Tuesday, August 24, 2021

Scientific Rankings for the Informatics Professor

While I agree with those who argue that scientific rankings, especially based on bibliographic citation indicators, are limited in their measurement of a scientist's impact, I must admit a certain fascination with them. Perhaps that stems from my interest in dissemination and retrieval of scientific information generally. And perhaps also, because I enjoy writing and tend to measure well by these metrics.

I do show up in most rankings of my primary and related scientific fields. As I consider my primary scientific discipline to be biomedical informatics, I can report that I rank 57th on one list of researchers in the field. On another more focused list of those who work in medical informatics, I rank 14th, although my ranking falls to 33rd when the list is less focused (details below - also see [1,2]). I am also on a global list of the top 1000 computer science and electronics researchers, where I rank 932nd globally and 569th among Americans. On a more focused computer science list for the information retrieval field, I rank 23rd.

A description of how these rankings are calculated gives some perspective into my positions on them. All of these rankings make use of the well-known citation measure, the h-index, although one uses additional factors. The h-index is a measure of the number of one's publications that have been cited by at least that same number of publications. So for example, if one has 15 papers that have been cited 15 or more times, their h-index is 15. There are two main public sources of h-index values that are most commonly used, which give different results due to the way they are calculated. The two are Google Scholar and Scopus, the latter an arm of the scientific publishing conglomerate, Elsevier. The Google Scholar h-index is usually higher than the Scopus h-index due to the former including a wide variety of academic products, such as conference proceedings, books, non-peer-reviewed reports, and other publications on the Internet, whereas the latter is limited to journal publications. As the Google Scholar value is also generated automatically, it is more likely to contain erroneously included papers, especially when author names are ambiguous. My current Google Scholar and Scopus h-index values are, as of this writing, 75 and 46 respectively.

Obviously the h-index is related to the duration of one's career, and as citation patterns vary in different fields, one must compare the h-index of different individuals with caution. With those caveats, we can explore further my own ranks. The list of biomedical informatics researchers is maintained by Allison McCoy of Vanderbilt University. One concern about this list is that it contains a number of researchers who, although published in the biomedical informatics literature, do not primarily work in the biomedical informatics field. This list is generated from software developed by Jimmy Lin of University of Waterloo, who maintains the list of information retrieval researchers (and several other fields within computer science). The list of top worldwide computer science researchers is maintained by a Web site devoted to computer science research, Guide2Research.

An additional ranking in which I appear is one compiled by John Ioannidis of Stanford University and colleagues [1,2]. This analysis includes the top 100,000 scientists across all fields, with additional enrichment from those in the top 2% of their field but not in the top 100,000. Unlike the other sources, this analysis is fixed, with data through 2019 and taking more factors into account than just the h-index. A composite C-score is made up of six factors measured from citations through 2019 and excludes self-citations:

  • h19 (ns)    h-index as of end-2019
  • hm19 (ns)    hm-index as of end-2019
  • ncs (ns)    total citations to single authored papers
  • ncsf (ns)    total citations to single+first authored papers
  • npsfl (ns)    number of single+first+last authored papers
  • ncsfl (ns)    total citations to single+first+last authored papers

The rationale for this more complex measure is based on observations that (a) in some fields, many papers have vast numbers of authors, (b) these large numbers of authors give great weight to measures based purely on citations, (c) many Nobel laureates do not rate highly in simple citation measures such as h-index, (d) many of those who rank highly in simple citation measures have few or no first-authored or last-authored papers, and (e) Nobel laureates rank higher when more complex measures such as a C-score are employed.

In this cast of more than a hundred thousand, my C-score of 3.938 gives me an overall rank of 22,034, which is based on 241 papers published and 6109 citations to them through 2019. As noted above, I rank 15th among those whose primary field is medical informatics. There are also others for whom medical informatics is listed as their secondary field, and when combined with those for whom it is primary, my ranking is 34th(?). There is a separate ranking for those whose primary field is bioinformatics. 

I can also extract out all researchers in the ranking from my institution and its affiliates (Oregon Health & Science University, OHSU School of Medicine, Oregon National Primate Research Center, and Portland VA Medical Center) and note that I rank 49th out of 256 included in this list. (I am also pleased to note that 10 people from my department make it on to the overall OHSU list, including Roger Chou, Heidi Nelson, Mark Helfand, Joan Ash, Cynthia Morris, Paul Gorman, Rochelle Fu, Linda Humphrey, and Aaron Cohen.)

One interesting aspect of the Ioannidis et al. analysis is that I rank better using the composite score than just by my h-index. Based solely on the h-index, I would rank only 131st for OHSU and 37th in the primary medical informatics list. My C-score is improved by my relatively higher number of first-author and single-author papers, and citations to them. I also must have fewer co-authors on my papers than my colleagues at OHSU and in informatics, as I do better with the hm-index, which adjusts for the number of authors on a paper. At OHSU in particular, where I rank 49th overall and 131st by h-index, I rank 51st in hm-index, 37th in citations to single-authored papers, and 41st in citations to single- and first-authored papers. My 104 single- and first-authored papers rank me 22nd at OHSU. My data for the Ioannidis et al. analysis is available in a spreadsheet (Enjoy!).

On a final note, I am pleased to report that citation indices are a family affair for me. My daughter Alyssa Hersh, MD, MPH is currently a resident in Obstetrics & Gynecology at OHSU. She is also a rising researcher, and as of this writing has a Google Scholar h-index of 6 and a Scopus h-index of 4. I have no doubt she will surpass my current citation metrics long before she reaches my current age!

References

[1] Ioannidis, J.P.A., Klavans, R., Boyack, K.W., 2016. Multiple Citation Indicators and Their Composite across Scientific Disciplines. PLoS Biol 14, e1002501. https://doi.org/10.1371/journal.pbio.1002501.

[2] Ioannidis, J.P.A., Boyack, K.W., Baas, J., 2020. Updated science-wide author databases of standardized citation indicators. PLoS Biol 18, e3000918. https://doi.org/10.1371/journal.pbio.3000918.