The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index.
Personalized Machine Learning-Based Prediction of Wellbeing and Empathy in Healthcare Professionals
Open accessAbstract
Healthcare professionals are known to suffer from workplace stress and burnout, which can negatively affect their empathy for patients and quality of care. While existing research has identified factors associated with wellbeing and empathy in healthcare professionals, these efforts are typically focused on the group level, ignoring potentially important individual differences and implications for individualized intervention approaches. In the current study, we implemented N-of-1 personalized machine learning (PML) to predict wellbeing and empathy in healthcare professionals at the individual level, leveraging ecological momentary assessments (EMAs) and smartwatch wearable data. A total of 47 mood and lifestyle feature variables (relating to sleep, diet, exercise, and social connections) were collected daily for up to three months followed by applying eight supervised machine learning (ML) models in a PML pipeline to predict wellbeing and empathy separately. Predictive insight into the model architecture was obtained using Shapley statistics for each of the best-fit personalized models, ranking the importance of each feature for each participant. The best-fit model and top features varied across participants, with anxious mood (13/19) and depressed mood (10/19) being the top predictors in most models. Social connection was a top predictor for wellbeing in 9/12 participants but not for empathy models (1/7). Additionally, empathy and wellbeing were the top predictors of each other in 64% of cases. These findings highlight shared and individual features of wellbeing and empathy in healthcare professionals and suggest that a one-size-fits-all approach to addressing modifiable factors to improve wellbeing and empathy will likely be suboptimal. In the future, such personalized models may serve as actionable insights for healthcare professionals that lead to increased wellness and quality of patient care.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
![Figure 1 Personalized machine learning pipeline flowchart adapted from [32]. This pipeline is run for each subject with a target variable set to wellbeing and empathy.](/paper-figures/e3ef6281d7ee4b659b74aa0232aad0ad/personalized-machine-learning-based-prediction-of-wellbeing-and-empathy-in-figure-1.jpg)
![Figure 2 Results from wellbeing and empathy models. (A,B). Mean absolute percentage error (MAPE) of wellbeing and empathy models, respectively. Mean and std are shown from nested cross-validation for each subject and the average across all participants. The dashed line at 0.2 as a threshold for good MAPE [57]. (C,D). Combined histogram of all predicted values for wellbeing and empathy across all participants. Blue and red represents actual and predicted values respectively. (E,F). Heatmap of actual vs. predicted values for wellbeing and empathy.](/paper-figures/0c8b6fd84a5e42bc8f73f4bc90bd7b95/personalized-machine-learning-based-prediction-of-wellbeing-and-empathy-in-figure-2.jpg)

![Figure 4 SHapley Additive Explainer (SHAP) plots across participants comparing wellbeing and empathy models. Rank feature importance and feature effects are shown. P28’s wellbeing slide shows timeshap [58] rank feature importance for their LSTM best-fit model. Individual effects of each feature on the dependent variable of wellbeing/empathy are depicted using the colored points to the right of the bar graph from low (blue) to high (pink) feature values relative to the outcome plotted on the x-axis (from low to high wellbeing/empathy going from left to right). For example, the P-6 Empathy Shapley plot shows that their top-ranking predictors of empathy are mild exercise over the past day followed by sleep satisfaction; since the color dots for mild exercise progress from pink to blue from left to right, lesser mild exercise supports greater patient empathy in this case but for sleep, greater sleep satisfaction (color dots progressing from blue to pink) supports greater patient empathy.](/paper-figures/2c96d01e69d7479e99fe103ca6d905d6/personalized-machine-learning-based-prediction-of-wellbeing-and-empathy-in-figure-4.jpg)

Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Consequently, a single lifestyle treatment domain is unlikely to be universally beneficial, and these studies fail to account for individual differences that may favor one behavioral health solution over another [17–19].”
From Personalized machine learning guided intervention for optimizing lifestyle behaviors in depression: a pilot study (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Yet, a major limitation of these homogenously assigned (non-personalized) behavioral intervention studies is the heterogeneity across individuals of the specific lifestyle factors most closely linked to their depression.”
From Personalized machine learning guided intervention for optimizing lifestyle behaviors in depression: a pilot study (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Shapley values indicate the relative importance and directionality of each feature as it predicts the depressed mood DV, notably reflecting associations but not causal relationships or inherent modifiability of the underlying variables [17, 18].”
From Personalized machine learning guided intervention for optimizing lifestyle behaviors in depression: a pilot study (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“We have previously demonstrated high accuracy ML modeling of individual depressed mood based on ecological momentary assessments (EMA) and passive smart watch data [17, 18, 27].”
From Personalized machine learning guided intervention for optimizing lifestyle behaviors in depression: a pilot study (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Consequently, a single lifestyle treatment domain is unlikely to be universally beneficial, and these studies fail to account for individual differences that may favor one behavioral health solution over another [17–19].”
From Personalized machine learning guided intervention for optimizing lifestyle behaviors in depression: a pilot study (2026) · cites this paper as [18]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 2×
“We also apply SHapley Additive exPlanations (SHAP) to each of the best fi t models for model interpretability [32,55,56] These SHAP values indicate the relative importance and directionality of each feature as it predicts the outcome variable, allowing us to be tt er understand the model…”
Methodmice: Multivariate Imputation by Chained Equations in R
Buuren, S. V., & Groothuis-Oudshoorn, K. (2011) · Journal of Statistical Software · doi:10.18637/jss.v045.i03 · Cited by 13,870 · cited 1×
“For personalized models, removing missing data can create unaccountable bias and lead to low accuracy on test data [51].”
BackgroundMaslach, C., Schaufeli, W. B., & Leiter, M. P. (2001) · Annual Review of Psychology · doi:10.1146/annurev.psych.52.1.397 · Cited by 12,852 · cited 1×
“It is also worth noting that research has indicated that interventions directed at healthcare workers are less effective compared to systematic changes in their respective organizations [71–73].”
Background(2010) · University of Twente Research Information · Cited by 6,037
Shanafelt, T. D., Boone, S., Tan, L., Dyrbye, L. N., Sotile, W., Satele, D., West, C. P., Sloan, J., & Oreskovich, M. R. (2012) · Archives of Internal Medicine · doi:10.1001/archinternmed.2012.3199 · Cited by 3,439
Physician burnout: contributors, consequences and solutions
West, C. P., Dyrbye, L. N., & Shanafelt, T. D. (2018) · Journal of Internal Medicine · doi:10.1111/joim.12752 · Cited by 2,768
Social relationships and health a flashpoint for health policy
Umberson, D., & Karas Montez, J. (2010) · Journal of Health and Social Behavior · doi:10.1177/0022146510383501 · Cited by 2,639
Burnout and self-reported patient care in an internal medicine residency program
Shanafelt, T. D., Bradley, K. A., Wipf, J. E., & Back, A. L. (2002) · Annals of Internal Medicine · doi:10.7326/0003-4819-136-5-200203050-00008 · Cited by 2,165
(2010) · doi:10.5555/1756006.1859921 · Cited by 1,924 · cited 1×
“With a limited amount of data per subject, and wanting to limit model overfitting, we opted for a nested CV approach instead of a single CV scheme with the only downside being increased computation cost and time [53].”
MethodEmpathy Decline and Its Reasons: A Systematic Review of Studies With Medical Students and Residents
Neumann, M., Edelhäuser, F., Tauschel, D., Fischer, M. R., Wirtz, M., Woopen, C., Haramati, A., & Scheffer, C. (2011) · Academic Medicine · doi:10.1097/acm.0b013e318221e615 · Cited by 1,637 · cited 1×
“For example, among medical students, studies have found that depression was negatively associated with empathy [61,62], whereas another study found that depression was positively associated with empathic concern [63].”
Result
Research works printed but not linked: 2
- Misra, A., Ojeda, A., and Mishra, J. (2018). BrainE: A Digital Platform for Evaluating, Engaging and Enhancing Brain Function, University of California Press. Regents of the University of California Copyright SD2018-816.
- Ashforth, 1997, Burnout as a Process: Commentary on Cordes, Dougherty and Blum, J. Organ. Behav., 18, 703, 10.1002/(SICI)1099-1379(199711)18:6<703::AID-JOB847>3.0.CO;2-1 · DOI
Cited by
The Joy Is Mine: Re‐Centering the Person in the Study of Well‐Being
Nissen, A. T., & Beck, E. D. (2025) · Social and Personality Psychology Compass · doi:10.1111/spc3.70058 · Cited by 7
Leightley, D., Williamson, C., Korbacz, A., Ćurčin, V., Marshall, I. J., & Greenberg, N. L. (2026) · British Medical Bulletin · doi:10.1093/bmb/ldag007 · Cited by 10
Predicting Empathy and Other Mental States During VR Sessions Using Sensor Data and Machine Learning
Kizhevska, E., Gjoreski, H., & Luštrek, M. (2025) · Sensors · doi:10.3390/s25185766 · Cited by 5
“Examples include monitoring healthcare professionals’ mood, well-being, and empathy via smartwatches and self-reports over the course of months [54], applying neural networks to brain imaging [55], and linking genetic or behavioral data to emotional responses [56].”
Thapa, S., Malviya, H., Verma, R., & Singh, J. (2025) · The Chemical Record · doi:10.1002/tcr.202500149 · Cited by 6
Cognitive shifts in pain perception under moral enhancement conditions: Evidence from an EEG study
Wang, H., Zhong, Y., Jia, S., Meng, Y., Bian, X., Zhang, X., & Liu, Y. (2025) · Brain and Cognition · doi:10.1016/j.bandc.2025.106273 · Cited by 4
Metadata
- Authors
- Nan, J., Herbert, M. S., Purpura, S., Henneken, A. N., Ramanathan, D., & Mishra, J.
- Affiliations
- University of California San Diego (US)
- VA San Diego Healthcare System (US)
- Corresponding author
- Nan, Jason
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2024-04-20
- Volume
- 24
- Issue
- 8
- Pages
- 2640
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC11053570
- OpenAlex
- W4395002494
- Cited by
- 22
- References
- 72
- Citations by year
- 2026: 10 · 2025: 10 · 2024: 2
- FWCI
- 12.92
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- T. Denny Sanford Institute for Empathy and Compassion
- Hope for Depression Research Foundation
- Stein Institute for Research on Aging
- Topics
- Health Sciences › Health Professions › General Health Professions › Healthcare professionals’ stress and burnout
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Social Sciences › Psychology › Social Psychology › Stress and Burnout Research
- Keywords
- healthcare workers, well-being, empathy, burnout, occupational stress, personalized machine learning, ecological momentary assessment, mood, social connectedness, sleep, diet, physical activity, individual differences, Shapley value, quality of care
- MeSH terms
- Machine Learning, Wearable Electronic Devices, Adult, Empathy, Female, Health Personnel, Humans, Male, Middle Aged
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Personalized Machine Learning-Based Prediction of Wellbeing and Empathy in Healthcare Professionals. https://app.cochat.ai/papers/10.3390/s24082640
- The paper
- Nan, J., Herbert, M. S., Purpura, S., Henneken, A. N., Ramanathan, D., & Mishra, J. (2024). Personalized Machine Learning-Based Prediction of Wellbeing and Empathy in Healthcare Professionals. Sensors. https://doi.org/10.3390/s24082640
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.