Accent

The Systematic Review Assistant-Deduplication Module (SRA-DM) project was developed in 2013 at the Bond University Centre for Research in Evidence-Based Practice (CREBP). The project aimed to reduce the amount of time taken to produce systematic reviews by maximising the efficiency of the various review stages such as optimising search strategies and screening, finding full text articles and removing duplicate citations.
The deduplication algorithm was developed using a heuristic-based approach with the aim of increasing the retrieval of duplicate records and minimising unique records being erroneously designated as duplicates. The algorithm was developed iteratively with each version tested against a benchmark dataset of 1,988 citations. Modifications were made to the algorithm to overcome errors in duplicate detection (Table 1). For example, errors often occurred due to variations in author names (e.g. first-name/surname sequence, use/absence of initialisation, missing author names and typographical errors), page numbers (e.g. full/truncated, or missing), text accent marks (e.g. French/German/Spanish) and journal names (e.g. abbreviated/complete, and ‘the’ used intermittently). The performance of the SRA-DM algorithm was compared with EndNote’s default one step auto-deduplication process. To determine the reliability of SRA-DM, we conducted a series of validation tests with results of different literature searches (cytology screening tests, stroke and haematology) which were retrieved from searching multiple biomedical databases (Table 2).Table 1

SRA-DM algorithm changes

Iterations	Changes to algorithms
First iteration	Matching criteria were based on simple field comparison (ignoring punctuation) with checks against the year field since this field has a lower probability for errors because it is restricted to integers 0–9 and therefore the best non-mistakable field.
Second iteration	Short format page numbers were converted to full format (e.g. 221–226, 221–6), and the algorithm was further modified to increase the sensitivity by incorporating matching criteria on authors OR title.
Third iteration	Match author AND title with the extension of the non-reference fields from only ‘year’ to year OR volume OR edition.
Fourth iteration	The fourth algorithm extended the matching criteria of the third algorithm, with the addition of an improved name matching system. This was context aware of author name variations, i.e. initialisation, punctuation and rearranged author listings using fuzzy logic, so that differences could be accommodated. For example, the following names are all syntactically equivalent and will match as identical authors:
	1. William Shakespeare
	2. W. Shakespeare
	3. W Shakespeare
	4. William John Shakespeare
	5. William J. Shakespeare
	6. W. J. Shakespeare
	7. W J Shakespeare
	8. Shakespeare, William
	9. Shakespeare, W
	10. Shakespeare, W, A
	11. Shakespeare, W, A, B, C
	12. William Shakespeare 1st
	13. William Shakespeare 2nd
	14. William Shakespeare IV
	15. William Adam Bob Charles Shakespeare XVI

Table 2

Databases searched for retrieval of citations for validation testing

Datasets	Databases searched
Cytology screening tests dataset	1. Cochrane Controlled Trials Register (CCTR)
	2. Cochrane Database of Systematic Reviews (CDSR)
	3. EMBASE
	4. MEDLINE
	5. National Research Register (NRR)
	6. Database of Assessments of Reviews of Effectiveness (DARE)
	7. NHS Health Technology Assessment (HTA)
	8. PreMEDLINE
	9. Science Citation Index
	10. Social Sciences Citation Index
Haematology dataset	1. MEDLINE
	2. EMBASE
	3. MEDLINE In-Process
	4. Biological Abstracts
	5. NHS Health Technology Assessment (HTA)
	6. Cochrane Controlled Trials Register (CCTR)
	7. Cochrane Database of Systematic Reviews (CDSR)
	8. CINAHL
	9. Science Citation Index
	10. Social Sciences Citation Index
Stroke dataset	1. MEDLINE
	2. EMBASE
	3. CENTRAL
	4. CINAHL
	5. PsycInfo

The selection of the correct keyword(s) when examining online queries is key for valid results [51 (link)]. Thus, many factors should be taken into consideration when using Google Trends data in order to ensure a valid analysis.
Google Trends is not case sensitive, but it takes into account accents, plural or singular forms, and spelling mistakes. Therefore, whatever the choice of keywords or combination of keywords, parts of the respective queries will not be considered for further analysis.
To partly overcome this limitation, the “+” feature can be used to include the most commonly encountered misspellings, which are selected and entered manually; however, we should keep in mind that some results will always be missing, as all possible spelling variations cannot be included. In addition, incorrect spellings of some words could be used even more often than the correct one, in which case, the analysis will not be trivial. However, in most of the cases, the correct spelling is the most commonly used, and therefore, the analysis can proceed as usual. For example, gonorrhea is often misspelled, mainly as “Gonorrea,” which is also the Spanish term for the disease. As depicted in Figure 4a, both terms have significantly high volumes. Therefore, to include more results, both terms could be entered as the search term by using the “+” feature (Figure 4b). In this way, all results including the correct and the incorrect spellings are aggregated in the results. Note that this is not limited to only two terms; the “+” feature can be used for multiple keywords or for results in multiple languages in a region.
In the case of accents, before choosing the keywords to be examined, the variations in interest between the terms with and those without accents and special characters should be explored. For example, measles translates into “Sarampión,” “ošpice,” “mässling,” and “Ιλαρά” in Spanish, Slovenian, Swedish, and Greek, respectively. As depicted in Figure 5, in Spanish and Greek, the term without the accent is searched for in higher volumes; in Slovenian, the term with the accent is mostly used; and in Swedish, the term without the accent is almost nonexistent. Thus, in Greek searches, the term without accent should be selected, in Slovenian and Swedish searches, terms with accents should be used, while for Spanish, as both terms yield significant results, either both terms using the “+” feature or the term without the accent should be selected.
Another important aspect is the use of quotation marks when selecting the keyword. This obviously applies only to keywords with two or more words. For example, breast cancer can be searched online by using or not using quotes. To elaborate, the term “breast cancer” without quotes will yield results that include the words “breast” and “cancer” in any possible combination and order; for example, keywords “breast cancer screening” and “breast and colon cancer” are both included in the results. However, when using quotes, the term “breast cancer” is included as is; for example, “breast cancer screening,” “living with breast cancer,” and “breast cancer patient.” As shown in Figure 6a, the results are almost identical in this case. However, this is not always the case. As depicted in Figure 6b, this is clearly different for “HIV test.” When searching for HIV test with and without quotes, the results differ in volumes of searches, despite the trend being very similar but not exactly the same.
Finally, when researching with Google Trends, the options of “search term” and “disease” (or “topic”) are available when entering a keyword. Although the “search term” gives results for all keywords that include the selected term, “disease” includes various keywords that fall within the category, or, as Google describes it, “topics are a group of terms that share the same concept in any language.”
Therefore, it is imperative that keyword selection is conducted with caution and that the available options and features are carefully explored and analyzed. This will ensure validity of the results.

All users were eligible to participate if they had provided consent for deidentified aggregate analysis of their data for research purposes, completed an EPDS at some point during their use of the app, and entered one or more usable open-ended text entries within the 60-day window prior to providing an EPDS score. Usable text entries were defined as English-language entries that retained at least one meaningful word after concatenated text entries had been processed to remove less meaningful words. Word removal applied to text before extraction of word2vec features, LDA topics, and sentiment. This included stop-words (such as “I”, “be”, and “did”) and overly common words found in responses to open-ended text prompts (such as “today” and “yes”). Pre-processing also removed capitalization, punctuation marks, and accent marks.

The link of the online site was provided to the patients. Patients first chose their symptoms on the online site and recorded their cough for 7 s in a quiet environment and without the presence of people. The presence of sounds other than coughing can cause misdiagnosis (Figure 1). Then the recorded sound will be played and if the quality is confirmed, it will go to the next stage. In the next step, the user must select the symptoms he has and select the time of occurrence. Then he will be asked additional questions, such as the current status, age, gender, previous history of infection, PCR test, CT scan of the lung, whether there is a conflict or not. The recorded sounds are not from a specific type of microphone and have been recorded by different types of smartphones, tablets and laptops. This case can have a positive effect on the study and avoid bias. All the data collected are from Tehran city, which are from different minorities and ethnicities with various accents. All audio files used in our study are in uncompressed Pulse-code modulation (PCM) 16-bit format with a sampling rate of 48 kHz and a fixed 7-s length (Pahar et al., 2022 (link)).

The total number of collected data is almost 40,353. Almost 17,690 data were manually removed due to incomplete information, low sound quality, silent audio content, presence of surrounding noise when recording cough, absence of cough sound in audio content. Among the remaining 22,663 cough sounds, there were 14,521 negative coughs and 8,142 positive coughs. On the website, in addition to recording the sound of coughing, patients also recorded information such as clinical symptoms, days of onset of symptoms, the status of PCR tests and CT scans, the presence of previous infections, age, gender, and the person's disease status. The information about the symptoms of the patients is shown in Table 1. According to Table 1, the most common symptom among people with COVID-19 is fever (51.75%). Dry cough and productive cough are among the most common symptoms of the patients participating in the study with prevalence of 25.01 and 21.22%. Also, 29.2% of patients had no clinical symptoms. The symptoms of healthy people were negligible, so it was ignored.
The age range and gender of patients and healthy people are also mentioned in Table 2. The age range of the participants was 5–90 years, most of the participants were between 15 and 30 years old and most of them were women. All participants were residents of Tehran city, which are from different minorities and ethnicities with various accents.