Pub Date : 2026-01-26DOI: 10.1038/s41746-026-02369-z
Alex Howard, Peter L. Green, Yinzheng Zhong, David M. Hughes, Alessandro Gerada, Simon Maskell, Anoop Velluva, Iain E. Buchan, William Hope
Predicting antibiotic treatment outcomes could help tackle antibiotic resistance by guiding prescribing decisions. Existing approaches do not quantitatively incorporate the judgment of clinician users. Our antibiotic decision-making algorithm predicted treatment outcomes for 13 antibiotics using clinical prediction models trained on prescribing and urine culture data from 93,906 patients, then weighted outcomes using treatment decisions made by 49 clinicians in an antibiotic choice ranking exercise. In a simulation using Emergency Department data, the algorithm chose more correctly-targeted World Health Organization Access category antibiotics (75.6% of cases versus 11.9%, 95% confidence interval of difference 57.6% to 69.7%, p < 0.001) and oral antibiotics (69% versus 22.6%, 95% confidence interval of difference 39.5% to 53.4%, p < 0.001) than human prescribers, and fewer intravenous antibiotics (31.2% versus 65.8%, 95% confidence interval of difference −41.9% to −27.1%, p < 0.001). These results show that our algorithm could improve antibiotic prescribing decisions by combining human judgment with data-driven probability predictions.
{"title":"Algorithmic antibiotic decision-making in urinary tract infection using prescriber-informed prediction of treatment utility","authors":"Alex Howard, Peter L. Green, Yinzheng Zhong, David M. Hughes, Alessandro Gerada, Simon Maskell, Anoop Velluva, Iain E. Buchan, William Hope","doi":"10.1038/s41746-026-02369-z","DOIUrl":"https://doi.org/10.1038/s41746-026-02369-z","url":null,"abstract":"Predicting antibiotic treatment outcomes could help tackle antibiotic resistance by guiding prescribing decisions. Existing approaches do not quantitatively incorporate the judgment of clinician users. Our antibiotic decision-making algorithm predicted treatment outcomes for 13 antibiotics using clinical prediction models trained on prescribing and urine culture data from 93,906 patients, then weighted outcomes using treatment decisions made by 49 clinicians in an antibiotic choice ranking exercise. In a simulation using Emergency Department data, the algorithm chose more correctly-targeted World Health Organization Access category antibiotics (75.6% of cases versus 11.9%, 95% confidence interval of difference 57.6% to 69.7%, <jats:italic>p</jats:italic> < 0.001) and oral antibiotics (69% versus 22.6%, 95% confidence interval of difference 39.5% to 53.4%, <jats:italic>p</jats:italic> < 0.001) than human prescribers, and fewer intravenous antibiotics (31.2% versus 65.8%, 95% confidence interval of difference −41.9% to −27.1%, <jats:italic>p</jats:italic> < 0.001). These results show that our algorithm could improve antibiotic prescribing decisions by combining human judgment with data-driven probability predictions.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"1 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146048235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-24DOI: 10.1038/s41746-025-02320-8
Yue Shi,Chi Chiu Wang,Yongkang Yang,Qin Li,Pui Wah Chung,Yao Wang
This systematic review and Bayesian network meta-analysis assessed the diagnostic accuracy of wearable digital technology (WDT) in monitoring women's fertility window compared to conventional methods. 8 databases were searched until January 1, 2025. 27 studies were included in the analysis, where 13 studies applied WDT in tracking ovulation. We evaluated the accuracy, sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver operating characteristic (SROC) of WDT, and compared the performance of different designs of WDT by NMA analysis. The revised QUADAS-2 tool was used for quality assessment. Our results demonstrated that WDT presented a pooled accuracy of 0.88 (95% CI: 0.86-0.90), with a sensitivity of 0.79 (95% CI: 0.70-0.87), specificity of 0.80 (95% CI: 0.60-1.00), PLR of 5.87 (95% CI: 2.49-13.88), NLR of 0.25 (95% CI: 0.13-0.51), DOR of 23.39 (95% CI: 3.45-158.71), and SROC of 0.75. Notably, WDT provided best detection for 3 days surrounding ovulation. Ring-type device, the use of multi-physiological parameters and the random forest algorithm method improved efficiency for WDT in the detection fertility window. Overall, WDT holds promise for fertility window tracking and could offer tentative support for optimizing pregnancy planning and monitoring women's reproductive health.
{"title":"The diagnostic accuracy of wearable digital technology in detecting fertility window and menstrual cycles: a systematic review and Bayesian network meta-analysis.","authors":"Yue Shi,Chi Chiu Wang,Yongkang Yang,Qin Li,Pui Wah Chung,Yao Wang","doi":"10.1038/s41746-025-02320-8","DOIUrl":"https://doi.org/10.1038/s41746-025-02320-8","url":null,"abstract":"This systematic review and Bayesian network meta-analysis assessed the diagnostic accuracy of wearable digital technology (WDT) in monitoring women's fertility window compared to conventional methods. 8 databases were searched until January 1, 2025. 27 studies were included in the analysis, where 13 studies applied WDT in tracking ovulation. We evaluated the accuracy, sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver operating characteristic (SROC) of WDT, and compared the performance of different designs of WDT by NMA analysis. The revised QUADAS-2 tool was used for quality assessment. Our results demonstrated that WDT presented a pooled accuracy of 0.88 (95% CI: 0.86-0.90), with a sensitivity of 0.79 (95% CI: 0.70-0.87), specificity of 0.80 (95% CI: 0.60-1.00), PLR of 5.87 (95% CI: 2.49-13.88), NLR of 0.25 (95% CI: 0.13-0.51), DOR of 23.39 (95% CI: 3.45-158.71), and SROC of 0.75. Notably, WDT provided best detection for 3 days surrounding ovulation. Ring-type device, the use of multi-physiological parameters and the random forest algorithm method improved efficiency for WDT in the detection fertility window. Overall, WDT holds promise for fertility window tracking and could offer tentative support for optimizing pregnancy planning and monitoring women's reproductive health.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"30 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pleural and ascitic cytology is essential for diagnosing metastatic cancer and predicting tumor origin, yet microscopic observation alone often leads to low accuracy and observer variability. Although deep learning shows great potential in pathology, its use in pleural and ascitic cytology remains limited. We present a data-efficient deep learning framework (MAMILE-UNI) that directly detects malignancy in pleural and ascitic effusions from cytology smear or cell block whole slide images (WSIs); in evaluation of 1250 WSIs, MAMILE-UNI achieved high AUROC, the mean of sensitivity and specificity (MeanSS), and accuracy. Furthermore, in identifying the origin of cancer from cytology smears, the method also achieved high accuracy, MeanSS and AUROC. Identifying the origin of cancer from histopathological slide images is equally important, and our method achieved high accuracy, precision, sensitivity, F1 score, specificity, MeanSS and AUROC in evaluation with 1,196 WSIs. Fisher's exact test validated the model predictions (p < 0.001).
{"title":"Deep learning for malignancy and tumor origin prediction using cytology or histopathology whole slide images.","authors":"Ching-Wei Wang,Tzu-Chiao Chu,Tzu-Kang Wu,Yu-Pang Chung,Sin-Si Lin,Tai-Kuang Chao","doi":"10.1038/s41746-026-02359-1","DOIUrl":"https://doi.org/10.1038/s41746-026-02359-1","url":null,"abstract":"Pleural and ascitic cytology is essential for diagnosing metastatic cancer and predicting tumor origin, yet microscopic observation alone often leads to low accuracy and observer variability. Although deep learning shows great potential in pathology, its use in pleural and ascitic cytology remains limited. We present a data-efficient deep learning framework (MAMILE-UNI) that directly detects malignancy in pleural and ascitic effusions from cytology smear or cell block whole slide images (WSIs); in evaluation of 1250 WSIs, MAMILE-UNI achieved high AUROC, the mean of sensitivity and specificity (MeanSS), and accuracy. Furthermore, in identifying the origin of cancer from cytology smears, the method also achieved high accuracy, MeanSS and AUROC. Identifying the origin of cancer from histopathological slide images is equally important, and our method achieved high accuracy, precision, sensitivity, F1 score, specificity, MeanSS and AUROC in evaluation with 1,196 WSIs. Fisher's exact test validated the model predictions (p < 0.001).","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"31 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-24DOI: 10.1038/s41746-026-02351-9
Mandi Tang,Mingming Fan,Ge Lin Kan
Improving adherence to physio-cognitive interventions is crucial for mitigating frailty and dementia in older adults, many of them staying in nursing homes. Digital interventions for nursing home residents, however, are often overlooked in both the academic community and the marketplace, let alone for adherence. This article presents a three-phase co-design study with frail nursing home residents (mean age: 80.42 years) to gamify "a physio-cognitive virtual reality intervention" (aPCVRi) prototype, a self-directed stationary bike simulator for physical activity controlling the integrated life-size VR local streets for reminiscence therapy and multisensory natural locomotion. To co-design gamification for playfulness, three design requirements (livingness, familiarity, and presence) were co-identified with participants and then translated into four strategies, which were then developed into four gamified modules. After integration, we found increases in participants' duration adherence (from 14.56 to 23.76 minutes), retention adherence, the number of voluntary enrollments, and psychological benefits. The four proposed guidelines for aPCVRi, therefore, emphasize playfulness and happiness, consistent with global efforts to improve dementia care.
{"title":"Co-designing with frail nursing home residents to gamify a VR-based physio-cognitive intervention.","authors":"Mandi Tang,Mingming Fan,Ge Lin Kan","doi":"10.1038/s41746-026-02351-9","DOIUrl":"https://doi.org/10.1038/s41746-026-02351-9","url":null,"abstract":"Improving adherence to physio-cognitive interventions is crucial for mitigating frailty and dementia in older adults, many of them staying in nursing homes. Digital interventions for nursing home residents, however, are often overlooked in both the academic community and the marketplace, let alone for adherence. This article presents a three-phase co-design study with frail nursing home residents (mean age: 80.42 years) to gamify \"a physio-cognitive virtual reality intervention\" (aPCVRi) prototype, a self-directed stationary bike simulator for physical activity controlling the integrated life-size VR local streets for reminiscence therapy and multisensory natural locomotion. To co-design gamification for playfulness, three design requirements (livingness, familiarity, and presence) were co-identified with participants and then translated into four strategies, which were then developed into four gamified modules. After integration, we found increases in participants' duration adherence (from 14.56 to 23.76 minutes), retention adherence, the number of voluntary enrollments, and psychological benefits. The four proposed guidelines for aPCVRi, therefore, emphasize playfulness and happiness, consistent with global efforts to improve dementia care.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"3 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1038/s41746-026-02391-1
Moshe Gish, Carmit Rapaport
{"title":"Agentic AI can help hospitals prepare for unprecedented weather","authors":"Moshe Gish, Carmit Rapaport","doi":"10.1038/s41746-026-02391-1","DOIUrl":"https://doi.org/10.1038/s41746-026-02391-1","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"69 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146032786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1038/s41746-026-02358-2
Rachel Marjorie Wei Wen Tseng, Li Cheng Ong, Jocelyn Hui Lin Goh, Yibing Chen, Tina Chen, Elaine Lum, Yih-Chung Tham
{"title":"Prospective real-world implementation of deep learning systems in healthcare: a systematic review guided by implementation science","authors":"Rachel Marjorie Wei Wen Tseng, Li Cheng Ong, Jocelyn Hui Lin Goh, Yibing Chen, Tina Chen, Elaine Lum, Yih-Chung Tham","doi":"10.1038/s41746-026-02358-2","DOIUrl":"https://doi.org/10.1038/s41746-026-02358-2","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"24 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146032790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The advent of artificial intelligence in cardiovascular imaging holds immense potential for earlier diagnoses, precision medicine, and improved disease management. However, the presence of sex-based disparities and strategies to mitigate biases in deep learning models for cardiac imaging remain understudied. In this study, we analyzed algorithmic bias in a foundation model that was pretrained on cardiac magnetic resonance imaging and radiology reports from multiple institutes and finetuned to estimate ejection fraction (EF) on the UK Biobank dataset. The model performed significantly worse in EF estimation for females than males in the diagnosis of reduced EF. Algorithmic fairness did not improve despite masking of protected attributes in radiology reports and data resampling, although explicit input of sex in model finetuning may improve EF estimation in some cases. The underdiagnosis of reduced EF among females holds critical implications for the exacerbation of existing sex-based disparities in cardiovascular health. We advise caution in the development of models for cardiovascular imaging to avoid such pitfalls.
{"title":"Sex disparities in deep learning estimation of ejection fraction from cardiac magnetic resonance imaging.","authors":"Dhamanpreet Kaur,Rohan Shad,Abhinav Kumar,Mrudang Mathur,Joseph Cho,Robyn Fong,Cyril Zakka,Curran Phillips,William Hiesinger","doi":"10.1038/s41746-025-02330-6","DOIUrl":"https://doi.org/10.1038/s41746-025-02330-6","url":null,"abstract":"The advent of artificial intelligence in cardiovascular imaging holds immense potential for earlier diagnoses, precision medicine, and improved disease management. However, the presence of sex-based disparities and strategies to mitigate biases in deep learning models for cardiac imaging remain understudied. In this study, we analyzed algorithmic bias in a foundation model that was pretrained on cardiac magnetic resonance imaging and radiology reports from multiple institutes and finetuned to estimate ejection fraction (EF) on the UK Biobank dataset. The model performed significantly worse in EF estimation for females than males in the diagnosis of reduced EF. Algorithmic fairness did not improve despite masking of protected attributes in radiology reports and data resampling, although explicit input of sex in model finetuning may improve EF estimation in some cases. The underdiagnosis of reduced EF among females holds critical implications for the exacerbation of existing sex-based disparities in cardiovascular health. We advise caution in the development of models for cardiovascular imaging to avoid such pitfalls.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"11 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1038/s41746-025-02309-3
Morteza Rohanian, Roya Hüppi, Farhad Nooralahzadeh, Noemi Dannecker, Yves Pauli, Werner Surbeck, Iris Sommer, Wolfram Hinzen, Nicolas Langer, Michael Krauthammer, Philipp Homan
Speech provides a rich behavioral signal of psychosis, yet its diagnostic use remains limited because speech patterns vary widely across individuals and contexts. We model this variability as uncertainty, capturing how consistently speech features indicate symptom expression. We introduce a multimodal model that integrates acoustic and linguistic information to predict symptom severity and psychosis-related traits across the spectrum, from high schizotypy to clinical psychosis. By estimating uncertainty for each modality, the model learns when to rely on specific signals, adapting to speech quality and task context to improve accuracy and interpretability. Using speech from 114 participants-32 with early psychosis and 82 with low or high schizotypy-recorded in German across structured and narrative tasks, the model achieved an F1-score of 83% (ECE = 0.045), demonstrating robust and well-calibrated performance. Uncertainty estimation further revealed which speech markers most reliably indicated symptoms, including pitch variability, fluency disruptions, and spectral instability.
{"title":"Uncertainty modeling in multimodal speech analysis across the psychosis spectrum.","authors":"Morteza Rohanian, Roya Hüppi, Farhad Nooralahzadeh, Noemi Dannecker, Yves Pauli, Werner Surbeck, Iris Sommer, Wolfram Hinzen, Nicolas Langer, Michael Krauthammer, Philipp Homan","doi":"10.1038/s41746-025-02309-3","DOIUrl":"https://doi.org/10.1038/s41746-025-02309-3","url":null,"abstract":"<p><p>Speech provides a rich behavioral signal of psychosis, yet its diagnostic use remains limited because speech patterns vary widely across individuals and contexts. We model this variability as uncertainty, capturing how consistently speech features indicate symptom expression. We introduce a multimodal model that integrates acoustic and linguistic information to predict symptom severity and psychosis-related traits across the spectrum, from high schizotypy to clinical psychosis. By estimating uncertainty for each modality, the model learns when to rely on specific signals, adapting to speech quality and task context to improve accuracy and interpretability. Using speech from 114 participants-32 with early psychosis and 82 with low or high schizotypy-recorded in German across structured and narrative tasks, the model achieved an F1-score of 83% (ECE = 0.045), demonstrating robust and well-calibrated performance. Uncertainty estimation further revealed which speech markers most reliably indicated symptoms, including pitch variability, fluency disruptions, and spectral instability.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":" ","pages":""},"PeriodicalIF":15.1,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146030348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：