Digital health, including telemedicine, has increased access to abortion care. The convenience, flexibility of appointment times, and ensured privacy to abortion users may make abortion services via telemedicine preferable. This scoping review systematically mapped studies conducted on abortion services via telemedicine, including their effectiveness and acceptability for abortion users and providers. All published papers included abortion services via telemedicine in the United States were considered. Articles were searched in PubMed, CINAHL, and Google Scholar databases in September 2022. The findings were synthesized narratively, and the PRISMA-ScR guidelines were used to report this study. Out of 757 retrieved articles, 33 articles were selected based on the inclusion criteria. These studies were published between 2011 and 2022, with 24 published in the last 3 years. The study found that telemedicine increased access to abortion care in the United States, especially for people in remote areas or those worried about stigma from in-person visits. The effectiveness of abortion services via telemedicine was comparable to in-clinic visits, with 6% or fewer abortions requiring surgical intervention. Both care providers and abortion seekers expressed positive perceptions of telemedicine-based abortion services. However, abortion users reported mixed emotions, with some preferring in-person visits. The most common reasons for choosing telemedicine included the distance to the abortion clinic, convenience, privacy, cost, flexibility of appointment times, and state laws imposing waiting periods or restrictive policies. Telemedicine offered a preferable option for abortion seekers and providers. The feasibility of accessing abortion services via telemedicine in low-resource settings needs further investigation.

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Artificial intelligence (AI) systems hold great promise to improve healthcare over the next decades. Specifically, AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of applications. In this work, we propose and evaluate a unified Holistic AI in Medicine (HAIM) framework to facilitate the generation and testing of AI systems that leverage multimodal inputs. Our approach uses generalizable data pre-processing and machine learning modeling stages that can be readily adapted for research and deployment in healthcare environments. We evaluate our HAIM framework by training and characterizing 14,324 independent models based on HAIM-MIMIC-MM, a multimodal clinical database (N=34,537 samples) containing 7,279 unique hospitalizations and 6,485 patients, spanning all possible input combinations of 4 data modalities (i.e., tabular, time-series, text, and images), 11 unique data sources and 12 predictive tasks. We show that this framework can consistently and robustly produce models that outperform similar single-source approaches across various healthcare demonstrations (by 6-33%), including 10 distinct chest pathology diagnoses, along with length-of-stay and 48-hour mortality predictions. We also quantify the contribution of each modality and data source using Shapley values, which demonstrates the heterogeneity in data modality importance and the necessity of multimodal inputs across different healthcare-relevant tasks. The generalizable properties and flexibility of our Holistic AI in Medicine (HAIM) framework could offer a promising pathway for future multimodal predictive systems in clinical and operational healthcare settings.

Machine learning for hospital operations is under-studied. We present a prediction pipeline that uses live electronic health-records for patients in a UK teaching hospital’s emergency department (ED) to generate short-term, probabilistic forecasts of emergency admissions. A set of XGBoost classifiers applied to 109,465 ED visits yielded AUROCs from 0.82 to 0.90 depending on elapsed visit-time at the point of prediction. Patient-level probabilities of admission were aggregated to forecast the number of admissions among current ED patients and, incorporating patients yet to arrive, total emergency admissions within specified time-windows. The pipeline gave a mean absolute error (MAE) of 4.0 admissions (mean percentage error of 17%) versus 6.5 (32%) for a benchmark metric. Models developed with 104,504 later visits during the Covid-19 pandemic gave AUROCs of 0.68–0.90 and MAE of 4.2 (30%) versus a 4.9 (33%) benchmark. We discuss how we surmounted challenges of designing and implementing models for real-time use, including temporal framing, data preparation, and changing operational conditions.

Patients are 20% less likely to die of sepsis because a new AI system developed at Johns Hopkins University catches symptoms hours earlier than traditional methods, an extensive hospital study demonstrates. The system, created by a Johns Hopkins researcher whose young nephew died from sepsis, scours medical records and clinical notes to identify patients at risk of life-threatening complications. The work, which could significantly cut patient mortality from one of the top causes of hospital deaths worldwide, is published today in Nature Medicine and npj Digital Medicine. "It is the first instance where AI is implemented at the bedside, used by thousands of providers, and where we're seeing lives saved," said Suchi Saria, founding research director of the Malone Center for Engineering in Healthcare at Johns Hopkins and lead author of the studies, which evaluated more than a half million patients over two years. "This is an extraordinary leap that will save thousands of sepsis patients annually. And the approach is now being applied to improve outcomes in other important problem areas beyond sepsis."

Digital health data are multimodal and high-dimensional. A patient’s health state can be characterized by a multitude of signals including medical imaging, clinical variables, genome sequencing, conversations between clinicians and patients, and continuous signals from wearables, among others. This high volume, personalized data stream aggregated over patients’ lives has spurred interest in developing new artificial intelligence (AI) models for higher-precision diagnosis, prognosis, and tracking. While the promise of these algorithms is undeniable, their dissemination and adoption have been slow, owing partially to unpredictable AI model performance once deployed in the real world. We posit that one of the rate-limiting factors in developing algorithms that generalize to real-world scenarios is the very attribute that makes the data exciting—their high-dimensional nature. This paper considers how the large number of features in vast digital health data can challenge the development of robust AI models—a phenomenon known as “the curse of dimensionality” in statistical learning theory. We provide an overview of the curse of dimensionality in the context of digital health, demonstrate how it can negatively impact out-of-sample performance, and highlight important considerations for researchers and algorithm designers.

Alzheimer’s disease is a neurodegenerative disease that imposes a substantial financial burden on society. A number of machine learning studies have been conducted to predict the speed of its progression, which varies widely among different individuals, for recruiting fast progressors in future clinical trials. However, because the data in this field are very limited, two problems have yet to be solved: the first is that models built on limited data tend to induce overfitting and have low generalizability, and the second is that no cross-cohort evaluations have been done. Here, to suppress the overfitting caused by limited data, we propose a hybrid machine learning framework consisting of multiple convolutional neural networks that automatically extract image features from the point of view of brain segments, which are relevant to cognitive decline according to clinical findings, and a linear support vector classifier that uses extracted image features together with non-image information to make robust final predictions. The experimental results indicate that our model achieves superior performance (accuracy: 0.88, area under the curve [AUC]: 0.95) compared with other state-of-the-art methods. Moreover, our framework demonstrates high generalizability as a result of evaluations using a completely different cohort dataset (accuracy: 0.84, AUC: 0.91) collected from a different population than that used for training.

Health care is a human process that generates data from human lives, as well as the care they receive. Machine learning has worked in health to bring new technology into this sociotechnical environment, using data to support a vision of healthier living for everyone. Interdisciplinary fields of research like machine learning for health bring different values and judgements together, requiring that those value choices be deliberate and measured. More than just abstract ideas, our values are the basis upon which we choose our research topics, set up research collaborations, execute our research methodologies, make assessments of scientific and technical correctness, proceed to product development, and finally operationalize deployments and describe policy. For machine learning to achieve its aims of supporting healthier living while minimizing harm, we believe that a deeper introspection of our field’s values and contentions is overdue. In this perspective, we highlight notable areas in need of attention within the field. We believe deliberate and informed introspection will lead our community to renewed opportunities for understanding disease, new partnerships with clinicians and patients, and allow us to better support people and communities to live healthier, dignified lives.

Research in computer analysis of medical images bears many promises to improve patients’ health. However, a number of systematic challenges are slowing down the progress of the field, from limitations of the data, such as biases, to research incentives, such as optimizing for publication. In this paper we review roadblocks to developing and assessing methods. Building our analysis on evidence from the literature and data challenges, we show that at every step, potential biases can creep in. On a positive note, we also discuss on-going efforts to counteract these problems. Finally we provide recommendations on how to further address these problems in the future.

Machine learning (ML) is a rapidly advancing field with increasing utility in health care. We conducted a systematic review and critical appraisal of ML applications in vascular surgery. MEDLINE, Embase, and Cochrane CENTRAL were searched from inception to March 1, 2021. Study screening, data extraction, and quality assessment were performed by two independent reviewers, with a third author resolving discrepancies. All original studies reporting ML applications in vascular surgery were included. Publication trends, disease conditions, methodologies, and outcomes were summarized. Critical appraisal was conducted using the PROBAST risk-of-bias and TRIPOD reporting adherence tools. We included 212 studies from a pool of 2235 unique articles. ML techniques were used for diagnosis, prognosis, and image segmentation in carotid stenosis, aortic aneurysm/dissection, peripheral artery disease, diabetic foot ulcer, venous disease, and renal artery stenosis. The number of publications on ML in vascular surgery increased from 1 (1991–1996) to 118 (2016–2021). Most studies were retrospective and single center, with no randomized controlled trials. The median area under the receiver operating characteristic curve (AUROC) was 0.88 (range 0.61–1.00), with 79.5% [62/78] studies reporting AUROC ≥ 0.80. Out of 22 studies comparing ML techniques to existing prediction tools, clinicians, or traditional regression models, 20 performed better and 2 performed similarly. Overall, 94.8% (201/212) studies had high risk-of-bias and adherence to reporting standards was poor with a rate of 41.4%. Despite improvements over time, study quality and reporting remain inadequate. Future studies should consider standardized tools such as PROBAST and TRIPOD to improve study quality and clinical applicability.