We attempted to score data extracted from written medical records containing assessment results using natural language processing, and to clarify the relationship between duration of sick leave and the use of emotional words among return-to-work (RTW) program users on sick leave due to mental health problems.
Method
Participants were users of an RTW program. We extracted textual data from their electronic medical records, and gave all words a score based on the following two considerations: positivity score (the degree of positive emotion a word has) and emotion score with respect to seven emotions (sadness, anxiety, anger, disgust, trust, surprise, and joy), with the score for each emotion measured for each word. We analyzed relationships between duration of sick leave and each score.
Results
Forty-two users participated. The results showed that high positive scores (β = −0.42, p < 0.00) and high sadness scores (β = −0.60, p < 0.00) were related to a shorter duration of sick leave, and high anger score (β = 0.52, p < 0.00) was related to a longer duration of sick leave.
Conclusion
Professional assessments based on occupational therapy and natural language processing of medical records may predict the appropriate timing of RTW.
Al-MosaiwiMJohnstoneT (2018) In an absolute state: elevated use of absolutist words is a marker specific to anxiety, depression, and suicidal ideation. Clinical Psychological Science6(4): 529–542. DOI: 10.1177/2167702617747074
2.
AlterALForgasJP (2007) On being happy but fearing failure: The effects of mood on self-handicapping strategies. Journal of Experimental Social Psychology43: 947–954. DOI: 10.1016/j.jesp.2006.07.009
3.
ArimaHAkiyamaTde MouraPA, et al. (2021) Resilience building for mood disorders: theoretical introduction and the achievements of the re-work program in Japan. Asian Journal of Psychiatry58: 102580. DOI: 10.1016/j.ajp.2021.102580
4.
BeckASteerRBrownG (1996) Manual for the Beck Depression Inventory-II. San Antonio, TX: Psychological Corporation.
5.
BrockmeyerTZimmermannJKulessaD, et al. (2015) Me, myself, and I: self-referent word use as an indicator of self-focused attention in relation to depression and anxiety. Frontiers in Psychology6(OCT): 1–10. DOI: 10.3389/fpsyg.2015.01564
6.
BuschFN (2009) Anger and depression. Advances in Psychiatric Treatment15: 271–278. DOI: 10.1192/apt.bp.107.004937
7.
DirkseDHadjistavropoulosHDHesserH, et al. (2015) Linguistic analysis of communication in therapist-assisted internet-delivered cognitive behavior therapy for generalized anxiety disorder. Cognitive Behaviour Therapy44(1): 21–32.
8.
ErvastiJJoensuuMPenttiJ, et al. (2017) Prognostic factors for return to work after depression-related work disability: a systematic review and meta-analysis. Journal of Psychiatric Research95: 28–36. DOI: 10.1016/j.jpsychires.2017.07.024
9.
FischerLRRushWAKluznikJC, et al. (2008) Identifying Depression Among Diabetes Patients Using Natural Language Processing of Office Notes.In: Health Maintenance Organization Research Network2008, pp. 125–126.
10.
ForgasJP (2017) Can sadness be good for you?: On the cognitive, motivational, and interpersonal benefits of mild negative affect. Australian Psychologist52: 3–13. DOI: 10.1111/ap.12232
11.
HattoriSKishidaISudaA, et al. (2019) A return to work program improves parasympathetic activity and psychiatric symptoms in workers on sick leave due to depression. Heliyon5(7): e02151. DOI: 10.1016/j.heliyon.2019.e02151
12.
IshidaM (2019) RMeCab: interface to MeCab. R package version 1.04.
13.
KojimaMFurukawaTATakahashiH, et al. (2002) Cross-cultural validation of the Beck Depression Inventory-II in Japan. Psychiatry Research110: 291–299. DOI: 10.1016/S0165-1781(02)00106-3
14.
LuutonenS (2007) Anger and depression - Theoretical and clinical considerations. Nordic Journal of Psychiatry61(4): 246–251. DOI: 10.1080/08039480701414890
15.
MalhiGSMannJJ (2018) Depression. The Lancet392(0161): 2299–2312. DOI: 10.1016/S0140-6736(18)31948-2
16.
Ministry of Health, Labor and Welfare (2010) Jisatsu/Utsutaisakunokeizaitekibeneki (jisatsuyautsuniyorushakaitekisonshitsu). Available at:https://www.mhlw.go.jp/stf/houdou/2r9852000000qvsy.html(accessed on 31 July 2021).
17.
Ministry of Health, Labor and Welfare (2019) Heisei30nendo"karoushinadonorousaihosyoujyoukyou". Available at:https://www.mhlw.go.jp/stf/newpage_05400.html(accessed on 31 July 2021).
NieuwenhuijsenKFaberBVerbeekJ, et al. (2014) Interventions to improve return to work in depressed people. Cochrane Database of Systematic Reviews2020(12): CD006237. DOI: 10.1002/14651858.CD006237.pub3
21.
PennebakerJWMehlMRNiederhofferKG (2003) Psychological aspects of natural language use: our words, our selves. Annual Review of Psychology54: 547–577. DOI: 10.1146/annurev.psych.54.101601.145041
22.
RamanoEBuysTde BeerM (2016) Formulating a return-to-work decision for employees with major depressive disorders: occupational therapists’ experiences. African Journal of Primary Health Care and Family Medicine8(2): 1–5. DOI: 10.4102/phcfm.v8i2.954
23.
ReederDM (1991) Cognitive therapy of anger management: Theoretical and practical considerations. Archives of Psychiatric Nursing5(3): 147–150. DOI: 10.1016/0883-9417(91)90015-W
24.
RomeroNSanchezAVazquezC (2014) Memory biases in remitted depression: The role of negative cognitions at explicit and automatic processing levels. Journal of Behavior Therapy and Experimental Psychiatry45. Elsevier Ltd: 128–135. DOI: 10.1016/j.jbtep.2013.09.008
25.
RudeSSGortnerEMPennebakerJW (2004) Language use of depressed and depression-vulnerable college students. Cognition & Emotion18(8): 1121–1133. DOI: 10.1080/02699930441000030
26.
RytsäläHJMelartinTKLeskeläUS, et al. (2005) Functional and work disability in major depressive disorder. Journal of Nervous and Mental Disease193(3): 189–195. DOI: 10.1097/01.nmd.0000154837.49247.96
27.
ShibataDWakamiyaSKinoshitaA, et al. (2017) Development of Alzheimer’s disease screening technology using narrative speech qualitative analysis of utterance with a dictionary of emotional expressions. Japan Association for Medical Informatics37(6): 303–311.
28.
TagoKJinQ (2018) Influence analysis of emotional behaviors and user relationships based on Twitter data. Tsinghua Science and Technology23(1): 104–113. DOI: 10.26599/TST.2018.9010012
29.
TakamuraHInuiTOkumuraM (2005) Extracting semantic orientations of words using spin model. 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (June): 133–140. DOI: 10.3115/1219840.1219857
30.
The Japan Institute for Labour Policy and Training (2013) Mental health shishobyonadonochiryotosyokugyoseikatsunoryoritusiennikansurutyosa. Available at:https://www.jil.go.jp/institute/research/2013/112.html(accessed on 31 July 2021).
31.
WadaKSairenchiTHaruyamaY, et al. (2013) Relationship between the onset of depression and stress response measured by the brief job stress questionnaire among Japanese employees: a cohort study. Plos One8(2): e56319. DOI: 10.1371/journal.pone.0056319
