of the major roles in the HIT workforce include:

  1. Health information managers (HIMs): HIMs are responsible for the management and analysis of health-related data, including the design and implementation of health information systems and the development and maintenance of electronic health records (EHRs).
  2. Health information technologists (HITs): HITs are responsible for the technical aspects of health information systems, including the design, development, and maintenance of software and hardware systems used in healthcare.
  3. Clinical informaticists: Clinical informaticists are healthcare professionals with expertise in both medicine and health informatics. They use their knowledge of both fields to improve the quality and safety of care delivery, and to support the use of health information technology in clinical settings.
  4. Health information exchange (HIE) coordinators: HIE coordinators are responsible for facilitating the exchange of health-related information between different healthcare organizations and systems. This includes ensuring the interoperability of different systems, and the security and privacy of health information.
  5. Chief information officers (CIOs): CIOs are responsible for the overall management of information technology in healthcare organizations, including the development and implementation of information technology strategies and the supervision of IT staff.

Overall, the roles in the HIT workforce are diverse and varied, and individuals in these roles work together to support the use of health information technology in healthcare and public health.

Find and access the major sources of information for biomedical and health informatics in the scientific literature and on the World Wide Web

There are many sources of information for biomedical and health informatics in the scientific literature and on the World Wide Web. Some of the major sources of information for this field include:

  1. PubMed: PubMed is a free database of biomedical literature maintained by the National Institutes of Health (NIH) in the United States. It contains millions of abstracts and full-text articles from scientific journals, and is a valuable resource for researchers and practitioners in biomedical and health informatics.
  2. IEEE Xplore Digital Library: The IEEE Xplore Digital Library is a comprehensive collection of technical literature in electrical engineering, computer science, and related fields. It contains many articles and conference proceedings on topics related to biomedical and health informatics, and is a valuable source of information for researchers in this field.
  3. Health Information and Libraries Journal: The Health Information and Libraries Journal (HILJ) is a peer-reviewed journal published by the Health Libraries Group of the Chartered Institute of Library and Information Professionals (CILIP) in the United Kingdom. It covers a wide range of topics related to health information and health informatics, and is a valuable source of information for librarians and other professionals working in this field.
  4. Journal of the American Medical Informatics Association (JAMIA): JAMIA is a peer-reviewed journal published by the American Medical Informatics Association (AMIA). It covers a wide range of topics related to health informatics, including the use of technology and information to improve the delivery of healthcare and public health.
  5. Health IT Buzz: Health IT Buzz is a blog maintained by the Office of the National Coordinator for Health Information Technology (ONC) in the United States. It provides news and updates on health information technology and health informatics, and is a valuable source of information for those interested in this field.

Overall, these and other sources of information are valuable for researchers and practitioners in biomedical and health informatics, and provide a wealth of information on the latest developments and trends in this field.

What are the contributions of William Hersh to informatics?

William Hersh is a well-known figure in the field of informatics. He is a professor and the chair of the Department of Medical Informatics & Clinical Epidemiology at the Oregon Health & Science University School of Medicine.

Some of Hersh's notable contributions to the field of informatics include his work on the development and implementation of electronic health records (EHRs), the use of natural language processing for clinical text analysis, and the integration of clinical research data with EHRs. He has also contributed to the development of informatics curricula and has written extensively on the subject.

Hersh is the author of several books on informatics, including "Introduction to Health Informatics" and "Essentials of Health Information Systems and Technology". He is also the editor-in-chief of the Journal of the American Medical Informatics Association and the Journal of Medical Internet Research.

Overall, Hersh has made many important contributions to the field of informatics, including his work on the development and implementation of EHRs, the use of natural language processing for clinical text analysis, and the integration of clinical research data with EHRs.