Artificial Intelligence in Healthcare and Regulation Challenges: a Mini Guide for (Mental) Health Professionals.

Artificial intelligence (AI) offers new perspectives in the healthcare sector, ranging from clinical decision support tools to new treatment strategies or alternative patient remote monitoring. However, as a disruptive technology, AI is associated with potential barriers, limitations and challenges for appropriate integration in medical practice. To avoid potential patient safety risks and harm, a robust regulatory framework is crucial to guide health professionals in their AI adoption in clinical practice. The European Union offers a new legal framework for the development and deployment of AI systems, the AI Act. This regulation was approved in March 2024 and will be fully applicable by 2025 to ensure that AI technologies are safe, transparent, and respect fundamental rights. However, these new regulatory concepts may be obscure for clinicians. This article aims to provide health professionals with the preliminary key points of regulation needed to interact adequately with these new AI applications and consider the potential risks of AI systems to patient safety.

Abortion Return Rates and Wait Times Before and After Texas' Executive Order Banning Abortion During COVID-19.

Objectives. To assess the associations between the executive order that Texas governor Greg Abbott issued on March 22, 2020, postponing procedures deemed not immediately medically necessary, and patients' access to abortion care in Texas. Methods. We used 17 515 individual-level patient records from 13 Texas abortion facilities for matched periods in 2019 and 2020 to examine differences in return rates for abortion after completion of a state-mandated ultrasound and median wait times between ultrasound and abortion visits for those who returned. Results. Patients were less likely to return for an abortion if they had an ultrasound while the executive order was under effect (82.8%) than in the same period in 2019 (90.4%; adjusted odds ratio = 2.06; 95% confidence interval = 1.12, 3.81). Compared with patients at or before 10.0 weeks' gestation at ultrasound, patients at more than 10 weeks' gestation had higher odds of not returning for an abortion or, if they returned, experienced greater wait times between ultrasound and abortion visits. Conclusions. Texas' executive order prohibiting abortion during the COVID-19 pandemic disrupted patients' access to care and disproportionately affected patients who were past 10 weeks' gestation. (Am J Public Health. 2024;114(10):1013-1023. https://doi.org/10.2105/AJPH.2024.307747).

Pott's Puffy Tumour: A Rare Complication of Sinusitis.

Introduction: Pott's puffy tumour is a rare entity defined by the presence of a subperiosteal abscess of the frontal bone associated with frontal osteomyelitis. Several predisposing conditions can lead to this entity, such as frontal sinusitis. Case description: We report the case of a 15-year-old patient who presented to the emergency department for headache, fever and forehead swelling. Computed tomography revealed severe pansinusitis complicated by a subperiosteal abscess associated with frontal osteomyelitis, leading to the diagnosis of Pott's puffy tumour. The management combined intravenous antibiotics and surgical drainage of both the sinusitis and subperiosteal abscess. Discussion: Pott's puffy tumour represents a rare but serious complication of frontal sinusitis. Clinicians should be aware of this potential complication as the diagnosis can be challenging at an early stage but may influence the subsequent prognosis. LEARNING POINTS: Pott's puffy tumour is a rare but severe complication of frontal sinusitis.The main symptoms are fever, headache, rhinorrhoea, and forehead swelling.Early diagnosis and treatment can prevent neurological sequelae and associated mortality.

[Febrile cervicalgia revealing infectious epiduritis : a case report]. / Cas clinique. Cervicalgies fébriles révélatrices d'une épidurite infectieuse.

Infectious epiduritis and epidural abscesses are relatively rare pathologies but with important neurological consequences. A low incidence associated with an insidious clinical presentation leads to frequent delays in diagnosis, which worsen the prognosis of patients with the development of neurological deficits. While the evaluation of risk factors, a careful clinical examination and biological tests can guide to the diagnosis, the key examination remains magnetic resonance imaging (MRI) while lumbar puncture remains contraindicated. Although surgery (spinal decompression) has long been the treatment of choice, the current management of patients with infectious epiduritis is debated between surgery and conservative treatment with systemic antibiotic therapy.

Les épidurites infectieuses et les abcès épiduraux sont des pathologies relativement rares, mais avec des conséquences neurologiques redoutables. Une faible incidence et une présentation clinique souvent insidieuse engendrent de fréquents retards de diagnostic qui péjorent le pronostic des patients avec le développement de déficits neurologiques. Si l'évaluation des facteurs de risque, un examen clinique scrupuleux et des analyses biologiques peuvent guider vers le diagnostic, l'examen-clé reste l'imagerie par résonance magnétique (IRM). La ponction lombaire est contre-indiquée. Bien que l'approche chirurgicale ait longtemps été le traitement de choix, un traitement plus conservateur basé sur une antibiothérapie systémique est également discuté.

At-home urine pregnancy test assessment after mifepristone and misoprostol for undesired pregnancy of unknown location.

OBJECTIVES: The ideal assessment after mifepristone and misoprostol for undesired pregnancy of unknown location (PUL) is unknown. STUDY DESIGN: We prospectively followed patients at Planned Parenthood League of Massachusetts (2019-2021) with PUL who received immediate mifepristone and misoprostol with serial at-home urine pregnancy tests (UPT) and in-office serum HCGs. RESULTS: Of 13 patients, 10 had a successful medication abortion. For those who completed UPTs (N = 9), all were negative by Day 14. Two abnormal pregnancies had positive UPTs on Day 14. CONCLUSION: A negative UPT on Day 14 may help determine complete abortion after medication abortion for undesired PUL. A positive UPT on Day 14 warrants further evaluation. IMPLICATION: Patients taking mifepristone and misoprostol in the setting of undesired PUL who cannot access serum testing may consider an at-home UPT to confirm complete abortion.

Human Decedent Identification Unit: identifying the deceased at a South African medico-legal mortuary.

The Johannesburg Forensic Pathology Services medico-legal mortuary perform postmortem examinations on all cases of unnatural deaths in the greater Johannesburg metropolitan area, in South Africa. Unidentified decedents can comprise up to 10.0% of the total number of annual admissions at this medico-legal mortuary. To address the identification of the deceased, the Human Decedent Identification Unit (ID Unit) was created to perform secondary examinations for identification purposes. The aim of this study was to report on the identification methods and success rate of the ID Unit. Over a period of 31 months (January 2018-July 2020), unidentified decedents comprised 8.1% (n = 693) of all cases at the Johannesburg mortuary. The ID Unit processed 385 (55.6%) unidentified individuals during this period, who were mostly adult (100%), Black (94.5%), males (91.7%). DNA samples were successfully collected from most cases in the form of hair (96.4%; n = 371), blood (92.2%; n = 355), and nail samples (90.1%; n = 347). Fingerprints retrieved in 65.5% of cases (n = 252). Ultimately, 87 persons (22.6%) were positively identified. Fingerprinting was the most successful method of identification (98.9% of cases; n = 86). One positive identification was facilitated through DNA analysis. The nationalities of the positively identified decedents were from South Africa (52.9%; n = 46), Zimbabwe (5.7%), Uganda (1.1%), Mozambique (1.1%), Malawi (1.1%), South Sudan (1.1%), and undisclosed in 36.8% of cases. Through the collaborative efforts of all the agencies involved, the impact of the work of this ID Unit is vast-not only for South African authorities but most importantly for the decedents and their families.

Patients' self-triage for unscheduled urgent care: a preliminary study on the accuracy and factors affecting the performance of a Belgian self-triage platform.

BACKGROUND: Management of unscheduled urgent care is a complex concern for many healthcare providers. Facing the challenge of appropriately dispatching unscheduled care, primary and emergency physicians have collaboratively implemented innovative strategies such as telephone triage. Currently, new original solutions tend to emerge with the development of new technologies. We created an interactive patient self-triage platform, ODISSEE, and aimed to explore its accuracy and potential factors affecting its performance using clinical case scenarios. METHODS: The ODISSEE platform was developed based on previously validated triage protocols for out-of-hours primary care. ODISSEE is composed of 18 icons leading to algorithmic questions that finally provide an advised orientation (emergency or primary care services). To investigate ODISSEE performance, we used 100 clinical case scenarios, each associated with a preestablished orientation determined by a group of experts. Fifteen volunteers were asked to self-triage with 50 randomly selected scenarios using ODISSEE on a digital tablet. Their triage results were compared with the experts' references. RESULTS: The 15 participants performed a total of 750 self-triages, which matched the experts references regarding the level of care in 85.6% of the cases. The orientation was incorrect in 14.4%, with an undertriage rate of 1.9% and an overtriage rate of 12.5%. The tool's specificity and sensitivity to advise participants on the appropriate level of care were 69% (95% CI: 64-74) and 97% (95% CI: 95-98) respectively. When combined with advice on the level of urgency, the tool only found the correct orientation in 68.4% with 9.2% of undertriages and 22.4% of overtriages. Some participant characteristics and the types of medical conditions demonstrated a significant association with the tool performance. CONCLUSION: Self-triage apps, such as the ODISSEE platform, could represent an innovative method to allow patients to self-triage to the most appropriate level of care. This study based on clinical vignettes highlights some positive arguments regarding ODISSEE safety, but further research is needed to assess the generalizability of such tools to the population without equity issues.

Mifepristone and Misoprostol for Undesired Pregnancy of Unknown Location.

OBJECTIVE: To compare immediate initiation with delayed initiation of medication abortion among patients with an undesired pregnancy of unknown location. METHODS: This retrospective cohort study used electronic medical record data from the Planned Parenthood League of Massachusetts (2014-2019) for patients who requested medication abortion with a last menstrual period (LMP) of 42 days or less and pregnancy of unknown location (no gestational sac) on initial ultrasonogram. Clinicians could initiate medication abortion with mifepristone followed by misoprostol while simultaneously excluding ectopic pregnancy with serial serum human chorionic gonadotropin (hCG) testing (same-day-start group) or establish a diagnosis with serial hCG tests and repeat ultrasonogram before initiating treatment (delay-for-diagnosis group). We compared primary safety outcomes (time to diagnosis of pregnancy location [rule out ectopic], emergency department visits, adverse events, and nonadherence with follow-up) between groups. We also reported secondary efficacy outcomes: time to complete abortion, successful medication abortion (no uterine aspiration), and ongoing pregnancy. RESULTS: Of 5,619 medication abortion visits for patients with an LMP of 42 days or less, 452 patients had pregnancy of unknown location (8.0%). Three patients underwent immediate uterine aspiration, 55 had same-day start, and 394 had delay for diagnosis. Thirty-one patients (7.9%), all in the delay-for-diagnosis group, were treated for ectopic pregnancy, including four that were ruptured. Among patients with no major ectopic pregnancy risk factors (n=432), same-day start had shorter time to diagnosis (median 5.0 days vs 9.0 days; P=.005), with no significant difference in emergency department visits (adjusted odds ratio [aOR] 0.90, 95% CI 0.43-1.88) or nonadherence with follow-up (aOR 0.92, 95% CI 0.39-2.15). Among patients who proceeded with abortion (n=270), same-day start had shorter time to complete abortion (median 5.0 days vs 19.0 days; P<.001). Of those who had medication abortion with known outcome (n=170), the rate of successful medication abortion was lower (85.4% vs 96.7%; P=.013) and the rate of ongoing pregnancy was higher (10.4% vs 2.5%; P=.041) among patients in the same-day-start group. CONCLUSION: In patients with undesired pregnancy of unknown location, immediate initiation of medication abortion is associated with more rapid exclusion of ectopic pregnancy and pregnancy termination but lower abortion efficacy.

Clinical prediction models for diagnosis of COVID-19 among adult patients: a validation and agreement study.

BACKGROUND: Since the beginning of the pandemic, hospitals have been constantly overcrowded, with several observed waves of infected cases and hospitalisations. To avoid as much as possible this situation, efficient tools to facilitate the diagnosis of COVID-19 are needed. OBJECTIVE: To evaluate and compare prediction models to diagnose COVID-19 identified in a systematic review published recently using performance indicators such as discrimination and calibration measures. METHODS: A total of 1618 adult patients present at two Emergency Department triage centers and for whom qRT-PCR tests had been performed were included in this study. Six previously published models were reconstructed and assessed using diagnostic tests as sensitivity (Se) and negative predictive value (NPV), discrimination (Area Under the Roc Curve (AUROC)) and calibration measures. Agreement was also measured between them using Kappa's coefficient and IntraClass Correlation Coefficient (ICC). A sensitivity analysis has been conducted by waves of patients. RESULTS: Among the 6 selected models, those based only on symptoms and/or risk exposure were found to be less efficient than those based on biological parameters and/or radiological examination with smallest AUROC values (< 0.80). However, all models showed good calibration and values above > 0.75 for Se and NPV but poor agreement (Kappa and ICC < 0.5) between them. The results of the first wave were similar to those of the second wave. CONCLUSION: Although quite acceptable and similar results were found between all models, the importance of radiological examination was also emphasized, making it difficult to find an appropriate triage system to classify patients at risk for COVID-19.

A mixed methods study of provider factors in buprenorphine treatment retention.

BACKGROUND: Low retention is a persistent challenge in the delivery of buprenorphine treatment for opioid use disorder (OUD). The goal of this study was to identify provider factors that could drive differences in treatment retention while accounting for the contribution of patient characteristics to retention. METHODS: We developed a novel a mixed-methods approach to explore provider factors that could drive retention while accounting for patient characteristics. We used Medicaid claims data from North Carolina in the United States to identify patient characteristics associated with higher retention. We then identified providers who achieved high and low retention rates. We matched high- and low-retention providers on their patients' characteristics. This matching created high- and low-retention provider groups whose patients had similar characteristics. We then interviewed providers while blinded to which belonged in the high- and low-retention groups on aspects of their practice that could affect retention rates, such as treatment criteria, treatment cost, and services offered. RESULTS: Less than half of patients achieved 180-day treatment retention with large differences by race and ethnicity. We did not find evidence that providers who achieved higher retention consistently did so by providing more comprehensive services or selecting for more stable patients. Rather, our findings suggest use of "high-threshold" clinical approaches, such as requiring participation in psychosocial services or strictly limiting dosages, explain differences in retention rates between providers whose patients have similar characteristics. All low-retention providers interviewed used a high-threshold practice compared to half of high-retention providers interviewed. Requiring patients to participate in psychosocial services, which were often paid out-of-pocket, appeared to be especially important in limiting retention. CONCLUSION: Providers who adopt low-threshold approaches to treatment may achiever higher retention rates than those who adopt high-threshold approaches. Addressing cost barriers and systemic racism are likely also necessary for improving buprenorphine treatment retention.

Dilation and evacuation with an abdominal cerclage at 21 weeks gestation: A case report.

This case demonstrates a successful dilation and evacuation (D&E) at 21 weeks gestation for a patient with abdominal cerclage without initial advanced dilation. We followed a 2-day protocol with placement of 5 laminaria and mifepristone for cervical preparation without complication.

Immersion in an emergency department triage center during the Covid-19 outbreak: first report of the Liège University hospital experience.

OBJECTIVES: Since the beginning of the novel coronavirus outbreak, different strategies have been explored to stem the spread of the disease and appropriately manage patient flow. Triage, an effective solution proposed in disaster medicine, also works well to manage Emergency Department (ED) flow. The aim of this study was to describe the role of an ED Triage Center for patients with suspected novel coronavirus disease (Covid-19) and characterize the patient flow. METHODS: In March 2020, we established a Covid-19 triage center close to the Liège University EDs. From March 2 to March 23, we planned to analyze the specific flow of patients admitted to this triage zone and their characteristics in terms of inner specificities, work-up and management. During this period, all patients presented to the ED with symptoms suggestive of Covid-19 were included in the study. RESULTS: A total amount of 1071 patients presented to the triage center during the study period. 41.50% of the patients presented with flu-like symptoms. In 82.00% of the cases, no risk factor of virus transmission was found. The SARS-Cov2 positive patients represented 29.26% of the screened patients. 83.00% of patients were discharged home while 17.00% were admitted to the hospital. CONCLUSION: Our experience suggests that triage centers for the assessment and management of Covid-19 suspected patients is an essential key strategy to prevent the spread of the disease among non-symptomatic patients who present to the EDs for care. This allows for a disease-centered work-up and safer diversion of Covid-19 patients to specific hospital units.

Advanced triage to redirect non-urgent Emergency Department visits to alternative care centers: the PERSEE algorithm.

OBJECTIVES: Primary care treatable visits in the Emergency Department (ED) are part of the different factors leading to the overcrowding. Their triage and diversion to alternative care centers could potentially help manage the increasing inflow provided the establishment of an advanced triage to ensure patients' safety. We aim to suggest a new triage tool, PERSEE, and prove its feasibility, safety and performance. METHODS: All self-referrals presented to the ED were triaged with the PERSEE algorithm: first, patients were classified with a five-level ED acuity scale and then evaluated by algorithms to determine their appropriate category (ED or Primary Care). Patients were eligible for a redirection if they were triaged by the acuity scale as level 3 or lower, considered as ambulatory patients and finally categorized as primary care patients. We defined appropriate redirections as patients requiring less than three emergency resources, no emergency-specific treatment and no hospitalization. RESULTS: During the study, 1999 patients were admitted to the ED. Among those, 1333 patients were self-referred (66.9%) of whom 1167 patients were triaged as level 3 or below (58.6%) and 775 patients triaged as ambulatory (39.0%). Among the 775 patients, 200 patients were categorized as primary care treatable (10.0%) and thereby, as potentially eligible for a redirection. We noticed an error rate of 7%, sensitivity of 24.06% and specificity of 97.6%. The redirection rate reached 15% of the self-referrals. CONCLUSION: These results indicate that PERSEE triage could lead to a safe redirection and could be an efficient tool to reduce ED crowding provided several adjustments.

Reliability and validity of an original nurse telephone triage tool for out-of-hours primary care calls: the SALOMON algorithm.

OBJECTIVES: Due to the persistent primary care physicians shortage and the substantial increase in their workload, the organization of primary care calls during out-of-hours periods has become an everyday challenge. The SALOMON algorithm is an original nurse telephone triage tool allowing to dispatch patients to the best level of care according to their conditions. This study evaluated its reliability and criterion validity in rea-life settings. METHODS: In this 5-year study, out-of-hours primary care calls were dispatched into four categories: Emergency Medical Services Intervention (EMSI), Emergency Department referred Consultation (EDRC), Primary Care Physician Home visit (PCPH), and Primary Care Physician Delayed visit (PCPD). We included data of patients' triage category, resources, and destination. Patients included into the primary care cohort were classified undertriaged if they had to be redirected to an emergency department (ED). Patients from the ED cohort were considered overtriaged if they did not require at least three diagnostic resources, one emergency-specific treatment or any hospitalization. In the ED cohort, only patients from the University Hospitals were considered. RESULTS: 10,207 calls were triaged using the SALOMON tool: 19.2% were classified as EMSI, 15.8% as EDRC, 62.8% as PCPH, and 2.2% as PCPD. The triage was appropriate for 85.5% of the calls with a 14.5% overtriage rate. In the PCPD/PCPH cohort, 96.9% of the calls were accurately triaged and 3.1% were undertriaged. SALOMON sensitivity and specificity reached 76.6% and 98.3%, respectively. CONCLUSION: SALOMON algorithm is a valid triage tool that has the potential to improve the organization of out-of-hours primary care work.

Appropriateness of psychiatric advance directives facilitated by peer support specialists and clinicians on Assertive Community Treatment teams.

BACKGROUND: Psychiatric advance directives (PADs) are used to document a person's treatment preferences for a future mental health crisis. Peer support specialists have been proposed to facilitate PADs, but little is known about the quality of peer versus clinician facilitated PADs. AIMS: This study examined whether PAD documents facilitated by peer specialists and non-peer clinicians differed in the mix of treatment requests and refusals and expert ratings of feasibility and consistency. METHODS: Analyses were conducted of content and expert ratings of 72 PAD documents from a randomized trial of PAD facilitation by peers and clinicians on Assertive Community Treatment (ACT) teams. A count of treatment refusals and requests was used to classify documents as predominantly prescriptive, proscriptive, or balanced. Regression was used to estimate relationships between PAD facilitator type and content. RESULTS: Peer-facilitated PADs were significantly more likely to be predominantly prescriptive than were PADs facilitated by non-peer clinicians. Prescriptive PADs were more likely to receive expert ratings of high feasibility and consistency. CONCLUSIONS: Results should alleviate some clinicians' apprehensions regarding the appropriateness of peer-facilitated PADs, such as the concern that people with lived experience with mental illness might encourage other consumers to use their PAD primarily for treatment refusals.