A paradigm shift?-On the ethics of medical large language models

After a wave of breakthroughs in image-based medical diagnostics and risk prediction models, machine learning (ML) has turned into a normal science. However, prominent researchers are claiming that another paradigm shift in medical ML is imminent-due to most recent staggering successes of large language models-from single-purpose applications toward generalist models, driven by natural language. This article investigates the implications of this paradigm shift for the ethical debate. Focusing on issues like trust, transparency, threats of patient autonomy, responsibility issues in the collaboration of clinicians and ML models, fairness, and privacy, it will be argued that the main problems will be continuous with the current debate. However, due to functioning of large language models, the complexity of all these problems increases. In addition, the article discusses some profound challenges for the clinical evaluation of large language models and threats to the reproducibility and replicability of studies about large language models in medicine due to corporate interests.

Uncertainty, Evidence, and the Integration of Machine Learning into Medical Practice

In light of recent advances in machine learning for medical applications, the automation of medical diagnostics is imminent. That said, before machine learning algorithms find their way into clinical practice, various problems at the epistemic level need to be overcome. In this paper, we discuss different sources of uncertainty arising for clinicians trying to evaluate the trustworthiness of algorithmic evidence when making diagnostic judgments. Thereby, we examine many of the limitations of current machine learning algorithms (with deep learning in particular) and highlight their relevance for medical diagnostics. Among the problems we inspect are the theoretical foundations of deep learning (which are not yet adequately understood), the opacity of algorithmic decisions, and the vulnerabilities of machine learning models, as well as concerns regarding the quality of medical data used to train the models. Building on this, we discuss different desiderata for an uncertainty amelioration strategy that ensures that the integration of machine learning into clinical settings proves to be medically beneficial in a meaningful way.

Randomised controlled trials in medical AI: ethical considerations

In recent years, there has been a surge of high-profile publications on applications of artificial intelligence (AI) systems for medical diagnosis and prognosis. While AI provides various opportunities for medical practice, there is an emerging consensus that the existing studies show considerable deficits and are unable to establish the clinical benefit of AI systems. Hence, the view that the clinical benefit of AI systems needs to be studied in clinical trials-particularly randomised controlled trials (RCTs)-is gaining ground. However, an issue that has been overlooked so far in the debate is that, compared with drug RCTs, AI RCTs require methodological adjustments, which entail ethical challenges. This paper sets out to develop a systematic account of the ethics of AI RCTs by focusing on the moral principles of clinical equipoise, informed consent and fairness. This way, the objective is to animate further debate on the (research) ethics of medical AI.

Enabling Fairness in Healthcare Through Machine Learning

The use of machine learning systems for decision-support in healthcare may exacerbate health inequalities. However, recent work suggests that algorithms trained on sufficiently diverse datasets could in principle combat health inequalities. One concern about these algorithms is that their performance for patients in traditionally disadvantaged groups exceeds their performance for patients in traditionally advantaged groups. This renders the algorithmic decisions unfair relative to the standard fairness metrics in machine learning. In this paper, we defend the permissible use of affirmative algorithms; that is, algorithms trained on diverse datasets that perform better for traditionally disadvantaged groups. Whilst such algorithmic decisions may be unfair, the fairness of algorithmic decisions is not the appropriate locus of moral evaluation. What matters is the fairness of final decisions, such as diagnoses, resulting from collaboration between clinicians and algorithms. We argue that affirmative algorithms can permissibly be deployed provided the resultant final decisions are fair.

Can Robots Do Epidemiology? Machine Learning, Causal Inference, and Predicting the Outcomes of Public Health Interventions

This paper argues that machine learning (ML) and epidemiology are on collision course over causation. The discipline of epidemiology lays great emphasis on causation, while ML research does not. Some epidemiologists have proposed imposing what amounts to a causal constraint on ML in epidemiology, requiring it either to engage in causal inference or restrict itself to mere projection. We whittle down the issues to the question of whether causal knowledge is necessary for underwriting predictions about the outcomes of public health interventions. While there is great plausibility to the idea that it is, conviction that something is impossible does not by itself motivate a constraint to forbid trying. We disambiguate the possible motivations for such a constraint into definitional, metaphysical, epistemological, and pragmatic considerations and argue that “Proceed with caution” (rather than “Stop!”) is the outcome of each. We then argue that there are positive reasons to proceed, albeit cautiously. Causal inference enforces existing classification schema prior to the testing of associational claims (causal or otherwise), but associations and classification schema are more plausibly discovered (rather than tested or justified) in a back-and-forth process of gaining reflective equilibrium. ML instantiates this kind of process, we argue, and thus offers the welcome prospect of uncovering meaningful new concepts in epidemiology and public health—provided it is not causally constrained.

How competitors become collaborators-Bridging the gap(s) between machine learning algorithms and clinicians

For some years, we have been witnessing a steady stream of high-profile studies about machine learning (ML) algorithms achieving high diagnostic accuracy in the analysis of medical images. That said, facilitating successful collaboration between ML algorithms and clinicians proves to be a recalcitrant problem that may exacerbate ethical problems in clinical medicine. In this paper, we consider different epistemic and normative factors that may lead to algorithmic overreliance within clinical decision-making. These factors are false expectations, the miscalibration of uncertainties, non-explainability, and the socio-technical context within which the algorithms are utilized. Moreover, we identify different desiderata for bridging the gap between ML algorithms and clinicians. Further, we argue that there is an intriguing dialectic in the collaboration between clinicians and ML algorithms. While it is the algorithm that is supposed to assist the clinician in diagnostic tasks, successful collaboration will also depend on adjustments on the side of the clinician.

On the ethics of algorithmic decision-making in healthcare

In recent years, a plethora of high-profile scientific publications has been reporting about machine learning algorithms outperforming clinicians in medical diagnosis or treatment recommendations. This has spiked interest in deploying relevant algorithms with the aim of enhancing decision-making in healthcare. In this paper, we argue that instead of straightforwardly enhancing the decision-making capabilities of clinicians and healthcare institutions, deploying machines learning algorithms entails trade-offs at the epistemic and the normative level. Whereas involving machine learning might improve the accuracy of medical diagnosis, it comes at the expense of opacity when trying to assess the reliability of given diagnosis. Drawing on literature in social epistemology and moral responsibility, we argue that the uncertainty in question potentially undermines the epistemic authority of clinicians. Furthermore, we elucidate potential pitfalls of involving machine learning in healthcare with respect to paternalism, moral responsibility and fairness. At last, we discuss how the deployment of machine learning algorithms might shift the evidentiary norms of medical diagnosis. In this regard, we hope to lay the grounds for further ethical reflection of the opportunities and pitfalls of machine learning for enhancing decision-making in healthcare.

Targeting Lymph Node Retrieval and Assessment in Stage II Colon Cancer: A Quality Outcome Community-Based Cancer Center Study

PURPOSE

Adequate lymph node evaluation is required for the proper staging of colon cancer. The current recommended number of lymph nodes that should be retrieved and assessed is 12.

METHODS

The multidisciplinary Gastrointestinal Tumor Board at the Derrick L. Davis Forsyth Regional Cancer Center reviewed and recommended that a minimum of 12 lymph nodes be examined in all cases of colon cancer to ensure proper staging. This recommendation occurred at the end of the first quarter of 2005. To ensure this new standard was being followed, an outcomes study looking at the number of lymph nodes evaluated in stage II colon cancer was initiated. All patients with stage II colon cancer diagnosed between 2004 and 2006 were reviewed.

RESULTS

There was a statistically significant improvement in the number of stage II colon cancer patients with 12 or more lymph nodes evaluated. Before the Gastrointestinal Tumor Board's recommendation, 49% (40 out of 82 patients) had 12 or more lymph nodes sampled. The median number of lymph nodes evaluated was 11. After the Gastrointestinal Tumor Board's recommendation, 79% (70 out of 88 patients) had 12 or more lymph nodes sampled. The median number of lymph nodes was 16.

CONCLUSION

Multidisciplinary tumor boards can impact the quality of care of patients as demonstrated in this study. Although we do not yet have survival data on these patients, based on the previous literature referenced in this article, we would expect to see an improvement in survival rates in patients with 12 or more nodes retrieved and assessed.

Infusion of palonosetron plus dexamethasone for the prevention of chemotherapy-induced nausea and vomiting

Serotonin (5-HT3) receptor antagonists are the foundation of standard antiemetic care for cancer patients receiving emetogenic chemotherapy. To enhance the efficacy of these supportive care agents, dexamethasone is routinely admixed with the 5-HT3 receptor antagonist, which is administered by intravenous infusion before chemotherapy begins. This phase II study evaluated the safety and efficacy of intravenous palonosetron admixed with dexamethasone to prevent chemotherapy-induced nausea and vomiting (CINV) in patients receiving moderately emetogenic chemotherapy. Cancer patients received palonosetron 0.25 mg plus dexamethasone 8 mg admixed in 50 mL of infusion solution before receiving at least one qualifying chemotherapeutic agent (cyclophosphamide < or = 1,500 mg/m2, doxorubicin > or = 20 mg/m2, carboplatin, or oxaliplatin). Patients used diaries to record nausea and emesis experienced and rescue medications used. Of 32 participants, 27 (84%) had a complete response (no emesis and no rescue medication) during the acute (0-24 hours) interval posttherapy, 19 (59%) had a complete response during the delayed (> 24-120 hours) posttherapeutic interval, and 19 (59%) had a complete response during the overall (0-120 hours) posttreatment interval. A total of 23 patients (72%) had no emetic episodes, 16 (50%) had no nausea, and 21 (66%) used no rescue medication throughout the overall 5-day interval. The combination was well tolerated. Palonosetron plus dexamethasone given as a pretreatment infusion is effective and safe in preventing acute and delayed CINV in patients receiving moderately emetogenic chemotherapy.

Combination therapy for chemotherapy-induced nausea and vomiting in patients receiving moderately emetogenic chemotherapy: palonosetron, dexamethasone, and aprepitant

The objective of this multicenter, phase II, open-label study was to evaluate the safety and efficacy of the newest 5-hydroxytryptamine3 (5-HT3) receptor antagonist, palonosetron, plus dexamethasone and aprepitant in preventing nausea and vomiting in patients receiving moderately emetogenic chemotherapy. Eligible patients received a single intravenous dose of palonosetron (0.25 mg on day 1 of chemotherapy), along with 3 daily oral doses of aprepitant (125 mg on day 1,80 mg on days 2 and 3) and dexamethasone (12 mg on day 1,8 mg on days 2 and 3). Efficacy and safety data were obtained from patient diaries and adverse event reporting. Fifty-eight patients were evaluable; 47% were women with breast cancer and 52% received cyclophosphamide-based chemotherapy. The proportion of patients with complete response (no emesis and no rescue medication) was 88% during the acute (0-24 hours) interval, 78% during the delayed (> 24-120 hours) interval, and 78% during the overall (0-120 hours post chemotherapy) interval. More than 90% of patients during all time intervals had no emetic episodes, and between 57% and 71% of patients reported no nausea during each of the 5 days post chemotherapy. Treatment was well tolerated, with no unexpected adverse events. These data demonstrate that palonosetron in combination with dexamethasone and aprepitant is safe and highly effective in preventing chemotherapy-induced nausea and vomiting in the days following administration of moderately emetogenic chemotherapy.

Postoperative Upper Airway Obstruction After Recovery of the Train of Four Ratio of the Adductor Pollicis Muscle from Neuromuscular Blockade

Anesthetics, and even minimal residual neuromuscular blockade, may lead to upper airway obstruction (UAO). In this study we assessed by spirometry in patients with a train-of-four (TOF) ratio >0.9 the incidence of UAO (i.e., the ratio of maximal expiratory flow and maximal inspiratory flow at 50% of vital capacity [MEF50/MIF50] >1) and determined if UAO is induced by neuromuscular blockade (defined by a forced vital capacity [FVC] fade, i.e., a decrease in values of FVC from the first to the second consecutive spirometric maneuver of > or =10%). Patients received propofol and opioids for anesthesia. Spirometry was performed by a series of 3 repetitive spirometric maneuvers: the first before induction (under midazolam premedication), the second after tracheal extubation (TOF ratio: 0.9 or more), and the third 30 min later. Immediately after tracheal extubation and 30 min later, 48 and 6 of 130 patients, respectively, were not able to perform spirometry appropriately because of sedation. The incidence of UAO increased significantly (P < 0.01) from 82 of 130 patients (63%) at preinduction baseline to 70 of 82 patients (85%) after extubation, and subsequently decreased within 30 min to values observed at baseline (80 of 124 patients, 65%). The mean maximal expiratory flow and maximal inspiratory flow at 50% of vital capacity ratio after tracheal extubation was significantly increased from baseline (by 20%; 1.39 +/- 1.01 versus 1.73 +/- 1.02; P < 0.01), and subsequently decreased significantly to values observed at baseline (1.49 +/- 0.93). A statistically significant FVC fade was not present, and a FVC fade of > or =10% was observed in only 2 patients after extubation. Thus, recovery of the TOF ratio to 0.9 predicts with high probability an absence of neuromuscular blocking drug-induced UAO, but outliers, i.e., persistent effects of neuromuscular blockade on upper airway integrity despite recovery of the TOF ratio, may still occur.

Efficacy and Safety Analysis of Epoetin Alfa in Patients With Small-Cell Lung Cancer: A Randomized, Double-Blind, Placebo-Controlled Trial

Purpose

This randomized, double-blind, placebo-controlled trial (N93-004) evaluated the effects of epoetin alfa on tumor response to chemotherapy and survival in patients with small-cell lung cancer (SCLC).

Patients and Methods

Adult patients with hemoglobin ≤ 14.5 g/dL starting chemotherapy received epoetin alfa 150 U/kg or placebo subcutaneously 3 times weekly until 3 weeks after completion of chemotherapy. Survival was assessed for 3 years. The primary end point was the proportion of patients with complete or partial response after three chemotherapy cycles.

Results

The trial was terminated prematurely after 224 of a projected 400 patients were accrued. Baseline characteristics were similar between groups. Epoetin alfa and placebo patients (n = 109 and n = 115, respectively) had mean baseline hemoglobin of 12.8 g/dL and 13.0 g/dL, respectively. Overall tumor response was similar between the epoetin alfa and placebo groups after three chemotherapy cycles (72% and 67%, respectively; 95% CI of difference, −6% to 18%) and after completion of chemotherapy (60% and 56%, respectively; 95% CI of difference, −9% to 17%). Epoetin alfa and placebo groups had similar median overall survival (10.5 and 10.4 months, respectively) and overall mortality (91.7% and 87.8%, respectively; hazard ratio, 1.172; 95% CI, 0.887 to 1.549; P = .264). Hemoglobin was maintained in the prechemotherapy range in epoetin alfa patients, but decreased substantially in placebo patients. Fewer epoetin alfa patients than placebo patients required transfusion.

Conclusion

These results suggest that in newly diagnosed patients with SCLC epoetin alfa does not affect tumor response to chemotherapy or survival. However, the early trial closure makes these conclusions preliminary.

Double-blind, randomized comparison of the antiemetic efficacy of intravenous dolasetron mesylate and intravenous ondansetron in the prevention of acute cisplatin-induced emesis in patients with cancer. Dolasetron Comparative Chemotherapy-induced Emesis Prevention Group

PURPOSE

To assess the comparative antiemetic efficacy of single-dose intravenous (IV) dolasetron mesylate and ondansetron in preventing cisplatin-induced nausea and vomiting.

PATIENTS AND METHODS

Cancer patients (n = 609) receiving first-course cisplatin chemotherapy were randomized to one of three treatments: 1.8 or 2.4 mg/kg dolasetron mesylate salt (equivalent to 1.3 and 1.8 mg/kg dolasetron base, respectively) or 32 mg ondansetron. Each treatment was infused over 15 minutes, 30 minutes before cisplatin administration. Patients were stratified to cisplatin doses of > or = 70 and less than 91 mg/m2 (n = 368) or > or = 91 mg/m2 (n = 241), administered over < or = 3 hours. Protocol-defined efficacy criteria included complete response (zero emetic episodes and no rescue medication), major response (1 to 2 emetic episodes and no rescue medication), and patients' report of nausea severity and satisfaction recorded on a 100-mm visual analog scale (VAS).

RESULTS

The three treatments met protocol-specified criteria for equivalence. Complete response rates for dolasetron mesylate 1.8 mg/kg, 2.4 mg/kg, and ondansetron, respectively, were 49.2%, 45.6%, and 50.4% for patients in the lower cisplatin stratum (mean, 74.7 mg/m2) and 36.8%, 31.3%, and 31.8% in the higher cisplatin stratum (mean, 100.6 mg/m2). No significant differences were observed in the extent of nausea with either dolasetron dose compared with ondansetron. Less nausea was noted with 1.8 mg/kg dolasetron compared with the 2.4 mg/kg dose (P = .044) All three antiemetic treatments were well tolerated. Asymptomatic electrocardiogram changes were recorded with both dolasetron and ondansetron.

CONCLUSION

A single IV dose of dolasetron mesylate (1.8 or 2.4 mg/kg) has comparable safety and efficacy to a single 32-mg IV dose of ondansetron in patients receiving cisplatin chemotherapy.

Efficacy and tolerability of oral ondansetron versus prochlorperazine in the prevention of emesis associated with cyclophosphamide-based chemotherapy and maintenance of health-related quality of life

This study compared the efficacy and tolerability of oral ondansetron (8 mg twice daily [BID] for up to 3 days) with those of phenothiazine prochlorperazine (10 mg BID for up to 3 days) in 133 cancer patients receiving cyclophosphamide-based chemotherapy. In addition, the study evaluated the impact of these treatments on patients' health-related quality of life, measured with both the Functional Living Index-Cancer and the Functional Living Index-Emesis questionnaires. The first dose of study drug was administered 30 minutes before initiation of chemotherapy. Patients received a rescue antiemetic at their request or if the investigator deemed it necessary. There was a statistically significant difference in the number of patients with no emetic episodes over the 3-day study period: 60% in the ondansetron group compared with 21% in the prochlorperazine group. Twenty-five percent of ondansetron-treated patients compared with 68% of prochlorperazine-treated patients experienced three or more emetic episodes, rescue medication use, or withdrawal from the study due to emesis or adverse events. Among patients with at least one emetic episode, the mean time to emesis was significantly longer (13 hours and 37 minutes) in the ondansetron group compared with the prochlorperazine group (9 hours and 30 minutes). Nausea and appetite scores did not differ significantly between groups. The score on the vomiting subscale of the Functional Living Index-Emesis was significantly more favorable in the ondansetron group compared with the prochlorperazine group, indicating better maintenance of health-related quality of life in ondansetron-treated patients. Both treatments were well tolerated. The most common potentially drug-related adverse event was headache, which occurred in significantly more (16%) ondansetron-treated patients compared with prochlorperazine-treated patients (3%). The results of this study demonstrate that oral ondansetron 8 mg BID for up to 3 days is more effective than prochlorperazine 10 mg BID for up to 3 days in the prevention of emesis associated with moderately emetogenic chemotherapy.

Efficacy and tolerability of oral ondansetron versus prochlorperazine in the prevention of emesis associated with cyclophosphamide-based chemotherapy and maintenance of health-related quality of life

This study compared the efficacy and tolerability of oral ondansetron (8 mg twice daily [BID] for up to 3 days) with those of phenothiazine prochlorperazine (10 mg BID for up to 3 days) in 133 cancer patients receiving cyclophosphamide-based chemotherapy. In addition, the study evaluated the impact of these treatments on patients' health-related quality of life, measured with both the Functional Living Index--Cancer and the Functional Living Index--Emesis questionnaires. The first dose of study drug was administered 30 minutes before initiation of chemotherapy. Patients received a rescue antiemetic at their request or if the investigator deemed it necessary. There was a statistically significant difference in the number of patients with no emetic episodes over the 3-day study period: 60% in the ondansetron group compared with 21% in the prochlorperazine group. Twenty-five percent of ondansetron-treated patients compared with 68% of prochlorperazine-treated patients experienced three or more emetic episodes, rescue medication use, or withdrawal from the study due to adverse events or lack of efficacy of the study drug. Among patients with at least one emetic episode, the mean time to emesis was significantly longer (13 hours and 37 minutes) in the ondansetron group compared with the prochlorperazine group (9 hours and 30 minutes). Nausea and appetite scores did not differ significantly between groups. The score on the vomiting subscale of the Functional Living Index--Emesis was significantly more favorable in the ondansetron group compared with the prochlorperazine group, indicating better maintenance of health-related quality of life in ondansetron-treated patients. Both treatments were well tolerated. The most common potentially drug-related adverse event was headache, which occurred in significantly more (16%) ondansetron-treated patients compared with prochlorperazine-treated patients (3%). The results of this study demonstrate that oral ondansetron 8 mg BID for up to 3 days is more effective than prochlorperazine 10 mg BID for up to 3 days in the prevention of emesis associated with moderately emetogenic chemotherapy.

Leucovorin and high-dose fluorouracil in metastatic prostate cancer. A phase II trial of the piedmont Oncology Association

We performed a Phase II trial of oral leucovorin and high-dose fluorouracil (5FU) in hormone refractory patients with metastatic prostate cancer who had not had prior chemotherapy. 5FU was given as a 24-hour infusion at a dosage of 4 g/m2 and oral leucovorin at a dosage of 50 mg every 6 hours for four doses, starting with the infusion of 5FU. Fifteen patients were treated and three were not evaluable for response. There were no complete (CR) or partial responses (PR) in 12 evaluable patients (95% confidence interval for CR+PR of 0 to 26%). Three patients had stable disease and the remainder progressed. Toxicities were generally mild to moderate, but one patient died of sepsis while neutropenic. This dose and schedule of leucovorin and 5FU is not better than single-agent 5FU in patients with metastatic prostate cancer.

Neoglycoprotein binding to colorectal tumour cells: comparison between primary and secondary lesions

Biotinylated neoglycoproteins are useful to determine the expression of sugar receptors (lectins) histochemically in routinely processed tissue sections. Assessment of the presence of distinct receptor classes with specificity to beta-galactosides and to alpha- or beta-N-acetylgalactosamine, selected on the basis of their potential relevance for recognition processes within the metastatic cascade in murine model systems, was performed for a common human tumour type, colorectal cancer. The four different types of neoglycoproteins, derived from covalent attachment of commercially available derivatives of beta-N-acetylgalactosamine, differed only quantitatively in their capacity to detect specific binding on cultured cells and tissue sections, thus posing no major restriction on the choice of synthetic process for histochemical efficiency of the product. Glycocytological application revealed specific probe binding and a regulation of level of receptor expression for a human colon carcinoma cell line primarily for N-acetylgalactosamine-specific receptors upon retinoic acid-induced differentiation. Monitoring of sections of the 12 cases of primary and secondary colorectal lesions invariably disclosed the presence of the respective receptors, the extent of cell labelling in primary tumours and metastases being similar. Establishment of metastases, even in different target organs, is apparently not followed by a major phenotypic variation in this feature.

Metabolism and excretion of etoposide in isolated, perfused rat liver models

The clearance of etoposide and formation of etoposide glucuronide have been measured in an isolated, perfused rat liver model to evaluate the effect of impaired hepatic function on etoposide kinetics. Hepatocellular injury was produced by pretreatment of rats with allyl alcohol or carbon tetrachloride; ligation of the bile duct simulated obstructive biliary disease. Etoposide clearance (3.59 +/- 1.06 ml/min) was reduced by both carbon tetrachloride (2.07 +/- 0.64 ml/min; P = 0.05) and allyl alcohol treatment (2.14 +/- 0.62 ml/min; P = 0.05). Biliary obstruction also impaired etoposide clearance but to a lesser extent than hepatocellular injury (2.47 +/- 0.69 ml/min; P = 0.20 versus control). In both hepatocellular and obstructive models, direct biliary etoposide excretion decreased. The metabolic clearance of etoposide to its glucuronide declined by 36% in the hepatotoxin models but was not decreased by biliary obstruction. Following hepatic injury, there is a reduction in the metabolism and excretion of etoposide by the liver. This effect is most marked on biliary drug excretion. Obstructive biliary disease does not significantly alter etoposide glucuronidation. Since most cancer patients have increased bilirubin on the basis of obstructive disease, little or no etoposide dose alteration will be needed. However, in the patient with significant hepatocellular injury, impaired etoposide clearance will be more pronounced, and etoposide dose alterations may be needed.