Jalmari Tuominen

Jalmari Tuominen

Auto-generated profile, based on publicly available information

Jalmari Tuominen

Faculty of Medicine and Health Technology Tampere University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 December 2023 in International Journal of Forecasting
Verified
Journal Article
Open access
JTJalmari Tuominen
Jalmari Tuominen
EPEetu Pulkkinen
Eetu Pulkkinen
JPJaakko Peltonen
Jaakko Peltonen
JKJuho Kanniainen
Juho Kanniainen
NONiku Oksala
Niku Oksala
ARAntti Roine
Antti Roine

22 August 2023 in Internal and Emergency Medicine
Verified
Journal Article
Open access
PDF file
AEAnna Eidstø
Anna Eidstø
JYJari Ylä-Mattila
Jari Ylä-Mattila
JTJalmari Tuominen
Jalmari Tuominen
HHHeini Huhtala
Heini Huhtala
APAri Palomäki
Ari Palomäki
TKTeemu Koivistoinen
Teemu Koivistoinen
The current evidence suggests that higher levels of crowding in the Emergency Department (ED) have a negative impact on patient outcomes, including mortality. However, only limited data are available about the association between crowding and mortality, especially for patients discharged from the ED. The primary objective of this study was to establish the association between ED crowding and overall 10-day mortality for non-critical patients. The secondary objective was to perform a subgroup analysis of mortality risk separately for both admitted and discharged patients. An observational single-centre retrospective study was conducted in the Tampere University Hospital ED from January 2018 to February 2020. The ED Occupancy Ratio (EDOR) was used to describe the level of crowding and it was calculated both at patient’s arrival and at the maximum point during the stay in the ED. Age, gender, Emergency Medical Service transport, triage acuity, and shift were considered as confounding factors in the analyses. A total of 103,196 ED visits were included. The overall 10-day mortality rate was 1.0% (n = 1022). After controlling for confounding factors, the highest quartile of crowding was identified as an independent risk factor for 10-day mortality. The results were essentially similar whether using the EDOR at arrival (OR 1.31, 95% CI 1.07–1.61, p = 0.009) or the maximum EDOR (OR 1.27, 95% CI 1.04–1.56, p = 0.020). A more precise, mortality-associated threshold of crowding was identified at EDOR 0.9. The subgroup analysis did not yield any statistically significant findings. The risk for 10-day mortality increased among non-critical ED patients treated during the highest EDOR quartile.

17 May 2022 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
JTJalmari Tuominen
Jalmari Tuominen
FLFrancesco Lomio
Francesco Lomio
NONiku Oksala
Niku Oksala
APAri Palomäki
Ari Palomäki
JPJaakko Peltonen
Jaakko Peltonen
ARAntti Roine
Antti Roine
Background and objective: Emergency Department (ED) overcrowding is a chronic international issue that is associated with adverse treatment outcomes. Accurate forecasts of future service demand would enable intelligent resource allocation that could alleviate the problem. There has been continued academic interest in ED forecasting but the number of used explanatory variables has been low, limited mainly to calendar and weather variables. In this study we investigate whether predictive accuracy of next day arrivals could be enhanced using high number of potentially relevant explanatory variables and document two feature selection processes that aim to identify which subset of variables is associated with number of next day arrivals. Performance of such predictions over longer horizons is also shown. Methods: We extracted numbers of total daily arrivals from Tampere University Hospital ED between the time period of June 1, 2015 and June 19, 2019. 158 potential explanatory variables were collected from multiple data sources consisting not only of weather and calendar variables but also an extensive list of local public events, numbers of website visits to two hospital domains, numbers of available hospital beds in 33 local hospitals or health centres and Google trends searches for the ED. We used two feature selection processes: Simulated Annealing (SA) and Floating Search (FS) with Recursive Least Squares (RLS) and Least Mean Squares (LMS). Performance of these approaches was compared against autoregressive integrated moving average (ARIMA), regression with ARIMA errors (ARIMAX) and Random Forest (RF). Mean Absolute Percentage Error (MAPE) was used as the main error metric. Results: Calendar variables, load of secondary care facilities and local public events were dominant in the identified predictive features. RLS-SA and RLS-FA provided slightly better accuracy compared ARIMA. ARIMAX was the most accurate model but the difference between RLS-SA and RLS-FA was not statistically significant. Conclusions: Our study provides new insight into potential underlying factors associated with number of next day presentations. It also suggests that predictive accuracy of next day arrivals can be increased using high-dimensional feature selection approach when compared to both univariate and nonfiltered high-dimensional approach. Performance over multiple horizons was similar with a gradual decline for longer horizons. However, outperforming ARIMAX remains a challenge when working with daily data. Future work should focus on enhancing the feature selection mechanism, investigating its applicability to other domains and in identifying other potentially relevant explanatory variables.

11 December 2020 in BMC Emergency Medicine
Verified
Journal Article
Open access
PDF file
JTJalmari Tuominen
Jalmari Tuominen
VHVille Hällberg
Ville Hällberg
NONiku Oksala
Niku Oksala
APAri Palomäki
Ari Palomäki
TLTimo Lukkarinen
Timo Lukkarinen
ARAntti Roine
Antti Roine
Background: Emergency departments (EDs) worldwide have been in the epicentre of the novel coronavirus disease (COVID-19). However, the impact of the pandemic and national emergency measures on the number of non-COVID-19 presentations and the assessed acuity of those presentations remain uncertain.Methods: We acquired a retrospective cohort containing all ED visits in a Finnish secondary care hospital during years 2018, 2019 and 2020. We compared the number of presentations in 2020 during the national state of emergency, i.e. from March 16 to June 11, with numbers from 2018 and 2019. Presentations were stratified using localized New York University Emergency Department Algorithm (NYU-EDA) to evaluate changes in presentations with different acuity levels.Results: A total of 27,526 presentations were observed. Compared to previous two years, total daily presentations were reduced by 23% (from 113 to 87,p < .001). In NYU-EDA classes, Non-Emergent visits were reduced the most by 42% (from 18 to 10,p < .001). Emergent presentations were reduced by 19 to 28% depending on the subgroup (p < .001). Number of injuries were reduced by 25% (from 27 to 20, p < .001). The NYU-EDA distribution changed statistically significantly with 4% point reduction in Non-Emergent visits (from 16 to 12%,p < .001) and 0.9% point increase in Alcohol-related visits (from 1.6 to 2.5%, p < .001).Conclusions: We observed a significant reduction in total ED visits in the course of national state of emergency. Presentations were reduced in most of the NYU-EDA groups irrespective of the assessed acuity. A compensatory increase in presentations was not observed in the course of the 3 month lockdown. This implies either reduction in overall morbidity caused by decreased societal activity or widespread unwillingness to seek required medical advice.

26 May 2023 in Journal of Medical Systems
Verified
Journal Article
Open access
PDF file
JTJalmari Tuominen
Jalmari Tuominen
TKTeemu Koivistoinen
Teemu Koivistoinen
JKJuho Kanniainen
Juho Kanniainen
NONiku Oksala
Niku Oksala
APAri Palomäki
Ari Palomäki
ARAntti Roine
Antti Roine
Emergency department (ED) crowding is a well-recognized threat to patient safety and it has been repeatedly associated with increased mortality. Accurate forecasts of future service demand could lead to better resource management and has the potential to improve treatment outcomes. This logic has motivated an increasing number of research articles but there has been little to no effort to move these findings from theory to practice. In this article, we present first results of a prospective crowding early warning software, that was integrated to hospital databases to create real-time predictions every hour over the course of 5 months in a Nordic combined ED using Holt-Winters’ seasonal methods. We show that the software could predict next hour crowding with an AUC of 0.94 (95% CI: 0.91-0.97) and 24 hour crowding with an AUC of 0.79 (95% CI: 0.74-0.84) using simple statistical models. Moreover, we suggest that afternoon crowding can be predicted at 1 p.m. with an AUC of 0.84 (95% CI: 0.74-0.91).

8 January 2021 in Research Square
Verified
Preprint
Open access
PDF file
JTJalmari Tuominen
Jalmari Tuominen
ARAntti Roine
Antti Roine
TSTaavi Saviauk
Taavi Saviauk
ASAnssi Seppo
Anssi Seppo
MPMiika Pihlaja
Miika Pihlaja
NONiku Oksala
Niku Oksala
Objective Emergency department (ED) crowding is a global problem associated with negative patient outcomes such as mortality and prolonged length of stay. Forecasting overcrowding would enable pre-emptive strategical maneuvers and is a subject of constant academic interest. However, most studies focus on forecasting arrivals in United States ED setting. We propose a novel and intuitive crowding metric called daily peak occupancy and assess forecasting ED crowding in a Nordic Combined ED using both established and novel predictive algorithms.Methods All episodes of care in Tampere University Hospital ED were acquired from December 1, 2014 to June 19, 2019, amounting to 488 167 individual events. Predictability of two target variables was investigated: total daily arrivals (TDA) and daily peak occupancy (DPO) with forecast horizon of one day. Three models were investigated: Seasonal Autoregressive Moving Average (SARIMA), Facebook’s Prophet algorithm, and General Linear Model (GLM). Calendar variables were used as independent variables.Results SARIMA outperformed other models in predicting both total daily arrivals and daily peak occupancy with mean absolute percentage errors of 6.6% (±5.3) and 12.4% (±10.7) respectively. Next day overcrowding can be predicted using SARIMA with an AUC of 0.74 and accuracy of 79 %.Conclusion Predictive models can be utilized in a Nordic emergency medicine setting with similar or better accuracy as previously reported. Predicting future occupancy is possible but more challenging than predicting arrivals. Predicting peaks in demand remains a significant challenge. Future work should focus on investigating the value of exogenous variables in increasing model sensitivity.