Health Informatics Assignment Week 19 to 21

Week 19 Questions


  1. With the advent of full-text searching, should the National Library of Medicine abandon human indexing of citations in MEDLINE? Why or why not?
  2. Explain why you think PMC is or is not a good idea.

    Answer:

    Also with the advent of full text searching, the National Library of Medicine should not abandon human indexing of citations in MEDLINE. The present-day MTI relies simplest on titles and abstracts, at the same time as human indexers base their evaluation on the whole text of an article. This restriction on MTI causes the laptop-generated terms to suffer don't forget errors in contrast to the human assigned record descriptors. Given the increasing availability of machine-readable journals, a complete textual content processing attempt to explore approaches to enhance MTI’s overall performance has started. One approach to full textual content processing mentioned right here includes simply filing all of the text of a journal article to the automatic indexing technique. Better consequences are possibly to be completed by way of addressing the ones sections of a complete text article which give attention to the primary points of the thing. Giant studies inside the discipline of computational linguistics is concerned with identifying key topics and sections in full textual content. Moreover, insights from human indexer exercise offer steerage for the automatic techniques being evolved. A baseline became set up to provide a context for evaluating the entire text indexing methods. The identify and abstract of the articles have been processed usually by way of MTI to establish the production baseline. The next approach is using MMI indexing. The procedure is then the name and abstract by myself, then the whole textual content. Those range from the baseline instances in that this indexing does not encompass the contribution of REL. The augmented version changed into built the usage of REL processing of simply the name and summary and the MMI processing of selected sections. With this approach, the use of the Medline quotation (title and summary), because the REL would possibly perform higher on that textual content than on textual content from the primary body of the thing because it's far educated on Medline citations. A massive parameter of MTI specifies the variety of citations much like the enter textual content which are considered with the aid of REL. We track this parameter to maximize MTI’s performance. Maximum MEDLINE implementations have always allowed the combination of searching on human indexing phrases and on phrases in the title and summary of the reference. With the development of full-textual content resources inside the Nineteen Eighties and Nineties, systems that allowed handiest phrase indexing began to emerge. This trend multiplied with the advent of the web. Maximum databases utilizing human indexing generally have a detailed protocol for undertaking of indexing terms from the thesaurus. The MEDLINE database is not any exception. The concepts of MEDLINE indexing had been laid out inside the -quantity MEDLARS Indexing guide. Next adjustments have happened with changes to MEDLINE, other databases, and MeSH over the years. The predominant ideas of the object, typically from to five headings, are designed as main headings, and exact within the MEDLINE record with the aid of an asterisk. The indexer is likewise required to assign appropriate subheadings. Finally, the indexer ought to also assign take a look at tags, geographical locations, and publication types. Few full-text sources are manually indexed. One form of indexing that commonly takes vicinity with full-text sources, in particular within the print global, is that finished for the index in the back of the e-book. However, these facts are hardly ever used in IR systems; alternatively, maximum on line textbooks rely upon computerized indexing. One exception to that is MDConsult, which uses lower back-of-e-book indexes to factor to specific sections in its online books. With the help of such terms the indexing is made quite easier and human friendly.

  3. How would you aggregate the clinical evidence-based resources described in the chap-ter into the best digital library for clinicians?
  4. Devise a curriculum for teaching clinicians and patients the most important points about searching for healthrelated information.
  5. Find a consumer-oriented Web page and determine the quality of the information on it.

    Answer:

    Google.Com has been rated as in particular sturdy in the vicinity of relationship constructing, because the simplicity of the web site's design enables a consumer to installation a Google account and go back to a homepage that is tailored to deliver the records that one desires to get right of entry to on a normal basis. Repeat Google users can effectively check in to gain get entry to a ramification of services ranging from maps and video to blogs, photographs and information. This website serves clients at the best plane the agency needs to pick out their want and desires as opposed to forcing them to buy something else that they don’t need. The website has helped people to get knowledge from offering them primary understandings to the superior versions. To be a consumer orientated web site, the website ought to have total transparency in all factors if you want to gain customer credence and loyalty. The feature of advertising certain products is widely spread by the site and it lets the people to interpret most of the recent knowledge. The site helps the people to gain the updates and current events in their mother language as there are several options in which the person could choose the desirable language and hence could attain the updates in the desirable field required.

  6. What are the limitations of recall and precision as evaluation measures and what alternatives would improve upon them?
  7. Select a concept that appears in two or more clinical terminologies and demonstrate how it would be combined into a record in the UMLS Metathesaurus.
  8. Describe how you might devise a system that achieves a happy medium between of intellectual property and barrier-free access to the archive of science.

    Answer:

    The main intellectual strategies of IR are indexing and retrieval. These will be described subsequent, accompanied via discussion at the assessment of IR systems and research directions. In automated indexing, the paintings are accomplished with the aid of a computer. Even though the mechanical going for walks of the automated indexing method lacks cognitive enter, vast intellectual effort may also have long gone into improvement of the device for doing it, so this shape of indexing nonetheless qualifies as an intellectual procedure. Most retrieval structures in reality use a hybrid of human and phrase indexing, in that the human-assigned indexing terms turn out to be part of the record, which could then be searched by way of the use of the complete controlled time period or character phrases within it. The improvement of virtual libraries can help in the development of such system. However, virtual library document stated that the overall capability of digital libraries has not been realized, noting that the underlying technology were developed with federal management, that records face both technical and operational demanding situations, and that the difficulty of intellectual property cannot be neglected. The document recommended that guide for studies be extended, huge-scale testbeds be advanced, all federal cloth be placed on-line, and the authorities lead efforts to expand virtual rights guidelines. An essential fault line inside the debate over highbrow belongings relates to the want to obtain a reasoned balance between get right of entry to and one-of-a-kind rights. Highbrow property lets in rightsholders to save you others from the use of their highbrow assets without permission, meaning it entails an essential exchange-off between quick-term static efficiency and long-time period dynamic efficiency. The Pew net & American lifestyles task keeps to do good sized research into the characteristics of customers of the internet for health records and the cultural and literacy obstacles they stumble upon. Virtual libraries provide some of the same offerings, however their cognizance has a tendency to be at the virtual components of content. The developing amount of medical records to be had in IR systems and virtual libraries requires new tactics to choose that which is great to use for scientific choices. There's a fantastic deal of concern approximately archiving of content material and managing its change while fewer copies of it exist on the document servers of publishers and other businesses.


Week 20 Questions


Questions

  1. Researchers in medical AI have argued that there is a need for more expert knowledgein medical decision-support systems, but developers of Bayesian systems have argued that expert estimates of likelihoods are inherently flawed and that advice programs must be based on solid data. How do you account for the apparent difference between these views? Which view is valid? Explain your answer.
  2. Explain the meaning of Internist-1/QMR’s frequency weights and evoking strengths.What does it mean for a finding to have a frequency weight of 4 and an evoking strength of 2? How do these parameters relate to the concepts of sensitivity, specificity, and predictive value that were introduced in Chapters 2 and 3?

    Answer:

    Programs offer custom-tailored evaluations or advice based on frames of patient-specific information. Many medical support staff (like DXplain or QMR) recommend separate diagnosis or show additional information that might help to narrow the scope of epidemiologic options. Other technologies (like the original Internist-1 program, through which QMR was inferred) suggest a single simplest argument besides in case of symptomatology of the patient. Some programs view and analyze the patient's report in a manner that is sensitive to the clinical context over time. Some programs also offer guidance on counseling rather than medical assistance. Fast Medical Reference (like its predecessor, Internist-1) facilitates medical problem-solving in general internal medicine while DXplain is a web-based medical framework that continues to evolve. informatics community. Internist-1 was a massive diagnostic system which gradually evolved into a framework of decision support identified as Quick Medical Reference (QMR). QMR has been industrially marketed over several decades, that is used by a huge professional as well as students’ community. Though this structure is not presently actually promoted, this has been extremely influential and has become the topic of substantial medical-Info research. Some programs view and analyze the patient's report in a manner that is conducive to the medical settings across time. Yet other technologies provide therapy advice instead of diagnosing aid. From the 1970s to the start of the current century, HELP served as a splendid illustration as to how the combination of strategic planning with other system operates would enhance a program 's acceptance and encourage heighten its use. Once the appropriateness of a clinical diagnosis is defined, sometimes recognized as the predictive value or composite reliability, the results of such a clinical diagnosis are initially checked to see if it correlates to what has been considered a conclusive predictor of same target condition, often pointed to as a gold standard. Internist-1 was able to identify several coexisting diseases and did not permit the reciprocal originality and validity conclusions which have defined most Bayesian diagnostic programs. It was developed to operate across only broad mainframe computers, and is therefore not tailored to practitioners' universal use. Especially Clinch for difficulty in diagnosis. Quick Medical Reference could also be used as either an online textbook, reporting identified patient symptoms in a particular illness or, alternatively, describing disorders that may be identified with a particular feature. QMR designers often claimed that the use of framework as an online guide seems to be more appropriate than using it as a consulting software to assist a physician, in addition, several of Internist-1 's consultation functionality became omitted in the QMR prototype which was available commercially. For instance, the QMR tool did not even ask pertinent questions from the consumer to seek a hypothesis and did not even attempt to determine when there could be more only one disease occurring at a particular time.

  3. Let us consider how deDombal and other developers of Bayesian systems have usedpatient-care experience to guide the collection of statistics that they need. For example, consider the database in the following table, which shows the relationship between two findings (f1 and f2) and a disease (D) for 10 patients.

Patient

f1

f2

D

,D

1

0

1

0

1

2

0

1

1

0

3

0

1

0

1

4

1

1

1

0

5

1

1

1

0

6

1

1

0

1

7

1

0

1

0

8

1

1

1

0

9

1

0

0

1

10

1

1

1

0

In the table, ,D signifies the absence of disease D. A 0 indicates the absence of a finding or disease, and a 1 indicates the presence of a finding or disease. For example, based on the above database, the probability of finding f1 in this population is 7/10570 percent.

Refer back to Chapters 2 and 3 as necessary in answering the following questions:

  1. What are the sensitivity and specificity of each of f1 and f2 for the disease D? What is the prevalence of D in this 10-person population?
  2. Use the database to calculate the following probabilities:

    p[f1uD]

    p[f1u,D]

    p[f2uD]

    p[f2u,D]

    p[D] p[,D]

  3. Use the database to calculate p[Duf1 and f2].
  4. Use the probabilities determined in b to calculate p[Duf1 and ,f2] using a heuristicmethod that assumes that findings f1 and f2 are conditionally independent given a disease and the absence of a disease. Why is this result different from the one in c? Why has it generally been necessary to make this heuristic approximation in Bayesian programs?
  1. In an evaluation study, the decision-support system ONCOCIN provided adviceconcerning cancer therapy that was approved by experts in only 79 percent of cases (Hickam et al., 1985b). Do you believe that this performance is adequate for a computational tool that is designed to help physicians to make decisions regarding patient care? What safeguards, if any, would you suggest to ensure the proper use of such a system? Would you be willing to visit a particular physician if you knew in advance that she made decisions regarding treatment that were approved by expert colleagues less than 80 percent of the time? If you would not, what level of performance would you consider adequate? Justify your answers.
  2. A large international organization once proposed to establish an independent laboratory—much like Underwriters Laboratory in the United States—that would test medical decision-support systems from all vendors and research laboratories, certifying the effectiveness and accuracy of those systems before they might be put into clinical use. What are the possible dimensions along which such a laboratory might evaluate decision-support systems? What kinds of problems might such a laboratory encounter in attempting to institute such a certification process? In the absence of such a credentialling system for decision-support systems, how can health-care workers feel confident in using a clinical decision aid?

Week 21 Questions


  1. What are two advantages and two limitations of including visual material in the following teaching programs:
    1. A simulated case of a patient who is admitted to the emergency unit with a gun-shot wound
    2. A lecture-style program on the anatomy of the pelvis
    3. A reference resource on bacteria and fungi
  2. You have decided to write a computer-based simulation to teach students about the management of chest pain.
    1. Discuss the relative advantages and disadvantages of the following styles of pres-entation: (1) a sequence of multiple-choice questions, (2) a simulation in which the patient’s condition changes over time and in response to therapy, and (3) a program that allows the student to enter free-text requests for information and that provides responses.
    2. Discuss at least four problems that you would expect to arise during the process ofdeveloping and testing the program.
    3. For each approach, discuss how you might develop a model that you could use toevaluate the student’s performance in clinical problem solving.
  3. Examine two clinical simulation programs. How do they differ in their presentationof history taking or physical examination of the patient?
  4. Select a topic in physiology with which you are familiar, such as arterial blood–gasexchange or filtration in the kidney, and construct a representation of the domain in terms of the concepts and subconcepts that should be taught for that topic. Using this representation, design a teaching program using one of the following methods: (1) a didactic approach, (2) a simulation approach, or (3) an exploration approach.
  5. Describe at least three challenges you can foresee in dissemination of computer-basedmedical education programs from one institution to another.
  6. Discuss the relative merits and problems of placing the computer in control of the teaching environment, with the student essentially responding to computer inquiries, versus having the student in control, with a much larger range of alternative courses of action.